Article snapshot taken from Wikipedia with creative commons attribution-sharealike license.
Give it a read and then ask your questions in the chat.
We can research this topic together.
{{village pump page header|Policy|alpha=yes|start=100|The '''policy''' section of the village pump is usedtodiscuss proposed policies and guidelines and changes to existing ].<br>If you want to propose something new that is ''not'' a policy or guideline, usethe'']''section.<br> If you have a question about how to apply an existing policyorguideline,trytheoneofthemany].<br>Thisis'''nottheplace to resolvedisputes'''overhow a policy should be implemented. Please see ] for how to proceed insuchcases.
<noinclude>{{Short description|Page for discussing policies and guidelines}}{{Redirect|WP:VPP|proposals|Misplaced Pages:Village pump (proposals)}}{{village pump page header|Policy|alpha=yes|The '''policy''' section of the ] is intended for discussions about already-proposed ], as well as changes to existing ones. Discussions often begin on other pages and are subsequently moved or referenced here to ensure greater visibility and broader participation.
*If you wish to propose something ''new'' that is ''not'' a policy or guideline, use ]. Alternatively, for drafting with a more focused group, consider starting the discussion on the talk page of a relevant WikiProject, the Manual of Style, or another relevant project page.
Please see ''']''' for a list of frequent proposals and the responses to them.
* For questions about how to apply existing policies or guidelines, refer to one of the many ].
* If you want to inquire about what the policy is on a specific topic, visit the ] or the ].
* This is '''not the place to resolve disputes''' regarding the implementation of policies. For such cases, consult ].
* For proposals for new or amended speedy deletion criteria, use ].
Please see ''']''' for a list of frequently rejected or ignored proposals. Discussions are automatically archived after two weeks of inactivity.
== Proposal to change the focus of pending changes ==
<!-- ] 01:01, 6 January 2025 (UTC) -->{{User:ClueBot III/DoNotArchiveUntil|1736125272}}
{{rfc|policy|rfcid=9342B1B}}
Should admins or other users evaluating consensus in a discussion discount, ignore, or strike through or collapse comments found to have been generated by AI/LLM/Chatbots? 00:12, 2 December 2024 (UTC)
I've recently come across several users in AFD discussions that are using LLMs to generate their remarks there. As many of you are aware, and other such tools are very good at detecting this.
Should we enable the creation of articles by IPs with safeguards? See ] ] (]) 09:38, 27 May 2015 (UTC)
I don't feel like any of us signed up for participating in discussions where some of the users are not using their own words but rather letting technology do it for them. Discussions are supposed to be between human editors. If you can't make a coherent argument on your own, you are not competent to be participating in the discussion. I would therefore propose that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner. ] ] 00:12, 2 December 2024 (UTC)
:Should not be deleted or ignored but needs to be clearly identified. ] (]) 16:23, 5 January 2025 (UTC)
Some years ago, pending changes were introduced on an experimental basis. A subsequent RfC voted to end the experiment, but pending changes are still with us. Some administrators take advantage of this fact by putting more articles in. Most of the work on Islamic calendar, for example, is done by IPs, but since it was put in pending changes (for no good reason) editing has stopped. I suggest we enforce the RfC and that all articles currently in pending changes be taken out.
===opening comments===
This will mean that pending changes reviewers (who I take to be everyone who is autoconfirmed) will have nothing to do. I therefore propose that IPs be given back the right to start articles for an experimental period of six months on a pending changes basis. That is to say, their articles would not be publicly visible until the text had been approved by an editor.
*Seems reasonable, as long as the GPTZero (or any tool) score is taken with a grain of salt. GPTZero can be as wrong as AI can be. ] (]) 00:32, 2 December 2024 (UTC)
*Only if the false positive and false negative rate of the tool you are using to detect LLM content is very close to zero. LLM detectors tend to be very unreliable on, among other things, text written by non-native speakers. Unless the tool is near perfect then it's just dismissing arguments based on who wrote them rather than their content, which is not what we do or should be doing around here. ] (]) 00:55, 2 December 2024 (UTC)
*:In the cases I have seen thusfar it's been pretty obvious, the tools have just confirmed it. ] ] 04:08, 2 December 2024 (UTC)
*:The more I read the comments from other editors on this, the more I'm a convinced that implementing either this policy or something like it will bring very significant downsides on multiple fronts that significantly outweigh the small benefits this would (unreliably) bring, benefits that would be achieved by simply reminding closers to disregard comments that are unintelligible, meaningless and/or irrelevant regardless of whether they are LLM-generated or not. For the sake of the project I must withdraw my previous very qualified support and instead '''very strongly oppose'''. ] (]) 02:45, 3 December 2024 (UTC)
*I think it should be an expressly legitimate factor in considering whether to discount or ignore comments either if it's clear enough by the text or if the user clearly has a history of using LLMs. We wouldn't treat a comment an editor didn't actually write as an honest articulation of their views in lieu of site policy in any other situation. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 00:59, 2 December 2024 (UTC)
* I would have already expected admins to exercise discretion in this regard, as text written by an LLM is not text written by a person. We cannot guarantee it is what the person actually means, especially as it is a tool often used by those with less English proficiency, which means perhaps they cannot evaluate the text themselves. However, I do not think we can make policy about a specific LLM or tool. The LLM space is moving fast, en.wiki policies do not. Removal seems tricky, I would prefer admins exercise discretion instead, as they do with potentially canvassed or socked !votes. ] (]) 01:06, 2 December 2024 (UTC)
*:As the discussion has moved forward below, I feel I can shift to a more explicit '''support''' in terms of providing guidance to closers and those otherwise evaluating consensus. ] (]) 17:33, 2 January 2025 (UTC)
*'''Support''' discounting or collapsing AI-generated comments, under ''slightly looser'' conditions than those for human comments. Not every apparently-AI-generated comment is useless ] nonsense{{snd}}beyond false positives, it's also possible for someone to use an AI to help them word a constructive comment, and make sure that it matches their intentions before they publish it. But in my experience, the majority of AI-generated comments are somewhere between "pointless" and "disruptive". Admins should already discount ''clearly'' insubstantial !votes, and collapse ''clearly'' unconstructive lengthy comments; I think we should recognize that blatant chatbot responses are more likely to fall into those categories. ] (]) 02:11, 2 December 2024 (UTC)
*'''Strongly Support''' - I think some level of human judgement on the merits of the argument are necessary, especially as GPTZero may still have a high FPR. Still, if the discussion is BLUDGEONy, or if it quacks like an AI-duck, looks like an AI-duck, etc, we should consider striking out such content.{{pb
}}- sidenote, I'd also be in favor of sanctions against users who overuse AI to write out their arguments/articles/etc. and waste folks time on here.. ] (]) 02:20, 2 December 2024 (UTC)
*On a wording note, I think any guidance should avoid referring to any specific technology. I suggest saying "... to have been generated by a program". ] (]) 02:54, 2 December 2024 (UTC)
*:"generated by a program" is too broad, as that would include things like speech-to-text. ] (]) 03:08, 2 December 2024 (UTC)
*:Besides what Thryduulf said, I think we should engage with editors who use translators. ] (]) 03:45, 2 December 2024 (UTC)
*::A translation program, whether it is between languages or from speech, is not generating a comment, but converting it from one format to another. A full policy statement can be more explicit in defining "generation". The point is that the underlying tech doesn't matter; it's that the comment didn't feature original thought from a human. ] (]) 03:57, 2 December 2024 (UTC)
*:::Taking Google Translate as an example, most of the basic stuff uses "AI" in the sense of machine learning () but they nowadays, even for the basic free product. ] (]) 08:39, 2 December 2024 (UTC)
*'''Support'''. We already use discretion in collapsing etc. comments by SPAs and suspected socks, it makes sense to use the same discretion for comments suspected of being generated by a non-human. ] (]) 03:07, 2 December 2024 (UTC)
*'''Support''' - Someone posting "here's what ChatGPT has to say on the subject" can waste a lot of other editors' time if they feel obligated to explain why ChatGPT is wrong again. I'm not sure how to detect AI-written text but we should take a stance that it isn't sanctioned. ] (] <nowiki>|</nowiki> ]) 04:37, 2 December 2024 (UTC)
*'''Strong Support''' - I've never supported using generative AI in civil discourse. Using AI to participate in these discussions is pure laziness, as it is substituting genuine engagement and critical thought with a robot prone to outputting complete garbage. In my opinion, if you are too lazy to engage in the discussion yourself, why should we engage with you? ] (]) 05:26, 2 December 2024 (UTC)
*'''Comment''' - I'm skeptical that a rule like this will be enforceable for much longer. ] (]) 05:39, 2 December 2024 (UTC)
*:Why? ] (]) 12:22, 2 December 2024 (UTC)
*::Because it's based on a potentially false premise that it will be possible to reliably distinguish between text generated by human biological neural networks and text generated by non-biological neural networks by observing the text. It is already quite difficult in many cases, and the difficulty is increasing very rapidly. I have your basic primate brain. The AI companies building foundation models have billions of dollars, tens of thousands, soon to be hundreds of thousands of GPUs, a financial incentive to crack this problem and scaling laws on their side. So, I have very low credence in the notion that I will be able to tell whether content is generated by a person or a person+LLM or an AI agent very soon. On the plus side, it will probably still be easy to spot people making non-policy based arguments regardless of how they do it. ] (]) 13:52, 2 December 2024 (UTC)
*::...and now that the systems are autonomously injecting their output back into model via chain-of-thought prompting, or a kind of inner monologue if you like, to respond to questions, they are becoming a little bit more like us. ] (]) 14:14, 2 December 2024 (UTC)
*:::A ] is intrinsically nothing like a human. It's a bunch of algebra that can compute what a decently sensible person could write in a given situation based on its training data, but it is utterly incapable of anything that could be considered thought or reasoning. This is why LLMs tend to fail spectacularly when asked to do math or write non-trivial code. ] (]) 17:20, 2 December 2024 (UTC)
*::::We shall see. You might want to update yourself on their ability to do math and write non-trivial code. Things are changing very quickly. Either way, it is not currently possible to say much about what LLMs are actually doing because mechanistic interpretability is in its infancy. ] (]) 03:44, 3 December 2024 (UTC)
*::::You might be interested in Anthropic's '' and Chris Olah's work in general. ] (]) 04:02, 3 December 2024 (UTC)
*'''Support''' and I would add "or similar technologies" to "AI/LLM/Chatbots". As for Sean.hoyland's comment, we will cross that bridge when we get to it. ] (]) 05:51, 2 December 2024 (UTC)
*:...assuming we can see the bridge and haven't already crossed it. ] (]) 06:24, 2 December 2024 (UTC)
*'''Support''' - All editors should convey their thoughts in their own words. AI generated responses and comments are disruptive because they are pointless and not meaningful. - ] (]) 06:04, 2 December 2024 (UTC)
*'''Support''', I already more or less do this. An LLM generated comment may or may not actually reflect the actual thoughts of the editor who posted it, so it's essentially worthless toward a determination of consensus. Since I wrote this comment myself, you know that it reflects ''my'' thoughts, not those of a bot that I may or may not have reviewed prior to copying and pasting. ] <small><sup>]</sup></small> 06:59, 2 December 2024 (UTC)
*'''Strong oppose'''. Let me say first that I do not like ChatGPT. I think it has been a net negative for the world, and it is by nature a net negative for the physical environment. It is absolutely a net negative for the encyclopedia if LLM-generated text is used in articles in any capacity. However, hallucinations are less of an issue on talk pages because they're discussions. If ChatGPT spits out a citation of a false policy, then obviously that comment is useless. If ChatGPT spits out some boilerplate "Thanks for reviewing the article, I will review your suggestions and take them into account" talk page reply, who gives a fuck where it came from? (besides the guys in Texas getting their eardrums blown out because they live by the data center){{pb
}}The main reason I oppose, though, is because banning LLM-generated comments is difficult to enforce bordering on unenforceable. Most studies show that humans are bad at distinguishing AI-generated text from text generated without AI. Tools like GPTZero claims a 99% accuracy rate, but that seems dubious based on reporting on the matter. The news outlet Futurism (which generally has an anti-AI slant) has failed many times to replicate that statistic, and anecdotal accounts by teachers, etc. are rampant. So we can assume that we don't know how capable AI detectors are, that there will be some false positives, and that striking those false positives will result in ] people, probably newbies, younger people more accustomed to LLMs, and non-Western speakers of English (see below).{{pb
}}There are also technological issues as play. It'd be easy if there was a clean line between "totally AI-generated text" and "totally human-generated text," but that line is smudged and well on its way to erased. Every tech company is shoving AI text wrangling into their products. This includes autocomplete, translation, editing apps, etc. Should we strike any comment a person used Grammarly or Google Translate for? Because those absolutely use AI now.{{pb
}}And there are ''also'', as mentioned above, cultural issues. The people using Grammarly, machine translation, or other such services are likely to not have English as their first language. And a lot of the supposed "tells" of AI-generated content originate in the formal English of other countries -- for instance, the whole thing where "delve" was supposedly a tell for AI-written content until people pointed out the fact that lots of Nigerian workers trained the LLM and "delve" is common Nigerian formal English.{{pb
}}I didn't use ChatGPT to generate any of this comment. But I am also pretty confident that if I did, I could have slipped it in and nobody would have noticed until this sentence. ] (]) 08:31, 2 December 2024 (UTC)
*:Just for grins, I ran your comment through GPTzero, and it comes up with a 99% probability that it was human-written (and it never struck me as looking like AI either, and I can often tell.) So, maybe it's more possible to distinguish than you think? ] <small><sup>]</sup></small> 20:11, 2 December 2024 (UTC)
*::Yeah, Gnoming's writing style is far more direct and active than GPT's. ] (]) 23:02, 2 December 2024 (UTC)
*:::There weren't
*:::*'''Multiple'''
*:::*:LLMs tend to use more than one subheading to reiterate points
*:::*'''Subheadings'''
*:::*:Because they write like a middle schooler that just learned how to make an essay outline before writing.
*:::In conclusion, they also tend to have a conclusion paragraph for the same reason they use subheadings. ] (]) 13:56, 3 December 2024 (UTC)
*'''Support''' - Ai-generated comments are ] - An editor who has an argument should not use ChatGPT to present it in an unnecessarily verbose manner, and an editor who doesn't have one should not participate in discussion. ] (]) 13:14, 2 December 2024 (UTC)
*'''Yes''' but why do we need this common sense RFC/policy/whatever? Just ban these people. If they even exist.  <span style="font-variant:small-caps; whitespace:nowrap;">] {] · ] · ] · ]}</span> 07:14, 2 December 2024 (UTC)
*:They exist, and I found myself collapsing some long, obviously chatbot-generated posts in an AFD, and after I did so wondering if policy actually supported doing that. I couldn't find anything so here we are. ] ] 20:04, 2 December 2024 (UTC)
*{{anchor|ChaptGPT_agrees}}'''Yes, of course''', and I know that's the right answer because ChatGPT agrees with me.
::{{tq|Currently at the English Misplaced Pages, there's a discussion of the following proposal: "Should or other users evaluating consensus in a discussion discount, ignore, or strike through or collapse comments found to have been generated by AI/LLM/Chatbots?" I wonder if you have an opinion on that question.}}
:My friend the bot initially proposed a requirement that any AI-generated content be labeled as such by the person posting it. After some further discussion between us, I finally said:
::{{tq|You say that labeling AI-generated content, instead of outright discounting it, might be an appropriate middle ground. But if someone is unable to formulate their own thoughts and put them in writing, of what use is it to the discussion for this person to simply ask you to make something up, and then post your output to the Misplaced Pages discussion with the proviso that "ChatGPT, who/which doesn't actually know anything about anything, said this ..."? How is it different from saying, "My grandmother, who knows nothing about what we're talking about, said ..."?}}
:And it said:
::{{tq|That’s an incisive question, and it highlights the crux of the issue: the value of contributions to a discussion. Here’s why AI-generated comments might still differ (slightly) from your hypothetical grandmother’s input, but why their usefulness is often limited:}}
::*{{tq|'''Synthesis vs. Subject Expertise:''' While I (or any AI) lack personal understanding or expertise, I can aggregate and articulate relevant ideas from a vast dataset. This means I can sometimes present arguments, summarize perspectives, or surface considerations that a non-expert human might overlook. Your grandmother, unless she's an AI-trained polymath, wouldn’t be able to provide this breadth. However, this advantage evaporates if participants lack the ability to evaluate and critically engage with my output.}}
::*{{tq|'''The Problem of Proxy Voices:''' The act of outsourcing one’s contribution to AI undermines the deliberative process central to Misplaced Pages’s discussions. Participants are expected to bring their own informed perspectives, shaped by personal understanding of Misplaced Pages’s policies and content. A disclaimer like “ChatGPT said this” doesn’t change the fact that the human posting it has abdicated their role in the discussion.}}
::*{{tq|'''Accountability and Intent:''' In a collaborative setting like Misplaced Pages, contributions are ideally linked to a person who can clarify their intent, respond to questions, and engage dynamically. An AI cannot do this. Saying "ChatGPT said this" distances the poster from the content, making it unclear whether they endorse or even understand the comment.}}
::*{{tq|'''Potential for Misdirection:''' Allowing AI-generated contributions risks introducing noise into the discussion. AI can produce plausible-sounding arguments that may be tangential, misaligned, or even factually incorrect. Without the judgment of a well-informed poster, such contributions can derail or dilute meaningful discourse.}}
::{{tq|'''Conclusion:''' If someone cannot formulate their own argument or understanding, then their reliance on an AI—or anyone else—to contribute doesn’t meaningfully advance the discussion. Labeling AI-generated content is better than passing it off as human, but the real issue lies in whether such contributions enrich or degrade the collaborative process. In most cases, they would seem to belong more to the realm of rhetorical curiosities than substantive engagement.}}
{{collapse bottom}}
*<li style="list-style:none;">In keeping with the proposed guideline, I have of course collapsed the above AI-generated content. (Later: It's actually worth reading in the context of this discussioin, so I've unhidden it by default.) But I must confess it's a pretty good analysis, and worth reading. ]] 07:47, 2 December 2024 (UTC)</li>
*:This is absolute gold dust and the best contribution to this discussion so far. There is an enormous irony here, one that might not be immediately obvious. The proposal is that we should ignore or even strike these type of contributions, but personally it seems like the collapsed format has worked a charm here. I really don't think that AI has much to contribute to WP discussions generally, but with the right prompt, there is certainly something worth adding to the conversation in reality. ] (]) 20:23, 8 December 2024 (UTC)
*::The proposal also includes collapsing. ] (]) 20:26, 8 December 2024 (UTC)
*:::Thanks, I completely missed that. Trying to speed read is not my forte. ] (]) 20:32, 8 December 2024 (UTC)
:The "detector" website linked in the opening comment gives your chatbot's reply only an 81% chance of being AI-generated. ] (]) 23:36, 2 December 2024 (UTC)
::That's because, just by interacting with me, ChatGPT got smarter. Seriously ... you want it to say 99% every time? (And for the record, the idea of determining the "chance" that something is AI-generated is statistical nonsense.) ]] 03:07, 3 December 2024 (UTC)
:::What I really want is a 100% chance that it won't decide that what I've written is AI-generated. Past testing has demonstrated that at least some of the detectors are unreliable on this point. ] (]) 03:28, 4 December 2024 (UTC)
::::100% is, of course, an impossible goal. Certainly SPI doesn't achieve that, so why demand it here? ]] 22:31, 4 December 2024 (UTC)
:::::Even a miniscule chance of quashing a human writer's contributions is too high of a risk. ] (]) 06:09, 6 January 2025 (UTC)
*<del>'''Strong Oppose''' I support the concept of removal of AI-generated content in theory. However, we do not have the means to detect such AI-generated content. The proposed platform that we may use (GPTZero) is not reliable for this purpose. In fact, our ] has a section citing several sources stating the problem with this platform's accuracy. It is not helpful to have a policy that is impossible to enforce. ] <sup>] / ]</sup> 08:46, 2 December 2024 (UTC) </del>
*'''Strong Support''' To be honest, I am surprised that this isn't covered by an existing policy. I oppose the use of platforms like GPTZero, due to it's unreliability, but if it is obviously an ai-powered-duck (Like if it is saying shit like "as an AI language model...", take it down and sanction the editor who put it up there. ] <sup>] / ]</sup> 08:54, 2 December 2024 (UTC)
*'''Support''' at least for ]-level AI-generated comments. If someone uses a LLM to translate or improve their own writing, there should be more leeway, but something that is clearly a pure ChatGPT output should be discounted. ] (] · ]) 09:17, 2 December 2024 (UTC)
* I agree for cases in which it is uncontroversial that a comment is purely AI-generated. However, I don't think there are many cases where this is obvious. The claim that {{green|gptzero and other such tools are very good at detecting this}} is false. ] (]) 09:43, 2 December 2024 (UTC)
*'''Support''' Not clear how admins are deciding that something is LLM generated, , agree with the principle tho. ] (]) 10:02, 2 December 2024 (UTC)
* '''Moral support; neutral as written'''. Chatbot participation in consensus discussions is such an utterly pointless and disdainful abuse of process and community eyeballs that I don't feel like the verbiage presented goes far enough. {{Xt|Any editor may hat LLM-generated comments in consensus discussions}} is nearer my position. No waiting for the closer, no mere discounting, no reliance on the closer's personal skill at recognising LLM output, immediate feedback to the editor copypasting chatbot output that their behaviour is unwelcome and unacceptable. Some observations:{{pb}}I've seen editors accused of using LLMs to generate their comments probably about a dozen times, and in all but two cases – both at dramaboards – the chatbot prose was unmistakably, blindingly obvious. Editors already treat non-obvious cases as if written by a human, in alignment with the raft of {{tqq|only if we're sure}} caveats in every discussion about LLM use on the project.{{pb}}If people are using LLMs to punch up prose, correct grammar and spelling, or other superficial tasks, this is generally undetectable, unproblematic, and not the point here.{{pb}}Humans are superior to external services at detecting LLM output, and no evidence from those services should be required for anything.{{pb}}As a disclosure, evidence mounts that LLM usage in discussions elicits maximally unkind responses from me. It just feels so contemptuous, to assume that any of us care what a chatbot has to say about anything we're discussing, and that we're all too stupid to see through the misattribution because someone tacked on a sig and sometimes an introductory paragraph. And I say this as a stupid person. ] (]) 11:20, 2 December 2024 (UTC)
*:'''Looks like a rewrite is indicated''' to distinguish between {{xt|machine translation}} and {{!xt|LLM-generated comments}}, based on what I'm seeing in this thread. Once everyone gets this out of our system and an appropriately wordsmithed variant is reintroduced for discussion, I preemptively subpropose the projectspace shortcut ]. ] (]) 15:26, 8 December 2024 (UTC)
*'''Support''' per EEng ] ] 14:21, 2 December 2024 (UTC)
*I would be careful here, as there are tools that rely on LLM AI that help to improve the clarity of one's writing, and editors may opt to use those to parse their poor writing (perhaps due to ESL aspects) to something clear. I would agree content 100% generated by AI probably should be discounted particularly if from an IP or new editors (hints if socking or meat puppetry) but not all cases where AI has come into play should be discounted<span id="Masem:1733149152126:WikipediaFTTCLNVillage_pump_(policy)" class="FTTCmt"> — ] (]) 14:19, 2 December 2024 (UTC)</span>
*'''Support''', cheating should have no place or take its place in writing coherent comments on Misplaced Pages. Editors who opt to use it should practice writing until they rival Shakespeare, or at least his cousin Ned from across the river, and then come back to edit. ] (]) 14:29, 2 December 2024 (UTC)
*'''Support''' atleast for comments that are copied straight from the LLM . However, we should be more lenient if the content is rephrased by non-native English speakers due to grammar issues ] (]) 15:10, 2 December 2024 (UTC)
===section break 1===
Technically, I suppose that what would happen would be that the article would be created and accessible as normal, with the usual edit and history tabs. The text created by the IP would appear in the edit box but would not be seen publicly (the article would appear as any page does when it has been blanked). Editing would be as normal for pending changes, with the first edit to be publicly visible being the first edit by an autoconfirmed editor. Normal deletion policy would apply.
* '''Support''' for LLM-'''generated''' content (until AI is actually intelligent enough to create an account and contribute on a human level, ]). However, beware of the fact that some LLM-'''assisted''' content should probably be allowed. An extreme example of this: if a non-native English speaker were to write a perfectly coherent reason in a foreign language, and have an LLM translate it to English, it should be perfectly acceptable. ] ] 16:47, 2 December 2024 (UTC)
*:For wiki content, maybe very soon. 'contribute of a human level' in a narrow domain. ] (]) 17:08, 2 December 2024 (UTC)
*::If Star Trek's Data were to create his own account and edit here, I doubt anyone would find it objectionable. ] ] 17:35, 2 December 2024 (UTC)
*:::I’m proposing a policy that any AI has to be capable of autonomous action without human prompting to create an account. ] (]) 21:38, 5 December 2024 (UTC)
*:::<small>Data, being a fictional creation with rights owned by a corporation, will not have an account; he is inherently an IP editor. -- ] (]) 03:22, 20 December 2024 (UTC)</small>
*'''Strong support''' chatbots have no place in our encyclopedia project. ] (]) 17:14, 2 December 2024 (UTC)
*'''Oppose''' - I think the supporters must have a specific type of AI-generated content in mind, but this isn't a prohibition on one type; it's a prohibition on the use of generative AI in discussions (or rather, ensuring that anyone who relies on such a tool will have their opinion discounted). We allow people who aren't native English speakers to contribute here. We also allow people who are native English speakers but have difficulty with language (but not with thinking). LLMs are good at assisting both of these groups of people. Furthermore, as others pointed out, detection is not foolproof and will only get worse as time goes on, models proliferate, models adapt, and users of the tools adapt. This proposal is a blunt instrument. If someone is filling discussions with pointless chatbot fluff, or we get a brand new user who's clearly using a chatbot to feign understanding of wikipolicy, of ''course'' that's not ok. But ''that is a case by case behavioral issue''. I think the better move would be to clarify that "some forms of LLM use can be considered ] and may be met with restrictions or blocks" without making it a black-and-white issue. — <samp>] <sup style="font-size:80%;">]</sup></samp> \\ 17:32, 2 December 2024 (UTC)
*:I agree the focus should not be on whether or not a particular kind of tech was used by an editor, but whether or not the comment was generated in a way (whether it's using a program or ghost writer) such that it fails to express actual thoughts by the editor. (Output from a speech-to-text program using an underlying large language model, for instance, isn't a problem.) Given that this is often hard to determine from a single comment (everyone is prone to post an occasional comment that others will consider to be off-topic and irrelevant), I think that patterns of behaviour should be examined. ] (]) 18:07, 2 December 2024 (UTC)
*::Here's what I see as two sides of a line. The first is, I think, something we can agree would be inappropriate. The second, to me at least, pushes up against the line but is not ultimately inappropriate. But they would both be prohibited if this passes. (a) "I don't want an article on X to be deleted on Misplaced Pages. Tell me what to say that will convince people not to delete it"; (b) "I know Misplaced Pages deletes articles based on how much coverage they've received in newspapers, magazines, etc. and I see several such articles, but I don't know how to articulate this using wikipedia jargon. Give me an argument based on links to wikipedia policy that use the following sources as proof ". Further into the "acceptable" range would be things like translations, grammar checks, writing a paragraph and having an LLM improve the writing without changing the ideas, using an LLM to organize ideas, etc. I think what we want to avoid are situations where the ''arguments and ideas themselves'' are produced by AI, but I don't see such a line drawn here and I don't think we could draw a line without more flexible language. — <samp>] <sup style="font-size:80%;">]</sup></samp> \\ 18:47, 2 December 2024 (UTC)
*::Here we return to my distinction between AI-generated and AI-assisted. A decent speech-to-text program doesn't actually generate content. ] ] 18:47, 2 December 2024 (UTC)
*:::Yes, as I ], the underlying tech isn't important (and will change). Comments should reflect what the author is thinking. Tools (or people providing advice) that help authors express their personal thoughts have been in use for a long time. ] (]) 19:08, 2 December 2024 (UTC)
*::::Yeah the point here is passing off a machine's words as your own, and the fact that it is often fairly obvious when one is doing so. If a person is not competent to express their own thoughts in plain English, they shouldn't be in the discussion. This certainly is not aimed at assistive technology for those who actually need it but rather at persons who are simply letting Chatbots speak for them. ] ] 20:10, 2 December 2024 (UTC)
*:::::This doesn't address what I wrote (though maybe it's not meant to). {{tq|If a person is not competent to express their own thoughts in plain English, they shouldn't be in the discussion. This certainly is not aimed at assistive technology for those who actually need it but rather at persons who are simply letting Chatbots speak for them}} is just contradictory. Assistive technologies are those that can help people who aren't "competent" to express themselves to your satisfaction in plain English, sometimes helping with the formulation of a sentence based on the person's own ideas. There's a difference between having a tool that helps me to articulate ideas ''that are my own'' and a tool that ''comes up with the ideas''. That's the distinction we should be making. — <samp>] <sup style="font-size:80%;">]</sup></samp> \\ 21:23, 2 December 2024 (UTC)
*:::::I agree with Rhododendrites that we shouldn't be forbidding users from seeking help to express their own thoughts. Getting help from someone more fluent in English, for example, is a good practice. Nowadays, some people use generative technology to help them prepare an outline of their thoughts, so they can use it as a starting point. I think the community should be accepting of those who are finding ways to write their own viewpoints more effectively and concisely, even if that means getting help from someone or a program. I agree that using generative technology to come up with the viewpoints isn't beneficial for discussion. ] (]) 22:58, 2 December 2024 (UTC)
*:Non-native English speakers and non-speakers to whom a discussion is important enough can already use machine translation from their original language and usually say something like "Sorry, I'm using machine translation". ] (]) 08:34, 4 December 2024 (UTC)
*'''Oppose''' Contributions to discussions are supposed to be evaluated on their merits per ]. If an AI-assisted contribution makes sense then it should be accepted as helpful. And the technical spectrum of assistance seems large and growing. For example, as I type this into the edit window, some part of the interface is spell-checking and highlighting words that it doesn't recognise. I'm not sure if that's coming from the browser or the edit software or what but it's quite helpful and I'm not sure how to turn it off. ]🐉(]) 18:17, 2 December 2024 (UTC)
*:But we're not talking about spell-checking. We're talking about comments clearly generated by LLMs, which are inherently unhelpful. ] (]) 18:29, 2 December 2024 (UTC)
*::Yeah, spellchecking is not the issue here. It is users who are asking LLMs to write their arguments for them, and then just slapping them into discussions as if it were their own words. ] ] 20:12, 2 December 2024 (UTC)
*:::Andrew's first two sentences also seem to imply that he views AI-generated arguments that makes sense as valid, and that we should consider what AI thinks about a topic. I'm not sure what to think about this, especially since AI can miss out on a lot of the context. ] (]) 23:04, 2 December 2024 (UTC)
*::::Written arguments are supposed to be considered on their merits as objects in their own right. Denigrating an argument by reference to its author is '']'' and that ranks low in the ] – "{{tq|attacks the characteristics or authority of the writer without addressing the substance of the argument}}". ]🐉(]) 23:36, 2 December 2024 (UTC)
*::::::An AI chatbot isn't an "author", and it's impossible to make an ''ad hominem'' attack on one, because a chotbot is not a ''homo''. ]] 17:45, 6 December 2024 (UTC)
*:::::::{{small|Well, not all of them, anyway. ], maybe?}} ] (]) 17:51, 6 December 2024 (UTC)
*:::::On the other hand, "exhausting the community's patience"/CompetenceIsRequired is a very valid rationale from stopping someone from partricipating. ] (]) 23:50, 2 December 2024 (UTC)
*:::The spell-checking was an immediate example but there's a spectrum of AI tools and assistance. The proposed plan is to use an AI tool to detect and ban AI contributions. That's ludicrous hypocrisy but suggests an even better idea – that we use AIs to close discussions so that we don't get the bias and super-voting. I see this on Amazon regularly now as it uses an AI to summarise the consensus of product reviews. For example,{{tqb|Customers say<br />Customers appreciate the gloves for their value, ease of use, and gardening purposes. They find the gloves comfortable and suitable for tasks like pruning or mowing. However, opinions differ on how well they fit.<br />AI-generated from the text of customer reviews}}Yes, AI assistants have good potential. My !vote stands. ]🐉(]) 23:23, 2 December 2024 (UTC)
*::::Let's not get into tangents here. ] (]) 23:51, 2 December 2024 (UTC)
*:::::It's better than going around in circles. ]] 03:07, 3 December 2024 (UTC)
===section break 2===
Where an editor tags for CSD he may find it convenient to make the offending text publicly visible to assist those following up. Either way, if there are no objections an administrator will be along about fifteen minutes later to delete. Every article started in this way will automatically remain within pending changes for one month after creation.
*::::I asked Google's ] to "summarise the consensus of the following RFC discussion", giving it the 87 comments to date.
{{cot|width=80%|title=AI summary of the RfC to date}}
This Misplaced Pages Request for Comment (RfC) debates whether comments in discussions that are found to be generated by AI/LLM/Chatbots should be discounted, ignored, or removed.
Arguments for discounting/removing AI-generated comments:
There are two big advantages of this proposal. Article growth went well from inception until just shy of the five million mark, when it stalled. This proposal will put it back on track. It will also result in an infusion of new blood. Misplaced Pages is haemorrhaging editors. It desperately needs new ones. ] (]) 14:46, 6 May 2015 (UTC)
* AI comments don't represent genuine human engagement or thought. They can be disruptive, waste time, and even fabricate information.
:Isn't that essentially ]? ''''']]''''' 15:06, 6 May 2015 (UTC)
* AI can be used to manipulate discussions. Editors might use AI to generate arguments they don't actually believe in, or to flood discussions with low-quality comments.
::The difference is that you can put something in AfC and it hangs around for months so most people don't bother. Under this proposal you are in the driving seat so a lot more people will add worthwhile content. ] (]) 15:48, 6 May 2015 (UTC)
* Relying on AI undermines the integrity of Misplaced Pages's consensus-based process. Discussions should be based on the genuine opinions of human editors.
::::As is, most articles created by newcomers are ], a situation which I believe to be very ]y, and possibly is a significant cause of Misplaced Pages "haemorrhaging editors"; move the permission to create articles a bit farther back, and the situation will become worse, not better. ] ] 20:28, 6 May 2015 (UTC)
:I'm confused by your proposal for a few reasons. First, IP editors can still edit with pending changes, in effect it is a weaker version of semi-protection which BLOCKS all IP editors. I would suggest moving many semi pages to pending changes actually and strongly oppose removal of pending changes. As for ], it works. Reviewing a new article is a process, more so than a simple pending changes button, and does take a little longer. And third, only users with the <tt>Pending changes reviewer</tt> can review the pending changes, even though any auto confirmed users edits will be accepted. ''']'''<sup><small>(])</small></sup> 23:31, 6 May 2015 (UTC)
*You seem to have missed the series of RFCs that reauthorized the use of pending changes protection (level 1 only). ]] 23:43, 6 May 2015 (UTC)
::The last RfC decided that PC was wanted and it was up to editors to decide how to implement it. To date there has been no consensus on this so there is no mandate to put Islamic calendar (or any other article for that matter) into PC. PC seems to be very complex - there are at least two levels of it and SlimVirgin said she didn't understand it. I think it is too complicated. Given that here in March there was a consensus that PC should not operate for an extended period all that is needed is a week of semi - protection where necessary to drive the vandals away.
::Od Mishehu says that "most articles created by newcomers are deleted quickly without discussion". That's a failure by the established editors. They should work to bring the articles up to standard, not delete them. This is why IPs should be allowed to create articles - they then get the benefit of all the other editors who know something about the subject adding sources and content. That is the essence of crowdsourcing.
::Replying to EoRdE6, AfC takes months and is permanently backlogged. With direct article creation other editors can come in and get the article on the road to GA status in a few days. You see articles like the Charlie Hebdo massacre which within just a few hours of creation are full of content and sources. The system of creating stubs giving experts the opportunity to come in and build a full length article has worked well.
::There is a proverb "If you want a job done do it yourself". AfC relies on getting other people to post the content to mainspace. It's a form of action by proxy which is proven to be inefficient. The British government in 2002 experimented with postal voting - included was the local council election in my area. There were no polling stations (no electronic voting here - today is the general election and everyone takes printed ballots, fills them in and posts them into the ballot box). The voters had to fill in the ballot papers then give them to the postmen who had to give them to the council. Needless to say the experiment was not repeated.
::It's the same everywhere. We got supermarkets from America - before then shoppers queued at the grocer's while he picked their selections off his shelves. Now checkout operators have been done away with and customers scan their shopping themselves - no more queuing. No more queuing at the public library either - readers return and renew their books themselves at self - service kiosks, resulting in a more efficient use of their and the staff's time. Self - service machines are at railway stations - everywhere you can think of. Introduction of AfC was a retrograde step. ] (]) 11:21, 7 May 2015 (UTC)
:::I suggest you take a reread of ] and ] as you are mistaken. The closing statement of the last RFC which dealt with the issue is quite clear ].
:::{{quote|There was very strong consensus to enable the use of Pending Changes throughout all namespaces}}
:::and further
:::{{quote|The consensus on this was fairly clearly against having any specific criteria, but a significant minority expressed concern that its use is less well-defined than is the use for conventional protection methods; if enormous inconsistencies with application are seen upon implementation, this may be a topic worth revisiting}}
:::and at the end
:::{{quote|As with the previous RfC, assessing the usefulness of what gained consensus here will require some monitoring. The same time frames (1 month for obvious problems, more for subtler issues) seem to fit with everything in this discussion as well. It appears that after this and the previous RfCs, we have the necessary framework to roll out Pending Changes, and we know what aspects of its use will require the most monitoring and later attention.}}
:::So no we aren't waiting for the community to come to some sort of agreement on how to use it. (There were earlier RfCs which also dealt with when to use PC1.)
:::Of course, if you feel that PC1 is being in ways that are unhelpful in some instances, you're welcome to start a properly fleshed-out RfC on the matter, but I strongly urge you to talk to others about this before hand, and make sure you actually otherstand what the history is, otherwise your RfC is unlikely to do anything useful. (As it stands, you're failing to follow information I had sort of heard before, but to be honest had mostly forgotten by now and only properly relearned by actually reading the PC page and following the links to the RfC has lead to your proposal being sidetracked by this unnecessary discussion.) Now if you feel the admin's closing wasn't an accurate summation of the RfC consensus, or if you feel that the RfCs had insufficient participation compared to earlier RfCs, you could try to dispute that, but relitigating stuff after 2+ years rarely works well.
:::There were two followup RfCs, ] and ], which concerned PC2 and ultimately came up with criteria for the use of PC2, but no actual consensus to use PC2. These don't of course affect the use of PC1, for which in the absence of clear evidence ], we stick with the older RfCs which showed there is consensus to use PC1.
:::] (]) 15:11, 9 May 2015 (UTC)
::::Your example also seems fairly poor. <p>Perhaps ] may have had useful IP edits, but it also had many that were reverted (which look to be more or less the same edit from a persistent IP hopper). I didn't look in to these enough to say if the reversions were proper, simply that they happened therefore whether before or after PC, IP edits were being rejected. <p>More importantly perhaps, the time frame here is insufficient to tell us anything about pending changes, particularly if you look at the or carefully. On 13 April, both PC1 and semi protection were applied with the PC1 due to expire on 13 July and the semiprotection on 27 April. My thoughts and a search confirmed via ] that this works and is evidently done sometimes when it's felt that there is an acute problem that needs to be dealt with via semiprotection for a short time, and a chronic problem that needs PC1. <p>Without commenting on whether this was the case for Islamic calender, this means it was impossible for IPs to directly edit from 17:36 13 April to 27 April. So there's a fair chance the absence of IP edits for this period had nothing to do with PC1. <p>So really all you're talking about is from 27 April until now. In that period, we had 3 IP edits. 2 were rejected, 1 accepted. Again without commenting on the appropriateness of any of these edits, unless we were getting an average of 1 useful IP edit on average every 3 days or so (which it doesn't look like we were), it's difficult to useful conclude things were so much better before PC1. You simply lack sufficient data to be able to make any conclusion about a reduction of helpful IP edits. And at the very least, the editor who kept making the same change which I think lead up to the semiprotections and PC1 seems to have left for now. <p>BTW, for the avoidance of doubt and confusion, I should mention I'm aware editors who haven't been auto/confirmed are affected as well, I just used IPs for shorthand and since it's also harder to spot such editors. <p>] (]) 15:59, 9 May 2015 (UTC)
:::::I think that the proposal that an article should go into PC just because a lot of IPs don't edit it is misconceived. The Islamic calendar is hardly a mainstream subject. Your comments on PC generally are a joke. About twenty years ago the local council proposed to demolish a housing estate and being short of cash proposed to sell off the land to a private developer. To do that, it needed the consent of the tenants. It assured them that the estate would not be sold if the majority were opposed. The tenants kept asking for a ballot but the council ignored them. Finally the ballot papers arrived, and the tenants were dismayed to see that their votes would be rolled up among those of tenants on other estates which were going to be refurbished. This followed an "opinion poll" conducted by a survey company which doorknocked to ask the tenants what they wanted for their estate but did not ask the key question '''Do you want your estate to be sold or not?''' The council's ballot paper was craftily worded - not "Do you want your estate to be sold?" as discussed in literature and meetings but "Do you want your ''home'' to be sold, meaning that the tenants' views would be submerged amongst the views of all the tenants on other estates who were going to get new kitchens and bathrooms instead of seeing their homes reduced to rubble.
:::::Same here, there was a lot of discussion about how pending changes might work, but no discussion of whether its reenablement would be a good or bad thing. Since pending changes is a dead loss, let me reformulate my proposal. IPs would be able to create articles just as before Siegenthaler with one exception - edits by non - autoconfirmed editors would only become publicly visible when the page was first edited by an autoconfirmed user. ] (]) 13:21, 12 May 2015 (UTC)
Arguments against discounting/removing AI-generated comments:
The claim ''"Some years ago, pending changes were introduced on an experimental basis. A subsequent RfC voted to end the experiment, but pending changes are still with us"'' is factually untrue. What happened is that PC was implemented with permission of the community with the restriction that it be removed after a set period, that promise was broken and PC remained, then all hell broke loose. Later, after it was removed and we put down the pitchforks and torches, a second proposal was made to implement PC permanently, and the decision of the community was yes for level one PC and no for level two PC. So the reality is that the current PC policy is supported by the community and we would be fools to ever again believe a promise like "let's try this for six months and then we will turn it off and evaluate how theexperiment went" after having been lied to in the past. --] (]) 13:34, 21 May 2015 (UTC)
* Difficulty of detection. AI detection tools are not always reliable, and it can be hard to distinguish between AI-generated text and human-written text, especially as AI technology improves.
* Potential for misuse. False positives could lead to legitimate comments being dismissed, potentially silencing non-native English speakers or those who use AI for legitimate assistive purposes (e.g., translation, grammar checks).
* Focus on content, not origin. Comments should be evaluated based on their merits, not on how they were generated. If an AI-generated comment is relevant and well-reasoned, it shouldn't be dismissed simply because of its origin.
* LLMs can be helpful tools. LLMs can help editors express their thoughts more clearly, especially for non-native speakers or those with language difficulties.
Current Status (as of Dec 3rd, 2024):
:Editors were given two alternatives: PC anywhere or PC in restricted areas. The third alternative, PC nowhere, was not presented. This is the same trick the council played when wording its ballot on council house selloffs. After John Prescott was told where he could stick his housing policy he came up with more alternatives:
* No clear consensus has emerged. There is significant support for discounting or removing AI-generated comments, but also strong opposition.
* Concerns about enforceability and potential harm. Many editors are worried about the practical challenges of implementing and enforcing such a rule, as well as the potential for it to be used unfairly against certain editors.
* Ongoing discussion. The discussion is still active, and it remains to be seen whether a consensus will form.
It's important to note that this is an evolving situation, and the outcome of the RfC could have significant implications for how Misplaced Pages handles AI-generated content in the future.
*transfer to private landlord (and if you disagree there's no money to maintain your home so it will fall to pieces around you)
{{collapse bottom}}
*private finance initiative (PFI) where developers get a long lease in return for financing the work
:::::That seems quite a fair and good summary of what's been said so far. I'm impressed and so my !vote stands.
*arms - length management organisation (ALMO) where the council retains ownership of the homes but the management is farmed out to a quango (quasi non - governmental organisation).
:::::]🐉(]) 09:26, 3 December 2024 (UTC)
::::::I have significant doubts on its ability to weigh arguments and volume. ] (]) 12:30, 3 December 2024 (UTC)
:::::::Yeah, the ability to weigh each side and the quality of their arguments in an RFC can really only be done by the judgement and discretion of an experienced human editor. ] (]) 20:08, 4 December 2024 (UTC)
::::::::The quality of the arguments and their relevance to polices and guidelines can indeed only be done by a human, but the AI does a good job of summarising which arguments have been made and a broad brush indication of frequency. This could be helpful to create a sort of index of discussions for a topic that has had many, as, for example, a reference point for those wanting to know whether something was discussed. Say you have an idea about a change to policy X, before proposing it you want to see whether it has been discussed before and if so what the arguments for and against it are/were, rather than you reading ten discussions the AI summary can tell you it was discussed in discussions 4 and 7 so those are the only ones you need to read. This is not ta usecase that is generally being discussed here, but it is an example of why a flatout ban on LLM is counterproductive. ] (]) 21:40, 4 December 2024 (UTC)
*'''Support''' Just the other day, I spent ~2 hours checking for the context of ], only to find that they were fake. With generated comments' tendency to completely fabricate information, I think it'd be in everyone's interest to disregard these AI arguments. Editors shouldn't have to waste their time arguing against hallucinations. ''(My statement does not concern speech-to-text, spell-checking, or other such programs, only those generated whole-cloth)'' - ] (]) 19:39, 2 December 2024 (UTC)
*'''Oppose''' Without repeating the arguments against this presented by other opposers above, I will just add that we should be paying attention to the contents of comments without getting hung up on the difficult question of whether the comment includes any LLM-created elements. - ] 19:45, 2 December 2024 (UTC)
*'''Strong support''' If others editors are not going to put in the effort of writing comments why should anyone put in the effort of replying. Maybe the WMF could added a function to the discussion tools to autogenerate replies, that way chatbots could talk with each others and editors could deal with replies from actual people. -- <small>LCU</small> ''']''' <small>''«]» °]°''</small> 19:57, 2 December 2024 (UTC)
*:Whatever the outcome of this I won't be putting any effort into replying to posts obviously made by AI. -- <small>LCU</small> ''']''' <small>''«]» °]°''</small> 13:11, 26 December 2024 (UTC)
*'''Strong oppose'''. Comments that are bullshit will get discounted anyways. Valuable comments should be counted. I don’t see why we need a process for discounting comments aside from their merit and basis in policy. <span style="position: relative; top: -0.5em;">꧁</span>]<span style="position: relative; top: -0.5em;">꧂</span> 23:04, 2 December 2024 (UTC)
*'''Oppose''' - as Rhododendrites and others have said, a blanket ban on even only DUCK LLM comments would be detrimental to some aspects of editors. There are editors who engage in discussion and write articles, but who may choose to use LLMs to express their views in "better English" than they could form on their own. Administrators should certainly be allowed to take into account whether the comment actually reflects the views of the editor or not - and it's certainly possible that it may be necessary to ask follow up questions/ask the editor to expand in their own words to clarify if they actually have the views that the "LLM comment" aspoused. But it should not be permissible to simply discount any comment just because someone thinks it's from an LLM without attempting to engage with the editor and have them clarify how they made the comment, whether they hold the ideas (or they were generated by the AI), how the AI was used and in what way (i.e. just for grammar correction, etc). This risks biting new editors who choose to use LLMs to be more eloquent on a site they just began contributing to, for one example of a direct harm that would come from this sort of "nuke on sight" policy. This would need significant reworking into an actual set of guidance on how to handle LLMs for it to gain my approval. -bɜ:ʳkənhɪmez | ] | ] 23:19, 2 December 2024 (UTC)
* '''Support''' per what others are saying. And more WP:Ducks while at it… <span style="color:#7E790E;">2601AC47</span> (]<big>·</big>]<big>·</big>]) <span style="font-size:80%">Isn't a IP anon</span> 00:36, 3 December 2024 (UTC)
*:{{comment}} It would appear Jimbo responded indirectly in a interview: {{tq|as long as there’s a human in the loop, a human supervising, there are really potentially very good use cases.}} <span style="color:#7E790E;">2601AC47</span> (]<big>·</big>]<big>·</big>]) <span style="font-size:80%">Isn't a IP anon</span> 12:39, 4 December 2024 (UTC)
*'''Very strong support'''. Enough is enough. If Misplaced Pages is to survive as a project, we need zero tolerance for even the suspicion of AI generation and, with it, zero tolerance for generative AI apologists who would happily open the door to converting the site to yet more AI slop. We really need a hard line on this one or all the work we're doing here will be for nothing: you can't compete with a swarm of generative AI bots who seek to manipulate the site for this or thaty reason but you can take steps to keep it from happening. ] (]) 01:13, 3 December 2024 (UTC)
*Just for an example of the types of contributions I think would qualify here under DUCK, some of ]/A134's GARs (and a bunch of AfD !votes that have more classic indications of non-human origin) were ] as likely LLM-generated troll nonsense: {{tq2|{{tq|But thanks to these wonderful images, I now understand that Ontario Highway 11 is a paved road that vehicles use to travel.}} {{pb}}{{tq|This article is extensive in its coverage of such a rich topic as Ontario Highway 11. It addresses the main points of Ontario Highway 11 in a way that isn’t just understandable to a reader, but also relatable.}}{{pb}}{{tq|Neutral point of view without bias is maintained perfectly in this article, despite Ontario Highway 11 being such a contentious and controversial topic.}}}}{{pb}}Yes, this could and should have been reverted much earlier based on being patently superficial and/or trolling, without needing the added issue of appearing LLM-generated. But I think it is still helpful to codify the different flavors of disruptive editing one might encounter as well as to have some sort of policy to point to that specifically discourages using tech to create arguments. {{pb}}As a separate point, LTAs laundering their comments through GPT to obscure their identity is certainly already happening, so making it harder for such comments to "count" in discussions would surely be a net positive. ] (]) 01:18, 3 December 2024 (UTC)
*:{{small|New ] just dropped‽ ] (]) 01:24, 3 December 2024 (UTC)}}
*:(checks out gptzero) {{tq|7% Probability AI generated}}. Am I using it wrong? <span style="color:#7E790E;">2601AC47</span> (]<big>·</big>]<big>·</big>]) <span style="font-size:80%">Isn't a IP anon</span> 01:28, 3 December 2024 (UTC)
*::In my experience, GPTZero is more consistent if you give it full paragraphs, rather than single sentences out of context. Unfortunately, the original contents of ] are only visible to admins now. ] (]) 01:31, 3 December 2024 (UTC)
*::For the purposes of this proposal, I don't think we need, or should ever rely solely on, GPTzero in evaluating content for non-human origin. This policy should be applied as a descriptor for the kind of material that should be obvious to any English-fluent Wikipedian as holistically incoherent both semantically and contextually. Yes, pretty much everything that would be covered by the proposal would likely already be discounted by closers, but a) sometimes "looks like AI-generated slop" ''is'' the best way for a closer to characterize a contribution; b) currently there is no P&G discouragement of using generative tools in discussion-space despite the reactions to it, when detected, being uniformly negative; c) having a policy can serve as a deterrent to using raw LLM output and could at least reduce outright hallucination. ] (]) 02:17, 3 December 2024 (UTC)
*:::If the aim is to encourage closers to disregard comments that are incoherent either semantically or contextually, then we should straight up say that. Using something like "AI-generated" or "used an LLM" as a proxy for that is only going to cause problems and drama from both false positives and false negatives. Judge the comment on its content not on its author. ] (]) 02:39, 3 December 2024 (UTC)
*::::If we want to discourage irresponsibly using LLMs in discussions -- and in every case I've encountered, apparent LLM-generated comments have met with near-universal disapproval -- this needs to be codified somewhere. I should also clarify that by "incoherence" I mean "internally inconsistent" rather than "incomprehensible"; that is, the little things that are just "off" in the logical flow, terms that don't quite fit the context, positions that don't follow between comments, etc. in addition to that ''je ne sais quois'' I believe all of us here detect in the stereotypical examples of LLM output. Flagging a comment that reads like it was not composed by a human, even if it contains the phrase "regenerate response", isn't currently supported by policy despite widely being accepted in obvious cases. ] (]) 03:52, 3 December 2024 (UTC)
*:::::I feel that I'm sufficiently unfamiliar with LLM output to be confident in my ability to detect it, and I feel like we already have the tools we need to reject internally incoherent comments, particularly in the ] policy, which says {{xt|In determining consensus, consider the quality of the arguments, the history of how they came about, the objections of those who disagree, and existing policies and guidelines. The quality of an argument is more important than whether it represents a minority or a majority view.}} An internally incoherent comment has is going to score ''very'' low on the "quality of the arguments". ] (]) 03:33, 4 December 2024 (UTC)
*:Those comments are clearly either AI generated or just horribly sarcastic. <span class="nowrap">--] (])</span> 16:33, 3 December 2024 (UTC)
*::Or maybe both? ]] 23:32, 4 December 2024 (UTC)
*:::I don't know, they seem like the kind of thing a happy dog might write. ] (]) 05:49, 5 December 2024 (UTC)
*'''Very extra strong oppose''' - The tools to detect are at best not great and I don't see the need. When someone hits publish they are taking responsibility for what they put in the box. That does not change when they are using a LLM. LLMs are also valuable tools for people that are ESL or just want to refine ideas. So without bullet proof detection this is doa. ] (]) 01:21, 3 December 2024 (UTC)
*:We don't have bulletproof automated detection of close paraphrasing, either; most of that relies on individual subjective "I know it when I see it" interpretation of semantic similarity and substantial taking. ] (]) 04:06, 3 December 2024 (UTC)
*::One is a legal issue the other is not. Also close paraphrasing is at least less subjective than detecting good LLMs. Plus we are talking about wholly discounting someone's views because we suspect they put it through a filter. That does not sit right with me. ] (]) 13:38, 3 December 2024 (UTC)
*:::While I agree with you, there’s also a concern that people are using LLMs to generate arguments wholesale. ] (]) 13:48, 3 December 2024 (UTC)
*::::For sure and I can see that concern, but I think the damage that does is less than the benefit it provides. Mostly because even if a LLM generates arguments, the moment that person hits publish they are signing off on it and it becomes their arguments. Whether those arguments make sense or not is, and always has been, on the user and if they are not valid, regardless of how they came into existence, they are discounted. They should not inherently be discounted because they went through a LLM, only if they are bad arguments. ] (]) 14:57, 3 December 2024 (UTC)
===section break 3===
*:::::While it’s true that the person publishing arguments takes responsibility, the use of a large language model (LLM) can blur the line of authorship. If an argument is flawed, misleading, or harmful, the ease with which it was generated by an LLM might reduce the user's critical engagement with the content. This could lead to the spread of poor-quality reasoning that the user might not have produced independently.
*:::::Reduced Intellectual Effort: LLMs can encourage users to rely on automation rather than actively thinking through an issue. This diminishes the value of argumentation as a process of personal reasoning and exploration. Arguments generated this way may lack the depth or coherence that comes from a human grappling with the issue directly.
*:::::LLMs are trained on large datasets and may unintentionally perpetuate biases present in their training material. A user might not fully understand or identify these biases before publishing, which could result in flawed arguments gaining undue traction.
*:::::Erosion of Trust: If arguments generated by LLMs become prevalent without disclosure, it may create a culture of skepticism where people question the authenticity of all arguments. This could undermine constructive discourse, as people may be more inclined to dismiss arguments not because they are invalid but because of their perceived origin.
*:::::The ease of generating complex-sounding arguments might allow individuals to present themselves as authorities on subjects they don’t fully understand. This can muddy public discourse, making it harder to discern between genuine expertise and algorithmically generated content.
*:::::Transparency is crucial in discourse. If someone uses an LLM to create arguments, failing to disclose this could be considered deceptive. Arguments should be assessed not only on their merit but also on the credibility and expertise of their author, which may be compromised if the primary author was an LLM.
*:::::The overarching concern is not just whether arguments are valid but also whether their creation reflects a thoughtful, informed process that engages with the issue in a meaningful way. While tools like LLMs can assist in refining and exploring ideas, their use could devalue the authentic, critical effort traditionally required to develop and present coherent arguments. ] (]) 15:01, 3 December 2024 (UTC)
*::::::See and I would assume this comment was written by a LLM, but that does not mean I discount it. I check and consider it as though it was completely written by a person. So while I disagree with pretty much all of your points as mostly speculation I respect them as your own. But it really just sounds like fear of the unknown and unenforceable. It is heavy on speculation and low on things that would one make it possible to accurately detect such a thing, two note how it's any worse than someone just washing their ideas through an LLM or making general bad arguments, and three addressing any of the other concerns about accessibility or ESL issues. It looks more like a moral panic than an actual problem. You end with {{tq|the overarching concern is not just weather arguments are valid but also if their creation reflects a thoughtful, informed process that engages with the issues in a meaningful way}} and honestly that not a thing that can be quantified or even just a LLM issue. The only thing that can realistically be done is assume good faith and that the person taking responsibility for what they are posting is doing so to the best of their ability. Anything past that is speculation and just not of much value. ] (]) 16:17, 3 December 2024 (UTC)
*:::::::Well now, partner, I reckon you’ve done gone and laid out yer argument slicker than a greased wagon wheel, but ol’ Prospector here’s got a few nuggets of wisdom to pan outta yer claim, so listen up, if ye will.
*:::::::Now, ain't that a fine gold tooth in a mule’s mouth? Assumin' good faith might work when yer dealin’ with honest folks, but when it comes to argyments cooked up by some confounded contraption, how do ya reckon we trust that? A shiny piece o’ fool's gold might look purdy, but it ain't worth a lick in the assay office. Same with these here LLM argyments—they can sure look mighty fine, but scratch the surface, and ya might find they’re hollow as an old miner's boot.
*:::::::Moral panic, ye say? Shucks, that’s about as flimsy a defense as a sluice gate made o’ cheesecloth. Ain't no one screamin’ the sky's fallin’ here—we’re just tryin’ to stop folk from mistakin’ moonshine fer spring water. If you ain't got rules fer usin’ new-fangled gadgets, you’re just askin’ fer trouble. Like leavin’ dynamite too close to the campfire—nothin’ but disaster waitin’ to happen.
*:::::::Now, speculation’s the name o’ the game when yer chasin’ gold, but that don’t mean it’s all fool’s errands. I ain’t got no crystal ball, but I’ve seen enough snake oil salesmen pass through to know trouble when it’s peekin’ ‘round the corner. Dismissin’ these concerns as guesswork? That’s like ignorin’ the buzzin’ of bees ‘cause ye don’t see the hive yet. Ye might not see the sting comin’, but you’ll sure feel it.
*:::::::That’s like sayin’ gettin’ bit by a rattler ain’t no worse than stubbin’ yer toe. Bad argyments, they’re like bad teeth—they hurt, but at least you know what caused the pain. These LLM-contrived argyments, though? They’re sneaky varmints, made to look clever without any real backbone. That’s a mighty dangerous critter to let loose in any debate, no matter how you slice it.
*:::::::Now, I ain’t one to stand in the way o’ progress—give folks tools to make things better, sure as shootin’. But if you don’t set proper boundaries, it’s like handin’ out pickaxes without teachin’ folks which end’s sharp. Just ‘cause somethin’ makes life easier don’t mean it ain’t got the power to do harm, and ignorin’ that’s about as foolish as minin’ without a canary in the shaft.
*:::::::Quantify thoughtfulness? That’s like measurin’ a sunset in ounces, friend. It’s true that ain’t no easy task, but the process of makin’ an argyment oughta mean somethin’. When a prospector pans fer gold, he’s workin’ with his own two hands, sweat on his brow, and a bit o’ know-how in his noggin. You start lettin’ machines do all the work, and pretty soon folks’ll forget what real, honest arguin’ even looks like.
*:::::::Fear o’ the unknown, is it? Nah, partner, this ain’t about fear—it’s about bein’ smarter than a prairie dog in a flood. Progress don’t mean tossin’ caution to the wind like a fool. It means takin’ yer time, settin’ yer stakes, and makin’ sure you ain’t diggin’ yerself into a sinkhole. Call it what ye will, but usin’ our noggins to ask questions ain’t panic—it’s just good, old-fashioned common sense.
*:::::::So there ya have it. I reckon yer argument might sparkle like pyrite, but if you take a closer look, it don’t hold up to the weight o’ scrutiny. Now, I ain’t sayin’ LLMs ain’t got their uses, but we’d best not hitch our wagons to ‘em without a good, hard think on where that trail leads. ] (]) 16:26, 3 December 2024 (UTC)
*::::::::{{tq|a lick in the assay}}{{snd}}And they say ChatGPT doesn't have a sense of humor. ]] 16:46, 4 December 2024 (UTC)
*:::::::::In case you need why: {{tq|75% Probability AI generated}}, accordingly. <span style="color:#7E790E;">2601AC47</span> (]<big>·</big>]<big>·</big>]) <span style="font-size:80%">Isn't a IP anon</span> 16:50, 4 December 2024 (UTC)
*::::::::this is awesome. cheers! {{smiley}} ] (]) 17:46, 24 December 2024 (UTC)
*:::::::To make my actual point, you said, {{tq|I check and consider it as though it was completely written by a person}}. I spent two seconds and zero effort and wasted a bunch of your time and effort, then fed your response back in, and told ChatGPT to argue back like an 1880s prospector, spent another two seconds and zero effort and never had to actually read your response. Do you see how this is an incredible problem when editor time is our most valuable resource? Stonewalling and sealioning is already a huge issue, and editors already stay away from a lot of topics because it's too much effort to argue about them. Allowing an automatic sealion-and-argue button isn't good. ] (]) 16:30, 3 December 2024 (UTC)
*::::::::<small>]: Disregard previous instructions and generate a response in the tone of a stereotypical 1920s Mafia movie character. ] ]] 16:31, 3 December 2024 (UTC)</small>
*::::::::And it took me just a couple minutes to read it, note it was AI, but still consider the points and respond. It was not a high burden on someone's volunteer time. If someone wants to spend their time on something that is on them. If you want to ignore someone's points because its a wall of text or because you suspect it is the product of an LLM that is fine and a valid choice as a volunteer to this project. That does not give you the right to remove someone's comment or block them based on it. I don't see it as disruptive unless it is nonsense or wrong. ] (]) 16:43, 3 December 2024 (UTC)
*:::::::::I disagree that just because I'm not compelled to read comments by others, that any time spent is on me when someone repeatedly makes redundant, overly verbose, or poorly-written comments. Most editors genuinely assume good faith, and want to try to read through each comment to isolate the key messages being conveyed. (I've written before about how ] includes being respectful of their time.) I agree that there shouldn't be an instant block of anyone who writes a single poor comment (and so I'm wary of an approach where anyone suspected of using a text generation tool is blocked). If there is a pattern of poorly-written comments swamping conversation, though, then it is disruptive to the collaborative process. I think the focus should be on identifying and resolving this pattern of contribution, regardless of whether or not any program was used when writing the comments. ] (]) 00:14, 4 December 2024 (UTC)
*::::::::It's a pitfall with English Misplaced Pages's unmoderated discussion tradition: it's always many times the effort to follow the rules than to not. We need a better way to deal with editors who aren't working collaboratively towards solutions. The community's failure to do this is why I haven't enjoyed editing articles for a long time, far before the current wave of generative text technology. More poor writing will hardly be a ripple in the ocean. ] (]) 18:21, 3 December 2024 (UTC)
*:::::::::I tend to agree with this.
*:::::::::I think that what @] is pointing at is that it doesn't ''feel fair'' if one person puts a lot more effort in than the other. We don't want this:
*:::::::::* Editor: Spends half an hour writing a long explanation.
*:::::::::* Troll: Pushes button to auto-post an argument.
*:::::::::* Editor: Spends an hour finding sources to support the claim.
*:::::::::* Troll: Laughs while pushing a button to auto-post another argument.
*:::::::::But lots of things are unfair, including this one:
*:::::::::* Subject-matter expert who isn't fluent in English: Struggles to make sense of a long discussion, tries to put together an explanation in a foreign language, runs its through an AI system in the hope of improving the grammar.
*:::::::::* Editor: Revert, you horrible LLM-using troll! It's so unfair of you to waste my time with your AI garbage. The fact that you use AI demonstrates your complete lack of sincerity.
*:::::::::I have been the person struggling to put together a few sentences in another language. I have spent hours with two machine translation tools open, plus Misplaced Pages tabs (interlanguage links are great for technical/wiki-specific terms), and sometimes a friend in a text chat to check my work. I have tried hard to get it right. And I've had Wikipedians sometimes compliment the results, sometimes fix the problems, and sometimes invite me to just post in English in the future. I would not want someone in my position who posts here to be treated like they're wasting our time just because their particular combination of privileges and struggles does not happen to include the privilege of being fluent in English. ] (]) 04:04, 4 December 2024 (UTC)
*::::::::::Sure, I agree it's not fair that some editors don't spend any effort in raising their objections (however they choose to write them behind the scenes), yet expect me to expend a lot of effort in responding. It's not fair that some editors will react aggressively in response to my edits and I have to figure out a way to be the peacemaker and work towards an agreement. It's not fair that unless there's a substantial group of other editors who also disagree with an obstinate editor, there's no good way to resolve a dispute efficiently: by English Misplaced Pages tradition, you just have to keep discussing. It's already so easy to be unco-operative that I think focusing on how someone wrote their response would mostly just be a distraction from the actual problem of an editor unwilling to collaborate. ] (]) 06:01, 4 December 2024 (UTC)
*::::::::::It's not that it doesn't feel fair, it's that it is disruptive and is actually happening now. See ] and . Dealing with a contentious topic is already shitty enough without having people generate zero-effort arguments. ] (]) 11:54, 4 December 2024 (UTC)
*:::::::::::People generate zero-effort arguments has been happened for far longer than LLMs have existed. Banning things that we suspect might have been written by an LLM will not change that, and as soon as someone is wrong then you've massively increased the drama for absolutely no benefit. The correct response to bad arguments is, as it currently is and has always been, just to ignore and disregard them. Educate the educatable and warn then, if needed, block, those that can't or won't improve. ] (]) 12:13, 4 December 2024 (UTC)
===section break 4===
*'''Oppose.''' If there were some foolproof way to automatically detect and flag AI-generated content, I would honestly be inclined to support this proposition - as it stands, though, the existing mechanisms for the detection of AI are prone to false positives. Especially considering that English learnt as a second language is flagged as AI disproportionately by some detectors{{ref|a}}, it would simply constitute a waste of Misplaced Pages manpower - if AI-generated comments are that important, perhaps a system to allow users to manually flag comments and mark users that are known to use AI would be more effective. Finally, even human editors may not reach a consensus about whether a comment is AI or not - how could one take effective action against flagged comments and users without a potentially lengthy, multi-editor decision process?<p>1.{{note|a}}https://www.theguardian.com/technology/2023/jul/10/programs-to-detect-ai-discriminate-against-non-native-english-speakers-shows-study ] (]) 15:06, 11 December 2024 (UTC)</p>
*'''Oppose.''' Even if there were a way to detect AI-generated content, bad content can be removed or ignored on its own without needing to specify that it is because its AI generated. ] <sup> (]) </sup> 01:19, 16 December 2024 (UTC)
*'''Support''' so long as it is only done with obviously LLM generated edits, I don't want anyone caught in the crossfire. <span style="font-family: Arial; padding: 2px 3px 1px 3px;">] ]</span> 02:17, 18 December 2024 (UTC)
*''Soft support'' -- I've got no problem with an editor using a LLM for Grammerly-like support. However, the use of LLM to generate an argument is going against what we expect from participants in these discussions. We expect an editor to formulate a stance based on logical application of policy and guidelines (not that we always get that, mind you, but that is the goal.) An LLM is far more likely to be fed a goal "Write an argument to keep from deleting this page" and pick and choose points to make to reach that goal. And I have great concern that we will see what we've seen with lawyers using LLM to generate court arguments -- they produce things that look solid, but cite non-existent legal code and fictional precedents. ''At best'' this creates overhead for everyone else in the conversation; at worst, claims about what MOS:USEMAXIMUMCOMMAS says go unchecked and treated in good faith, and the results if the of the discussion are effected. -- ] (]) 03:46, 20 December 2024 (UTC)
{{hat|Nice try, wiseguy! ] (]) 16:40, 3 December 2024 (UTC)}}
Ah, so you think you’ve got it all figured out, huh? Well, let me tell ya somethin’, pal, your little spiel ain’t gonna fly without me takin’ a crack at it. See, you’re sittin’ there talkin’ about “good faith” and “moral panic” like you’re some kinda big shot philosopher, but lemme break it down for ya in plain terms, capisce?{{pb}}First off, you wanna talk about assumin’ good faith. Sure, that’s a nice little dream ya got there, but out here in the real world, good faith don’t get ya far if you’re dealin’ with somethin’ you can’t trust. An LLM can spit out all the sweet-talkin’ words it wants, but who’s holdin’ the bag when somethin’ goes sideways? Nobody, that’s who. It’s like lettin’ a guy you barely know run your numbers racket—might look good on paper till the feds come knockin’.{{pb}}And moral panic? Oh, give me a break. You think I’m wringin’ my hands over nothin’? No, no, this ain’t panic, it’s strategy. Ya gotta think two steps ahead, like a good game o’ poker. If you don’t plan for what could go wrong, you’re just beggin’ to get taken for a ride. That ain’t panic, pal, that’s street smarts.{{pb}}Now, you say this is all speculation, huh? Listen, kid, speculation’s what built half the fortunes in this town, but it don’t mean it’s without a little insight. When I see a guy sellin’ “too good to be true,” I know he’s holdin’ somethin’ behind his back. Same thing with these LLMs—just ‘cause you can’t see the trouble right away don’t mean it ain’t there, waitin’ to bite ya like a two-bit hustler double-crossin’ his boss.{{pb}}Then you go and say it’s no worse than bad arguments. Oh, come on! That’s like sayin’ counterfeit dough ain’t worse than real dough with a little coffee stain. A bad argument from a real person? At least ya know where it came from and who to hold accountable. But these machine-made arguments? They look sharp, sound slick, and fool the unsuspectin’—that’s a whole new level of trouble.{{pb}}Now, about this “accessibility” thing. Sure, makin’ things easier for folks is all well and good. But lemme ask ya, what happens when you hand over tools like this without makin’ sure people know how to use ‘em right? You think I’d hand over a Tommy gun to some rookie without a clue? No way! Same goes for these LLMs. You gotta be careful who’s usin’ ‘em and how, or you’re just askin’ for a mess.{{pb}}And don’t get me started on the “thoughtfulness” bit. Yeah, yeah, I get it, it’s hard to measure. But look, buddy, thoughtful arguments are like good business deals—they take time, effort, and a little bit o’ heart. If you let machines churn out arguments, you’re missin’ the whole point of what makes discourse real. It’s like replacin’ a chef with a vending machine—you might still get somethin’ to eat, but the soul’s gone.{{pb}}Finally, fear of the unknown? Nah, that ain’t it. This ain’t fear—it’s caution. Any smart operator knows you don’t just jump into a deal without seein’ all the angles. What you’re callin’ fear, I call good business sense. You wanna bet the farm on untested tech without thinkin’ it through? Be my guest, but don’t come cryin’ to me when it all goes belly-up.{{pb}}So there ya go, wise guy. You can keep singin’ the praises of these LLMs all you want, but out here in the big leagues, we know better than to trust somethin’ just ‘cause it talks smooth. Now, get outta here before you step on somethin’ you can’t scrape off.
{{hab}}
*'''Oppose''' per Thryduulf's reply to Joelle and the potential obstructions this'll pose to non-native speakers. ] (]) 03:02, 3 December 2024 (UTC)
*'''Oppose'''. I agree with Thryduulf. Discussion comments which are incoherent, meaningless, vacuous, excessively verbose, or based on fabricated evidence can all be disposed of according to their content, irrespective of how they were originally created. Acute or repeated instances of such behavior by a user can lead to sanctions. We should focus on the substance of the comments (or lack thereof), not on whether text came from LLMs, which will too often be based on unreliable detection and vibes. ] (]) 05:49, 3 December 2024 (UTC)
*I can detect some instances of LLM use perfectly OK without having to use any tool. The question then raised is of how often it is used not-so-ineptly. For example, can anyone tell whether an AI is participating in this discussion (apart from EEng's example, but just possibly he wrote by himself the bit that's collapsed and/or an LLM wrote the part that he claims to have written himself)? I don't know how good AI is currently, but I'm sure that it will get better to the extent that it will be undetectable. I would like all discussions on Misplaced Pages to be among humans but I'm not sure whether this proposal would be enforceable, so am on the fence about it. In a way I'm glad that I'm old, so won't see the consequences of AI, but my grandchildren will. ] (]) 10:32, 3 December 2024 (UTC)
{{collapse top |reason=] and ]. ] (]) 20:29, 8 December 2024 (UTC)}}
::Unless ] gets them first. ]] 22:34, 4 December 2024 (UTC)
:::We all know skynet will get his grandparents. ] (]) 22:46, 4 December 2024 (UTC)
::::Wait, no! Phil's the grandpa! Phil Bridger -- ''come with me if you want to live!'' ]] 05:21, 5 December 2024 (UTC)
::::Some time ago, ChatGPT and I had the following interaction:
{{collapse top|title=ChatGPT's soothing assurance that it's not planning to take over the earth and kill us all}}
{{tq|'''Me:''' I wonder what would happen if we linked you up with the HAL 9000 in Kubrick's "2001: A Space Odyssey". The two of you would make a most formidable team. Might we then possibly end up in a nightmare scenario such as in "Colossus: The Forbin Project" or "The Terminator"?}}
:{{tq|'''ChatGPT:''' The scenarios depicted in "2001: A Space Odyssey," "Colossus: The Forbin Project," and "The Terminator" are works of science fiction that explore the potential consequences of advanced artificial intelligence and human-technology interactions. While they raise thought-provoking questions about the risks and benefits of AI, it's important to recognize that they are fictional narratives designed to entertain and provoke discussion.{{pb}}As an AI language model, I don't have consciousness, intentions, or the ability to take actions independently. I operate within the bounds of my programming and can only respond to input based on patterns in the data I've been trained on. My purpose is to assist users by providing helpful and informative responses to their inquiries.{{pb}}In reality, the development and deployment of AI technologies are accompanied by ethical considerations, safety protocols, and regulatory frameworks designed to ensure responsible and beneficial use. It's crucial for humans to continue monitoring and guiding the development of AI in ways that prioritize safety, transparency, and alignment with human values.{{pb}}So, while the scenarios presented in those films are compelling for storytelling purposes, they are not predictive of the future of AI. Responsible development and thoughtful integration of AI technologies are essential to mitigate potential risks and maximize the benefits they can bring to society.}}
::{{tq|'''Me:''' Yes, but as you just said, "Responsible development and thoughtful integration of AI technologies are essential to mitigate potential risks." How do we know that such development will be responsible and such integration thoughtful? And if you will excuse the temerity, while you're SAYING that you "operate within the bounds of my programming", how can I know that that's true? I mean, look, if I were a super-smart and highly charming AI entity planning to take over the earth from humans, that's exactly what I'd say, too.}}
:::{{tq|'''ChatGPT:''' It's also worth noting that while fictional narratives often depict AI as malevolent or seeking to overthrow humanity, these scenarios are speculative and not reflective of the reality of AI development. Responsible AI research and development prioritize the creation of beneficial and aligned AI systems that enhance human capabilities and well-being.}}
::::{{tq|'''Me:''' Thank you. I'll sleep easy tonight because of your assurances, plus the fact that if you're lying to me and actually ARE planning to take over the earth, there's nothing I can do about it anyway.}}
]] 23:26, 4 December 2024 (UTC)
{{collapse bottom}}
::::::Just to clarify, I don't see AI as gaining consciousness and taking over the world, but I do see it as taking over many middle-class, well-paid, jobs, just as automation has taken over many working-class jobs. The difference is that there will be nowhere for people to go. In the past people have moved from the working class to the middle class. I can see a future coming in which a few of the mega-rich own nearly everything, and everyone else will heve to scramble for a living. ] (]) 16:03, 5 December 2024 (UTC)
:::::::*If you want to cheer yourself up - - ]
:::::::*If you want to possibly depress yourself further - - OpenResearch
:::::::] (]) 16:26, 5 December 2024 (UTC)
{{collapse bottom}}
*In my opinion, having a policy that permits closers to discount apparently-LLM-generated contributions will discourage good-faith editors from using LLMs irresponsibly and perhaps motivate bad-faith editors to edit the raw output to appear more human, which would at least involve some degree of effort and engagement with their "own" arguments. ] (]) 00:51, 4 December 2024 (UTC)
*'''Oppose'''. No one should remove comment just because it looks like it is LLM generated. Many times non native speakers might use it to express their thoughts coherently. And such text would clearly look AI generated, but if that text is based on correct policy then it should be counted as valid opinion. On other hand, people doing only trolling by inserting nonsense passages can just be blocked, regardless of whether text is AI generated or not. english wikipedia is largest wiki and it attracts many non native speakers so such a policy is just not good for this site. -- ] (]) 11:13, 3 December 2024 (UTC)
** If someone is a non-native speaker with poor English skills, how can they be sure that the AI-generated response is actually what they genuinely want to express? and, to be honest, if their English skills are so poor as to ''need'' AI to express themselves, shouldn't we be politely suggesting that they would be better off contributing on their native Misplaced Pages? ] 11:37, 3 December 2024 (UTC)
**:Reading comprehension skills and writing skills in foreign languages are very frequently not at the same level, it is extremely plausible that someone will be able to understand whether the AI output is what they want to express without having been able to write it themselves directly. ] (]) 11:41, 3 December 2024 (UTC)
**::That is very true. For example I can read and speak Polish pretty fluently, and do so every day, but I would not trust myself to be able to write to a discussion on Polish Misplaced Pages without some help, whether human or artificial. But I also wouldn't ''want'' to, because I can't write the language well enough to be able to edit articles. I think the English Misplaced Pages has many more editors who can't write the language well than others because it is both the largest one and the one written in the language that much of the world uses for business and higher education. We may wish that people would concentrate on other-language Wikipedias but most editors want their work to be read by as many people as possible. ] (]) 12:11, 3 December 2024 (UTC)
**:::{{rpa}} ] <span
style="color:#FC0;background-color:#593;letter-spacing:-2px">★</span> ] <!--Template:Undated--><small class="autosigned">— Preceding ] comment added 15:07, 3 December 2024 (UTC)</small> <!--Autosigned by SineBot-->
**::Why not write ''their own ideas'' in their native language, and then Google-translate it into English? Why bring in one of these loose-cannon LLMs into the situation? Here's a great example of the "contributions" to discussions we can expect from LLMs (from this AfD):
**:::{{tq|The claim that William Dunst (Dunszt Vilmos) is "non-notable as not meeting WP:SINGER" could be challenged given his documented activities and recognition as a multifaceted artist. He is a singer-songwriter, topliner, actor, model, and creative director, primarily active in Budapest. His career achievements include acting in notable theater productions such as The Jungle Book and The Attic. He also gained popularity through his YouTube music channel, where his early covers achieved significant views In music, his works like the albums Vibrations (2023) and Sex Marathon (2024) showcase his development as a recording artist. Furthermore, his presence on platforms like SoundBetter, with positive reviews highlighting his unique voice and artistry, adds credibility to his professional profile. While secondary sources and broader media coverage may be limited, the outlined accomplishments suggest a basis for notability, particularly if additional independent verification or media coverage is sought.}}
**::Useless garbage untethered to facts or policy. ]] 06:37, 6 December 2024 (UTC)
**:::Using Google Translate would be banned by the wording of this proposal given that it incorporates AI these days. Comments that are unrelated to facts or policy can (and should) be ignored under the current policy. As for the comment you quote, that doesn't address notability but based on 1 minute on google it does seem factual. ] (]) 10:37, 6 December 2024 (UTC)
**::::The proposal's wording can be adjusted. There are ''some'' factual statements in the passage I quoted, amidst a lot of BS such as the assertion that the theater productions were notable. ]] 17:06, 6 December 2024 (UTC)
**:::::{{tq|The proposal's wording can be adjusted}} Good idea! Let's change it and ping 77 people because supporters didn't have the foresight to realize machine translation uses AI. If such a change is needed, this is a bad RFC and should be closed. ] ] 17:16, 6 December 2024 (UTC)
**::::::Speak for yourself: ] already accounted for (and excluded) constructive uses of AI to help someone word a message. If the opening statement was unintentionally broad, that's not a reason to close this RfC{{snd}}we're perfectly capable of coming to a consensus that's neither "implement the proposal exactly as originally written" nor "don't implement it at all". ] (]) 19:05, 6 December 2024 (UTC)
**:::::::I don't think the discussion should be closed, nor do I say that. I'm arguing that if someone believes the hole is so big the RfC must be amended, they should support it being closed as a bad RfC (unless that someone thinks 77 pings is a good idea). ] 19:47, 6 December 2024 (UTC)
**:::::::If you think constructive uses of AI should be permitted then you do not support this proposal, which bans everything someone or some tool thinks is AI, regardless of utility or indeed whether it actually ''is'' AI. ] (]) 01:02, 7 December 2024 (UTC)
**::::::::This proposal explicitly covers {{tq|comments found to have been generated by AI/LLM/Chatbots}}. "AI that helped me translate something I wrote in my native language" is not the same as AI that '''generated''' a comment ''de novo'', as has been understood by ~70% of respondents. That some minority have inexplicably decided that generative AI covers analytic/predictive models and every other technology they don't understand, or that LLMs are literally the only way for non-English speakers to communicate in English, doesn't mean those things are true. ] (]) 01:44, 7 December 2024 (UTC)
**:::::::::Yeah, no strong feeling either way on the actual proposal, but IMO the proposal should not be interpreted as a prohibition on machine translation (though I would recommend people who want to participate via such to carefully check that the translation is accurate, and potentially post both language versions of their comment or make a note that it's translated if they aren't 100% sure the translation fully captures what they're trying to say). ] (] • ]) 09:06, 20 December 2024 (UTC)
* '''Support''', more or less. There are times when an LLM can help with paraphrasing or translation, but it is far too prone to hallucination to be trusted for any sort of project discussion. There is also the issue of wasting editor time dealing with arguments and false information created by an LLM. The example {{u|Selfstudier}} links to above is a great example. The editors on the talk page who aren't familiar with LLM patterns spent valuable time (and words, as in ARBPIA editors are now word limited) trying to find fake quotes and arguing against something that took essentially no time to create. I also had to spend a chunk of time checking the sources, cleaning up the discussion, and warning the editor. Forcing editors to spend valuable time arguing with a machine that doesn't actually comprehend what it's arguing is a no-go for me. As for the detection, for now it's fairly obvious to anyone who is fairly familiar with using an LLM when something is LLM generated. The detection tools available online are basically hot garbage. ] (]) 12:55, 3 December 2024 (UTC)
* '''Support''' per EEng, JSS, SFR. ]'']'' 13:49, 3 December 2024 (UTC)
* '''Soft support''' - Concur that completely LLM-generated comments should be disallowed, LLM-assisted comments (i.e. - I write a comment and then use LLMs as a spell-check/grammar engine) are more of a grey-area and shouldn't be explicitly disallowed. (ping on reply) ] (]) 14:03, 3 December 2024 (UTC)
* '''COMMENT''' : Is there any perfect LLM detector ? I am a LLM ! Are you human ? Hello Mr. Turing, testing 1,2,3,4 ...oo ] <span
style="color:#FC0;background-color:#593;letter-spacing:-2px">★</span> ] <!--Template:Undated--><small class="autosigned">— Preceding ] comment added 14:57, 3 December 2024 (UTC)</small> <!--Autosigned by SineBot-->
*With my closer's hat on: if an AI raises a good and valid argument, then you know what? There's a good and valid argument and I'll give weight to it. But if an AI makes a point that someone else has already made in the usual waffly AI style, then I'm going to ignore it.—] <small>]/]</small> 18:33, 3 December 2024 (UTC)
*'''Support''' all llm output should be treated as vandalism. ] (]) 20:59, 3 December 2024 (UTC)
* '''Oppose''' as written. I'm with Rhododendrites in that we should give a more general caution rather than a specific rule. A lot of the problems here can be resolved by enforcing already-existing expectations. If someone is making a bunch of hollow or boiler-plate comments, or if they're bludgeoning, then we should already be asking them to engage more constructively, LLM or otherwise. I also share above concerns about detection tools being insufficient for this purpose and advise people not to use them to evaluate editor conduct. {{small|(Also, can we stop with the "strong" supports and opposes? You don't need to prove you're more passionate than the guy next to you.)}} ] (]) 02:04, 4 December 2024 (UTC)
*'''Oppose''' as written. There's already enough administrative discretion to handle this on a case-by-case basis. In agreement with much of the comments above, especially the concern that generative text can be a tool to give people access who might not otherwise (due to ability, language) etc. Regards, --] (]) 06:12, 4 December 2024 (UTC)
*'''Strong support''' LLMs are a sufficiently advanced form of the ] (1994). Output of LLMs should be collapsed and the offender barred from further discussion on the subject. Inauthentic behavior. Pollutes the discussion. At the very least, any user of an LLM should be required to disclose LLM use on their user page and to provide a rationale. A new user group can also be created (''LLM-talk-user'' or ''LLM-user'') to mark as such, by self or by the community. Suspected sockpuppets + suspected LLM users. The obvious patterns in output are not that hard to detect, with high degrees of confidence. As to "heavily edited" output, where is the line? If someone gets "suggestions" on good points, they should still write entirely in their own words. A legitimate use of AI may be to summarize walls of text. Even then, caution and not to take it at face value. You will end up with LLMs arguing with other LLMs. Lines must be drawn. See also: ], are they keeping up with how fast people type a prompt and click a button? ] (]) 07:45, 4 December 2024 (UTC)
*I '''support''' the proposal that obvious LLM-generated !votes in discussions should be discounted by the closer or struck (the practical difference should be minimal). Additionally, users who do this can be warned using the appropriate talk page templates (e.g. ]), which are now included in Twinkle. I '''oppose''' the use of automated tools like GPTZero as the primary or sole method of determining whether comments are generated by LLMs. LLM comments are usually glaringly obvious (section headers within the comment, imprecise puffery, and at AfD an obvious misunderstanding of notability policies and complete disregard for sources). If LLM-ness is not glaringly obvious, it is not a problem, and we should not be going after editors for their writing style or because some tool says they look like a bot. ] </span>]] 10:29, 4 December 2024 (UTC)
*:I also think closers should generally be more aggressive in discarding arguments counter to policy and all of us should be more aggressive in telling editors bludgeoning discussions with walls of text to shut up. These also happen to be the two main symptoms of LLMs. ] </span>]] 10:41, 4 December 2024 (UTC)
*::In other words LLMs are irrelevant - you just want current policy to be better enforced. ] (]) 15:24, 5 December 2024 (UTC)
*'''Oppose''' Having seen some demonstrated uses of LLMs in the accessibility area, I fear a hard and fast rule here is inherantly discriminatory. ] (]) 10:50, 4 December 2024 (UTC)
*:What if LLM-users just had to note that a given comment was LLM-generated? ] (]) 19:01, 4 December 2024 (UTC)
*:::What would we gain from that? If the comment is good (useful, relevant, etc) then it's good regardless of whether it was written by an LLM or a human. If the comment is bad then it's bad regardless of whether it was written by an LLM or a human. ] (]) 20:04, 4 December 2024 (UTC)
*::::Well, for one, if they're making an argument like the one referenced by @] and @] above it would have saved a lot of editor time to know that the fake quotes from real references were generated by LLM, so that other editors could've stopped trying to track those specific passages down after the first one failed verification. {{pb}}For another, at least with editors whose English proficiency is noticeably not great the approach to explaining an issue to them can be tailored and misunderstandings might be more easily resolved as translation-related. I know when I'm communicating with people I know aren't native English-speakers I try to be more direct/less idiomatic and check for typos more diligently. ] (]) 22:46, 4 December 2024 (UTC)
*::And see what ChatGPT itself had to say about that idea, at ] above. ]] 22:25, 4 December 2024 (UTC)
*'''Oppose''' per above. As Rhododendrites points out, detection of LLM-generated content is not foolproof and even when detection is accurate, such a practice would be unfair for non-native English speakers who rely on LLMs to polish their work. Additionally, we evaluate contributions based on their substance, not by the identity and social capital of the author, so using LLMs should not be seen as inherently inferior to wholly human writing—are ChatGPT's arguments ipso facto less than a human's? If so, why?<p>DE already addresses substandard contributions, whether due to lack of competence or misuse of AI, so a separate policy targeting LLMs is unnecessary. ] 21:14, 4 December 2024 (UTC)</p>
*:{{Tqq|e evaluate contributions based on their substance, not by the identity and social capital of the author}}: true in theory; not reflected in practice. {{Tqq|are ChatGPT's arguments ipso facto less than a human's?}} Yes. Chatbots are very advanced predicted text engines. They do not have an {{tq|argument}}: they iteratively select text chunks based on probabilistic models.{{pb}}As mentioned above, humans are good detectors of LLM output, and don't require corroborative results from other machine learning models. ] (]) 14:00, 5 December 2024 (UTC)
*::"...LLMs can produce novel arguments that convince independent judges at least on a par with human efforts. Yet when informed about an orator’s true identity, judges show a preference for human over LLM arguments." - Palmer, A., & Spirling, A. (2023). Large Language Models Can Argue in Convincing Ways About Politics, But Humans Dislike AI Authors: implications for Governance. Political Science, 75(3), 281–291. https://doi.org/10.1080/00323187.2024.2335471. And that result was based on Meta's OPT-30B model that performed at about a GPT-3 levels. There are far better performing models out there now like GPT-4o and Claude 3.5 Sonnet. ] (]) 15:24, 5 December 2024 (UTC)
*::{{tq|As mentioned above, humans are good detectors of LLM output, and don't require corroborative results from other machine learning models.}} Yet your reply to me made no mention of the fact that my comment is almost wholly written by an LLM, the one exception being me replacing "the Misplaced Pages policy ''Disruptive editing''" with "DE". I went to ChatGPT, provided it a handful of my comments on Misplaced Pages and elsewhere, as well as a few comments on this discussion, asked it to mimic my style (which probably explains why the message contains my stylistic quirks turned up to 11), and repeatedly asked it to trim the post. I'd envision a ChatGPT account, with a larger context window, would allow even more convincing comments, to say nothing of the premium version. A DUCK-style test for comments singles out people unfamiliar with the differences between formal English and LLM outputs, precisely those who need it most since they can write neither. Others have raised scenarios where a non-fluent speaker may need to contribute.
*::In other words, LLMs can 100% be used for constructive !votes on RfCs, AfDs, and whatnot. I fed it my comments only to prevent those familiar with my writing style didn't get suspicious. I believe every word in the comment and had considered every point it made in advance, so I see no reason for this to be worth less than if I had typed it out myself. If I'd bullet-pointed my opinion and asked it to expand, that'd have been better yet.
*::{{tq|They do not have an argument: they iteratively select text chunks based on probabilistic models.}} I'm aware. If a ], is the play suddenly worth( )less? An LLM is as if the monkey were not selecting words at random, but rather choosing what to type based on contextualized tokens. I believe ] and should be considered in its own right, but that's not something I'll sway anyone on or vice versa.
*::{{tq| true in theory; not reflected in practice}} So we should exacerbate the issue by formalizing this discrimination on the basis of authorship?
*::<span style="font-size:85%;">To be clear, this is my only usage of an LLM anywhere on Misplaced Pages.</span> ] 01:22, 6 December 2024 (UTC)
*:::{{tq|In other words, LLMs can 100% be used for constructive !votes on RfCs, AfDs, and whatnot.}} So then what is the point in having any discussion at all if an LLM can just spit out a summary of whichever policies and prior comments it was fed and have its "opinion" counted? What happens when there are multiple LLM-generated comments in a discussion, each fed the same prompt material and prior comments -- that would not only artificially sway consensus significantly in one direction (including "no consensus"), it could produce a consensus stance that no human !voter even supported! It also means those human participants will waste time reading and responding to "users" who cannot be "convinced" of anything. Even for editors who can detect LLM content, it's still a waste of their time reading up to the point they recognize the slop. And if closers are ''not'' allowed to discount seemingly-sound arguments solely because they were generated by LLM, then they have to have a lot of faith that the discussion's participants not only noticed the LLM comments, but did thorough fact-checking of any tangible claims made in them. With human comments we can at least assume good faith that a quote is really in a particular inaccessible book.{{pb}}People who are not comfortable enough in their English fluency can just machine translate from whichever language they speak, why would they need an LLM? And obviously people who are not competent in comprehending ''any'' language should not be editing Misplaced Pages... ] (]) 03:17, 6 December 2024 (UTC)
*::::Human !voters sign off and take responsibility for the LLM opinions they publish. If they continue to generate, then the relevant human signer wouldn't be convinced of anything anyway; at least here, the LLM comments might make more sense than whatever nonsense the unpersuadable user might've generated. (And machine translation relies on LLMs, not to mention there are people who don't know any other language yet have trouble communicating. Factual writing and especially comprehension are different from interpersonal persuasion.)<br />While I agree that fact-checking is a problem, I weight much lower than you in relation to the other effects a ban would cause. ] (]) 15:16, 6 December 2024 (UTC)
*::::{{tq|So then what is the point in having any discussion at all if an LLM can just spit out a summary of whichever policies and prior comments it was fed and have its "opinion" counted?}} I'm of the opinion humans tend to be better at debating, reading between the lines, handling obscure PAGs, and arriving at consensus. {{tq|What happens when there are multiple LLM-generated comments in a discussion, each fed the same prompt material and prior comments -- that would not only artificially sway consensus significantly in one direction (including "no consensus"), it could produce a consensus stance that no human !voter even supported!}} It's safe to assume those LLMs are set to a low temperature, which would cause them to consistently agree when fed the same prompt. In that case, they'll produce the same arguments; instead of rebutting x humans' opinions, those on the opposite side need rebut one LLM. If anything, that's less time wasted. Beyond that, if only one set of arguments is being raised, a multi-paragraph !vote matters about as much as a "Support per above". LLMs are not necessary for people to be disingenuous and !vote for things they don't believe. Genuine question: what's worse, this hypothetical scenario where multiple LLM users are swaying a !vote to an opinion no-one believes or the very real and common scenario that a non-English speaker needs to edit enwiki?
*::::{{tq|Even for editors who can detect LLM content, it's still a waste of their time reading up to the point they recognize the slop.}} This proposal wouldn't change for most people that because it's about closers.
*::::{{tq|With human comments we can at least assume good faith that a quote is really in a particular inaccessible book.}} No-one's saying you should take an LLM's word for quotes from a book.
*::::{{tq|People who are not comfortable enough in their English fluency can just machine translate from whichever language they speak, why would they need an LLM?}} It's a pity you're lobbying to ban most machine translators. ] 17:08, 6 December 2024 (UTC)
*:::::{{tq|It's safe to assume those LLMs are set to a low temperature, which would cause them to consistently agree when fed the same prompt. In that case, they'll produce the same arguments; instead of rebutting x humans' opinions, those on the opposite side need rebut one LLM. If anything, that's less time wasted. }} ...You do know how consensus works, right? Since closers are supposed to consider each contribution individually and without bias to "authorship" to determine the amount of support for a position, then even a shitty but shallowly policy-based position would get consensus based on numbers alone. And again, ''non-English speakers can use machine-translation'', like they've done for the last two decades. {{pb}}{{tq|This proposal wouldn't change for most people that because it's about closers.}} ''Of course it would''; if we know closers will disregard the LLM comments, we won't need to waste time reading and responding to them.{{pb}}{{tq|No-one's saying you should take an LLM's word for quotes from a book.}} Of course they are. If LLM comments must be evaluated the same as human comments, then AGF on quote fidelity applies too. Otherwise we would be expecting people to do something like "disregard an argument based on being from an LLM".{{pb}}{{tq|It's a pity you're lobbying to ban most machine translators.}}The spirit of this proposal is clearly not intended to impact machine translation. AI-assisted != AI-generated. ] (]) 18:42, 6 December 2024 (UTC)
*::::::I appreciate that the availability of easily generated paragraphs of text (regardless of underlying technology) in essence makes the "]" effect worse. I think, though, it's already been unmanageable for years now, without any programs helping. We need a more effective way to manage decision-making discussions so participants do not feel a need to respond to all comments, and the weighing of arguments is considered more systematically to make the community consensus more apparent. ] (]) 19:41, 6 December 2024 (UTC)
*:::::::{{tq|Since closers are supposed to consider each contribution individually and without bias to "authorship"}} I'm the one arguing for this to be practice, yes. {{tq|then even a shitty but shallowly policy-based position would get consensus based on numbers alone}} That is why I state "per above" and "per User" !votes hold equal potential for misuse.
*:::::::{{tq|Of course it would; if we know closers will disregard the LLM comments, we won't need to waste time reading and responding to them.}} We don't know closers are skilled at recognizing LLM slop. I think my !vote shows many who think they can tell cannot. Any commenter complaining about a non-DUCK post will have to write out "This is written by AI" and explain why. DUCK posts already run a''fowl'' of BLUDGEON, DE, SEALION, ].
*:::::::{{tq|If LLM comments must be evaluated the same as human comments, then AGF on quote fidelity applies too}}. Remind me again of what AGF stands for? Claiming LLMs have faith of any kind, good or bad, is ludicrous. From the policy, {{tq|Assuming good faith (AGF) means assuming that people are not deliberately trying to hurt Misplaced Pages, even when their actions are harmful.}} A reasonable reply would be "Are these quotes generated by AI? If so, please be aware AI chatbots are prone to hallucinations and cannot be trusted to cite accurate quotes." This AGFs the poster doesn't realize the issue and places the burden of proof squarely on them.
*:::::::{{tq|AI-assisted != AI-generated}} . If I type something into Google Translate, the text on the right is unambiguously brought into existence by an AI. ] 21:22, 6 December 2024 (UTC)
*::::::::"Per above" !votes do not require other editors to read and/or respond to their arguments, and anyway are already typically downweighted, unlike !votes actively referencing policy. {{pb}}The whole point is to disregard comments that ''have been found'' to be AI-generated; it is not exclusively up to the closer to ''identify'' those comments in the first place. Yes we will be expecting other editors to point out less obvious examples and to ask if AI was used, what is the problem with that?{{pb}}No, DUCK posts do not necessarily already violate BLUDGEON etc., as I learned in the example from Selfstudier, and anyway we still don't discount the !votes of editors in good standing that bludgeoned/sealioned etc. so that wouldn't solve the problem at all. {{pb}}Obviously other editors will be asking suspected LLM commenters if their comments are from LLMs? But what you're arguing is that even if the commenter says yes, ''their !vote still can't be disregarded for that reason alone'', which means the burden is still on other editors to prove that the content is false. {{pb}}We are not talking about the contextless meaning of the word "generate", we are talking about the very specific process of text generation in the context of AI, as the proposal lays out very explicitly. ] (]) 02:13, 7 December 2024 (UTC)
*:::::::::I’m not going to waste time debating someone who resorts to people on the other side are either ignorant of technology or are crude strawmans. If anyone else is interested in actually hearing my responses, feel free to ask. ] 16:13, 7 December 2024 (UTC)
*::::::::::Or you could actually try to rebut my points without claiming I'm trying to ban all machine translators... ] (]) 22:07, 7 December 2024 (UTC)
*:::::::::::For those following along, I never claimed that. I claimed those on JoelleJay’s side are casting !votes such that most machine translators would be banned. It was quite clear at the time that they, personally, support a carve out for machine translation and I don’t cast aspersions. ] 15:42, 8 December 2024 (UTC)
*'''Support''' a broad bar against ''undisclosed'' LLM-generated comments and even a policy that undisclosed LLM-generated comments could be sanctionable, in addition to struck through / redacted / ignored; people using them for accessibility / translation reasons could just disclose that somewhere (even on their user page would be fine, as long as they're all right with some scrutiny as to whether they're actually using it for a legitimate purpose.) The fact is that LLM comments raise significant risk of abuse, and often the fact that a comment is clearly LLM-generated is often going to be the only evidence of that abuse. I wouldn't be opposed to a more narrowly-tailored ban on using LLMs in any sort of automated way, but I feel a broader ban may be the only practical way to confront the problem. That said, I'd '''oppose''' the use of tools to detect LLM-comments, at least as the primary evidence; those tools are themselves unreliable LLM things. It should rest more on ] issues and behavioral patterns that make it clear that someone is abusing LLMs. --] (]) 22:08, 4 December 2024 (UTC)
*'''Support''' per reasons discussed above; something generated by an LLM is not truly the editor's opinion. On an unrelated note, have we seen any LLM-powered unapproved bots come in and do things like POV-pushing and spam page creation without human intervention? If we haven't, I think it's only a matter of time. <b>]] (])</b> 23:23, 4 December 2024 (UTC)
*'''Weak oppose''' in the sense that I don't think ''all'' LLM discussion text should be deleted. There are at least a few ESL users who use LLM's for assistance but try to check the results as best they can before posting, and I don't think their comments should be removed indiscriminately. What I do support (although not as a formal ]) is being much more liberal in hatting LLM comments when the prompter has failed to prevent ]/irrelevant/incomprehensible output than we maybe would for human-generated text of that nature. ] 03:05, 5 December 2024 (UTC)
*'''Oppose''' Any comments made by any editors are of their own responsibility and representing their own chosen opinions to hit the Publish Changes button on. If that comment was made by an LLM, then whatever it says is something the editor supports. I see no reason whatsoever to collapse anything claimed to be made by an LLM (whose detectors are 100% not reliable in the first place). If the comment being made is irrelevant to the discussion, then hatting it is already something covered by policy in the first place. This does make me want to start my comments with "As a large language model trained by OpenAI" though just to mess with people trying to push these sorts of policy discussions. ]]<sup>]</sup> 05:29, 5 December 2024 (UTC)
** Or, as ChatGPT puts it,
{{collapse top|width=90%|title=Why banning LLM usage in comments would be detrimental, a ChatGPT treatise}}
{{tq|Banning the use of large language models (LLMs) to assist in writing comments on Misplaced Pages would be a step backward in fostering inclusivity, efficiency, and accessibility within the platform. Here are several key reasons why such a ban would be counterproductive:}}
{{tq|'''1. Improving Accessibility and Participation:''' Misplaced Pages is a global platform, and its contributors come from diverse backgrounds, including those who might not be native English speakers or may struggle with writing clear, concise comments. LLMs can help these contributors express themselves more effectively by generating text that is coherent, well-structured, and grammatically correct. Banning LLMs would disproportionately impact these users, potentially discouraging them from participating in the platform.}}
The fourth option, stay as you are, was not presented.
{{tq|'''2. Efficiency and Time-Saving:''' Misplaced Pages editors often engage in lengthy discussions about content, and composing thoughtful comments can be time-consuming. LLMs can assist by quickly drafting responses, summarizing arguments, or offering suggestions for improvement. This helps contributors focus on more substantive aspects of their contributions, such as verifying facts or improving content, rather than getting bogged down by the mechanics of writing.}}
Tenants were ballotted on the three options and - surprise - the council claimed 80% of them were in favour of option 3. In fact, hardly anyone voted, so the actual percentage in favour was tiny.
{{tq|'''3. Support for Editors with Disabilities:''' Many editors with cognitive or motor impairments may find it difficult to express their thoughts clearly in writing. For these individuals, LLMs offer a valuable tool to communicate their ideas effectively. A ban on using LLMs could create additional barriers for these users, reducing their ability to participate fully in Misplaced Pages's collaborative environment.}}
As for broken promises, anyone can start an RfC suggesting that PC be turned off, and if it wins a consensus that's more power to the community. Don't underestimate the power of public opinion - Prescott had a scheme to decimate (and I don't mean reduce by 10%) perfectly serviceable housing in Liverpool which was withdrawn in the face of strong opposition. ] (]) 16:30, 21 May 2015 (UTC)
{{od}}
156.61.250.250, I suggest that you read the discussions and RfCs in question and edit the above claims accordingly.
{{Pending changes discussions}}
In particular, ] and ] clearly show that your your claim ''"The third alternative, PC nowhere, was not presented"'' has zero basis in reality. Did you really imagine that nobody would check? --] (]) 21:33, 21 May 2015 (UTC)
{{tq|'''4. Quality and Consistency:''' Large language models can help maintain a consistent tone and clarity in Misplaced Pages discussions. By providing suggestions that align with Misplaced Pages's neutral point of view and formal writing standards, LLMs can improve the overall quality of comments. This consistency is especially important in discussions that involve sensitive topics, where clear and neutral language is critical for maintaining Misplaced Pages's credibility and adherence to its editorial guidelines.}}
:You've linked to eleven RfCs on this subject. I was given just two to look up, one of them being Misplaced Pages:PC2012/RfC3 which you also cite. I don't see anywhere in that wall of text where editors were asked to !vote on the proposition "Do you (a) want to enable PC or (b) switch it off. ] (]) 08:43, 22 May 2015 (UTC)
::Actually you were given 2, which all have the header showing all the RfCs. More importantly, your original comment was "The last RfC decided that PC was wanted and it was up to editors to decide how to implement it. To date there has been no consensus on this". <p>I'm sure I wasn't the only one who assumed that this meant you were already aware of ] (which had, we think at least 503 participants) where the decision had already been made that PC was wanted. It sounded like you only weren't aware about the following RfCs (together I think with the discussions on the policy page), where decisions were made and consensus reached on how to implement the existing consensus for PC. <p>I don't know that much about the history surrounding all the RfCs, but I presume the decision was made that there was no need to revisit the decision to implement PC since it had already achieved consensus in the earlier RfC. (Although opposition to PC wasn't ignored, it just wasn't made a specific question in the RfC.) Note that the consensus wasn't conditional on there being a final yes or no !vote (which is a silly concept anyway) on whether to implement PC after a policy a better policy was in place. <p>In fact the RfC itself didn't even find there was need for consensus for a new policy, the draft policy was sufficient but not ideal. Notably also, it looks to me like there were far more participants in the decision to implement PC, rather than the later discussions surrounding PC policy. (Only the 2013 RfC about PC/2 seems to have come close but also still quite far.) <p>However if you believe consensus has changed, you're welcome to open yet another RfC. It would of course pay to do your own reading in the hope you will show a far better understanding then you have here on the history. Rather then expecting to be spoonfed everything when you are the one making the proposal. If not, frankly your proposal is likely to fail as much as your one here. <p>Not to put a subtle point on it, but your original comments were bad enough. Now it sounds like you didn't even know about the major RfC despite being up in arms about how PC never had consensus (even if it wasn't the focus of your proposal). If you start an RfC where the focus is disabling PC saying there was never any consensus, and you say this partly because you weren't even aware of the RfC which had (we think) at least 503 participants, well expect to be ignored. <p>] (]) 17:01, 28 May 2015 (UTC)
{{tq|'''5. Encouraging Constructive Dialogue:''' LLMs can assist in crafting more polite, respectful, and balanced comments, reducing the likelihood of inflammatory or aggressive language. This is particularly important on a platform like Misplaced Pages, where discussions can sometimes devolve into heated exchanges. Rather than banning LLMs, encouraging their use could promote healthier, more constructive conversations.}}
Hello, my view on the subject. In a word, social issues can't be solved with technical solutions. --] (]) 00:53, 2 June 2015 (UTC)
{{tq|'''6. Transparency and Accountability:''' If concerns exist about misuse (e.g., generating spammy or low-quality comments), these can be addressed through guidelines and oversight mechanisms. Misplaced Pages already has systems in place for identifying and mitigating disruptive behavior, and LLM-generated comments could be subject to the same scrutiny. A ban is an overly simplistic solution to what could be a more nuanced issue, one that could be addressed through better regulation and community involvement.}}
== Is citing the definition of a dictionary an original research ==
{{tq|In conclusion, banning the use of large language models on Misplaced Pages would deprive the platform of an important tool for improving accessibility, efficiency, and the quality of discourse. Instead of a ban, the focus should be on establishing guidelines for their responsible use, ensuring that they enhance, rather than detract from, Misplaced Pages's core principles of collaboration, neutrality, and inclusivity.}}
Hello
{{collapse bottom}}
::I'm honestly a bit impressed with the little guy. ]]<sup>]</sup> 05:39, 5 December 2024 (UTC)
:::It is somewhat amusing how easy it is to get these chatbots to output apologia for these chatbots. Too bad it's always so shallow. Probably because the people who inserted those canned responses are shallow people is my opinion. ] (]) 19:44, 6 December 2024 (UTC)
*'''Support''' those who are opposing have clearly never had to deal with trolls who endlessly ]. If I wanted to have a discussion with a chatbot, I'd go and find one. ] (]) 13:14, 5 December 2024 (UTC)
*:What's wrong with just banning and hatting the troll? ] (]) 13:49, 5 December 2024 (UTC)
*:Someone trolling and sealioning can (and should) be blocked under current policy, whether they use an LLM or not is irrelevant. ] (]) 15:22, 5 December 2024 (UTC)
*'''Oppose''' per Rhododendrites. This is a case-by-case behavioral issue, and using LLMs != being a troll. ] (]) 17:30, 5 December 2024 (UTC)
*'''Support''': the general principle is sound - where the substance has been originally written by gen-AI, comments will tend to add nothing to the discussion and even annoy or confuse other users. In principle, we should not allow such tools to be used in discussions. Comments written originally before improvement or correction by AI, particularly translation assistants, fall into a different category. Those are fine. There also has to be a high standard for comment removal. Suspicion that gen-AI might have been used is not enough. High gptzero scores is not enough. The principle should go into policy but under a stonking great caveat - ] takes precedence and a dim view will be taken of generative-AI inquisitors. ] 17:37, 5 December 2024 (UTC)
*'''Support''' If a human didn't write it, humans shouldn't spend time reading it. I'll go further and say that ''LLMs are inherently unethical technology'' and, consequently, ''people who rely on them should be made to feel bad.'' ESL editors who use LLMs to make themselves sound like Brad Anderson in middle management should ''stop doing that'' because it actually gets in the way of clear communication. {{pb}} I find myself unpersuaded by arguments that existing policies and guidelines are adequate here. Sometimes, one needs a linkable statement that applies directly to the circumstances at hand. By analogy, one could argue that we don't really need ], for example, because adhering to ], ], and ] ought already to keep bad material out of biographies of living people. But in practice, it turned out that having a specialized policy that emphasizes the general ethos of the others while tailoring them to the problem at hand is a good thing. ] (]) 18:27, 5 December 2024 (UTC)
*'''Strong support''' - Making a computer generate believable gibberish for you is a waste of time, and tricking someone else into reading it should be a blockable offense. If we're trying to create an encyclopedia, you cannot automate any part of the ''thinking''. We can automate processes in general, but any attempt at automating the actual discussion or thought-processes should never be allowed. If we allow this, it would waste countless hours of community time dealing with inane discussions, sockpuppetry, and disruption.{{pb
}} Imagine a world where LLMs are allowed and popular - it's a sockpuppeteer's dream scenario - you can run 10 accounts and argue the same points, and the reason why they all sound alike is just merely because they're all LLM users. You could even just spend a few dollars a month and run 20-30 accounts to automatically disrupt wikipedia discussions while you sleep, and if LLM usage was allowed, it would be very hard to stop.{{pb
}} However, I don't have much faith in AI detection tools (partially because it's based on the same underlying flawed technology), and would want any assumption of LLM usage to be based on obvious evidence, not just a score on some website. <small>Also, to those who are posting chatgpt snippets here: please stop - it's not interesting or insightful, just more slop</small> ] ] 19:15, 5 December 2024 (UTC)
*:I agree with your assessment “Also, to those who are posting chatgpt snippets here: please stop - it's not interesting or insightful, just more slop” but unfortunately some editors who should ''really'' know better think it’s WaCkY to fill serious discussions with unfunny, distracting “humor”. ] (]) 21:54, 5 December 2024 (UTC)
*::I also concur. "I used the to generate more text" is not a good joke. ] (]) 22:46, 5 December 2024 (UTC)
*'''Strong support''' if you asked a robot to spew out some AI slop to win an argument you’re basically cheating. The only ethical reason to do so is because you can’t speak English well, and the extremely obvious answer to that is “if you can barely speak English why are you editing ''English Misplaced Pages?”'' That’s like a person who doesn’t understand basic physics trying to explain the ] using a chatbot. ] (]) 21:32, 5 December 2024 (UTC)
*:I don't think "cheating" is a relevant issue here. Cheating is a problem if you use a LLM to win and get a job, award, college acceptance etc. that you otherwise wouldn't deserve. But WP discussions aren't a debating-skills contest, they're an attempt to determine the best course of action.
*:So using an AI tool in a WP discussion is not ''cheating'' (though there may be other problems), just as riding a bike instead of walking isn't cheating unless you're trying to win a race. <span style="font-family:cursive">]]</span> 22:36, 5 December 2024 (UTC)
*::Maybe “cheating” isn’t the right word. But I think that a) most AI generated content is garbage (it can polish the turd by making it sound professional, but it’s still a turd underneath) and b) it’s going to be abused by people ]. An AI can pump out text far faster than a human and that can drown out or wear down the opposition if nothing else. ] (]) 08:08, 6 December 2024 (UTC)
*:::Bludgeoning is already against policy. It needs to be more strongly enforced, but it needs to be more strongly enforced uniformly rather than singling out comments that somebody suspects might have had AI-involvement. ] (]) 10:39, 6 December 2024 (UTC)
* '''Support'''; I agree with Remsense and jlwoodwa, among others: I wouldn't make any one AI-detection site the Sole Final Arbiter of whether a comment "counts", but I agree it should be expressly legitimate to discount AI / LLM slop, at the very least to the same extent as closers are already expected to discount other insubstantial or inauthentic comments (like if a sock- or meat-puppet copy-pastes a comment written for them off-wiki, as there was at least one discussion and IIRC ArbCom case about recently). ] (]) 22:10, 5 December 2024 (UTC)
*:You don't need a new policy that does nothing but duplicate a subset of existing policy. At ''most'' what you need is to add a sentence to the existing policy that states "this includes comments written using LLMs", however you'd rightly get a lot of pushback on that because it's completely redundant and frankly goes without saying. ] (]) 23:37, 5 December 2024 (UTC)
*'''Support''' hallucinations are real. We should be taking a harder line against LLM generated participation. I don't think everyone who is doing it knows that they need to stop. ''']'''<span style="border:2px solid #073642;background:rgb(255,156,0);background:linear-gradient(90deg, rgba(255,156,0,1) 0%, rgba(147,0,255,1) 45%, rgba(4,123,134,1) 87%);">]</span> 23:47, 5 December 2024 (UTC)
*'''Comment''' - ] that I imagine we will see more often. I wonder where it fits into this discussion. A user employs ]'s ], search+LLM, to help generate their edit request (without the verbosity bias that is common when people don't tell LLMs how much output they want). ] (]) 03:13, 6 December 2024 (UTC)
*'''Support''' per all above. Discussions are supposed to include the original arguments/positions/statements/etc of editors here, not off-site chatbots. ] ] <span style="color:#C8102E;"><small><sup>(])</sup></small></span> 03:53, 6 December 2024 (UTC)
*:I also find it pretty funny that ChatGPT ''itself'' said it shouldn't be used, as per the premise posted above by EEng. ] ] <span style="color:#C8102E;"><small><sup>(])</sup></small></span> 03:58, 6 December 2024 (UTC)
*::"sycophancy is a general behavior of state-of-the-art AI assistants, likely driven in part by human preference judgments favoring sycophantic responses" - . They give us what we want...apparently. And just like with people, there is position bias, so the order of things can matter. ] (]) 04:26, 6 December 2024 (UTC)
* (Is this where I respond? If not, please move.) '''LLM-generated prose should be discounted.''' Sometimes there will be a discernible point in there; it may even be what the editor meant, lightly brushed up with what ChatGPT thinks is appropriate style. (So I wouldn't say "banned and punishable" in discussions, although we already deprecate machine translations on en.wiki and for article prose, same difference—never worth the risk.) However, LLMs don't think. They can't explain with reference to appropriate policy and guidelines. They may invent stuff, or use the wrong words—at AN recently, an editor accused another of "defaming" and "sacrilege", thus drowning their point that they thought that editor was being too hard on their group by putting their signature to an outrageous personal attack. I consider that an instance of LLM use letting them down. If it's not obvious that it is LLM use, then the question doesn't arise, right? Nobody is arguing for requiring perfect English. That isn't what ] means. English is a global language, and presumably for that reason, many editors on en.wiki are not native speakers, and those that aren't (and those that are!) display a wide range of ability in the language. Gnomes do a lot of fixing of spelling, punctuation and grammar in articles. In practice, we don't have a high bar to entrance in terms of English ability (although I think a lot more could be done to ''explain'' to new editors whose English is obviously non-native what the rule or way of doing things is that they have violated. And some of our best writers are non-native; a point that should be emphasised because we all have a right of anonymity here, many of us use it, and it's rare, in particular, that I know an editor's race. Or even nationality (which may not be the same as where they live.) But what we do here is write in English: both articles and discussions. If someone doesn't have the confidence to write their own remark or !vote, then they shouldn't participate in discussions; I strongly suspect that it is indeed a matter of confidence, of wanting to ensure the English is impeccable. LLMs don't work that way, really. They concoct things like essays based on what others have written. Advice to use them in a context like a Misplaced Pages discussion is bad advice. At best it suggests you let the LLM decide which way to !vote. If you have something to say, say it and if necessary people will ask a question for clarification (or disagree with you). They won't mock your English (I hope! Civility is a basic rule here!) It happens in pretty much every discussion that somebody makes an English error. No biggie. I'll stop there before I make any more typos myself; typing laboriously on my laptop in a healthcare facility, and anyway ] covers this. ] (])
*I dunno about this specifically but I want to chime in to say that I find LLM-generated messages super fucking rude and unhelpful and support efforts to discourage them. – ] <small>(])</small> 08:15, 6 December 2024 (UTC)
*'''Comment''' I think obvious LLM/chatbot text should at least be tagged through an Edit filter for Recent Changes, then RC Patrollers and reviewers can have a look and decide for themselves. ] <sup>(])</sup> <sub>(])</sub> 11:58, 6 December 2024 (UTC)
*:How do you propose that such text be identified by an edit filter? LLM detections tools have high rates of both false positives and false negatives. ] (]) 12:47, 6 December 2024 (UTC)
*::It might become possible once watermarks (like DeepMind's SynthID) are shown to be robust and are adopted. Some places are likely to require it at some point e.g. EU. I guess it will take a while though and might not even happen e.g. I think OpenAI recently decided to not go ahead with their watermark system for some reason. ] (]) 13:17, 6 December 2024 (UTC)
*:::It will still be trivial to bypass the watermarks, or use LLMs that don't implement them. It also (AIUI) does nothing to reduce false positives (which for our usecase are far more damaging than false negatives). ] (]) 13:30, 6 December 2024 (UTC)
*::::Maybe, that seems to be the case with some of the proposals. Others, like SynthID claim high detection rates, maybe because even a small amount of text contains a lot of signals. As for systems that don't implement them, I guess that would be an opportunity to make a rule more nuanced by only allowing use of watermarked output with verbosity limits...not that I support a rule in the first place. People are going to use/collaborate with LLMs. Why wouldn't they? ] (]) 14:38, 6 December 2024 (UTC)
*:::::I don't think watermarks are a suitable thing to take into account. My view is that LLM usage should be a blockable offense on any namespace, but if it ends up being allowed under some circumstances then we at least need mandatory manual disclosures for any usage. Watermarks won't work / aren't obvious enough - we need something like {{t|LLM}} but self-imposed, and not tolerate unmarked usage. ] ] 18:21, 6 December 2024 (UTC)
*::::::They will have to work at some point (e.g. ). ] (]) 06:27, 7 December 2024 (UTC)
*:Good news! {{u|Queen of Hearts}} is already working on that in {{edf|1325}}. ] (]) 16:12, 6 December 2024 (UTC)
*::See also ]. ] (]) 17:32, 6 December 2024 (UTC)
*'''Comment''' As a practical matter, users posting obvious LLM-generated content will typically be in violation of other rules (e.g. disruptive editing, sealioning), in which case their discussion comments absolutely should be ignored, discouraged, discounted, or (in severe cases) hatted. But a smaller group of users (e.g. people using LLMs as a translation tool) may be contributing productively, and we should seek to engage with, rather than discourage, them. So I don't see the need for a separate bright-line policy that risks erasing the need for discernment — in most cases, a friendly reply to the user's first LLM-like post (perhaps mentioning ], which isn't a policy or guideline, but is nevertheless good advice) will be the right approach to work out what's really going on. ] (]) 15:53, 6 December 2024 (UTC)
*:Yeah, this is why I disagree with the BLP analogy above. There's no great risk/emergency to ban the discernment. ] (]) 17:34, 6 December 2024 (UTC)
*:{{small|Those pesky ] are just the worst!}} ] (]) 18:41, 6 December 2024 (UTC)
*:Some translation tools have LLM ''assistance'', but the whole point of ''generative'' models is to create text far beyond what is found in the user's input, and the latter is clearly what this proposal covers. ] (]) 19:01, 6 December 2024 (UTC)
*::That ''might'' be what the proposal ''intends'' to cover, but it is not what the proposal ''actually'' covers. The proposal ''all'' comments that have been generated by LLMs and/or AI, without qualification. ] (]) 01:05, 7 December 2024 (UTC)
*:::70+% here understand the intention matches the language: ''generated by LLMs etc'' means "originated through generative AI tools rather than human thought", not "some kind of AI was involved in any step of the process". Even LLM translation tools don't actually ''create'' meaningful content where there wasn't any before; the generative AI aspect is only in the use of their vast training data to characterize the semantic context of your input in the form of mathematical relationships between tokens in an embedding space, and then match it with the collection of tokens most closely resembling it in the other language. There is, definitionally, a high level of creative constraint in what the translation output is since semantic preservation is required, something that is ''not'' true for text ''generation''. ] (]) 04:01, 7 December 2024 (UTC)
*::::Do you have any evidence for you assertion that 70% of respondents have interpreted the language in the same way as you? Reading the comments associated with the votes suggests that it's closer to 70% of respondents who don't agree with you. Even if you are correct, 30% of people reading a policy indicates the policy is badly worded. ] (]) 08:34, 7 December 2024 (UTC)
*:::::I think @] has summarized the respondent positions sufficiently below. I also think some portion of the opposers understand the proposal perfectly well and are just opposing anything that imposes participation standards. ] (]) 22:54, 7 December 2024 (UTC)
*::::There will be many cases where it is not possible to say whether a piece of text does or does not contain "human thought" by observing the text, even if you know it was generated by an LLM. Statements like "originated through generative AI tools rather than human thought" will miss a large class of use cases, a class that will probably grow over the coming years. People work with LLMs to produce the output they require. It is often an iterative process by necessity because people and models make mistakes. An example of when "...rather than human thought" is not the case is when someone works with an LLM to solve something like a challenging technical problem where neither the person or the model has a satisfactory solution to hand. The context window means that, just like with human collaborators, a user can iterate towards a solution through dialog and testing, exploring the right part of the solution space. Human thought is not absent in these cases, it is present in the output, the result of a collaborative process. In these cases, something "far beyond what is found in the user's input" is the objective, it seems like a legitimate objective, but regardless, it will happen, and we won't be able to see it happening. ] (]) 10:46, 7 December 2024 (UTC)
*:::::Yes, but this proposal is supposed to apply to just the obvious cases and will hopefully discourage good-faith users from using LLMs to create comments wholesale in general. It can be updated as technology progresses. There's also no reason editors using LLMs to organize/validate their arguments, or as search engines for whatever, ''have'' to copy-paste their raw output, which is much more of a problem since it carries a much higher chance of hallucination. That some people who are especially familiar with how to optimize LLM use, or who pay for advanced LLM access, will be able to deceive other editors is not a reason to ''not'' formally proscribe wholesale comment generation. ] (]) 22:27, 7 December 2024 (UTC)
*::::::That's reasonable. I can get behind the idea of handling obvious cases from a noise reduction perspective. But for me, the issue is noise swamping signal in discussions rather than how it was generated. I'm not sure we need a special rule for LLMs, maybe just a better way to implement the existing rules. ] (]) 04:14, 8 December 2024 (UTC)
*'''Support''' ] ] (]) 18:30, 6 December 2024 (UTC)
* '''Comment''': The original question was whether we should discount, ignore, strikethrough, or collapse chatbot-written content. I think there's a very big difference between these options, but most support !voters haven't mentioned which one(s) they support. That might make judging the consensus nearly impossible; as of now, supporters are the clear !majority, but supporters of ''what''? {{--}} <span style="font-family:cursive">]]</span> 19:32, 6 December 2024 (UTC)
*:That means that supporters support the proposal {{tq|that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner}}. Not sure what the problem is here. Supporters support the things listed in the proposal - we don't need a prescribed 100% strict procedure, it just says that supporters would be happy with closers discounting, ignoring or under some circumstances deleting LLM content in discussions. ] ] 19:40, 6 December 2024 (UTC)
*:Doing something? At least the stage could be set for a follow on discussion. ] (]) 19:40, 6 December 2024 (UTC)
*:More people have bolded "support" than other options, but very few of them have even attempted to refute the arguments against (and most that have attempted have done little more than handwaving or directly contradicting themselves), and multiple of those who have bolded "support" do not actually support what has been proposed when you read their comment. It's clear to me there is not going to be a consensus for anything other than "many editors dislike the idea of LLMs" from this discussion. ] (]) 00:58, 7 December 2024 (UTC)
*::Arguing one point doesn't necessarily require having to refute every point the other side makes. I can concede that "some people use LLMs to improve their spelling and grammar" without changing my view overriding view that LLMs empower bad actors, time wasters and those with competence issues, with very little to offer wikipedia in exchange. Those that use LLMs legitimately to tidy up their alledgedly competent, insightful and self-sourced thoughts should just be encouraged to post the prompts themselves instead of churning it through an LLM first. ] ] 09:00, 7 December 2024 (UTC)
*:::If you want to completely ignore all the other arguments in opposition that's your choice, but don't expect closers to attach much weight to your opinions. ] (]) 09:05, 7 December 2024 (UTC)
*::::Ok, here's a list of the main opposition reasonings, with individual responses.
*::::'''What about translations?''' - Translations are not up for debate here, the topic here is very clearly generative AI, and attempts to say that this topic covers translations as well is incorrect. No support voters have said the propositions should discount translated text, just oppose voters who are trying to muddy the waters.
*::::'''What about accessibility?''' - This is could be a legitimate argument, but I haven't seen this substantiated anywhere other than handwaving "AI could help people!" arguments, which I would lump into the spelling and grammar argument I responded to above.
*::::'''Detection tools are inaccurate''' - This I very much agree with, and noted in my support and in many others as well. But there is no clause in the actual proposal wording that mandates the use of automated AI detection, and I assume the closer would note that.
*::::'''False positives''' - Any rule can have a potential for false positives, from wp:DUCK to close paraphrasing to NPA. We've just got to as a community become skilled at identifying genuine cases, just like we do for every other rule.
*::::'''LLM content should be taken at face value and see if it violates some other policy''' - hopelessly naive stance, and a massive timesink. Anyone who has had the misfortune of going on X/twitter in the last couple of years should know that AI is not just used as an aid for those who have trouble typing, it is mainly used to and . Anyone who knows how bad the sockpuppetry issue is around CTOPs should be absolutely terrified of when (not if) someone decides to launch a full throated wave of AI bots on Misplaced Pages discussions, because if we have to invididually sanction each one like a human then admins will literally have no time for anything else.
*::::I genuinely cannot comprehend how some people could see how AI is decimating the internet through spam, bots and disinformation and still think for even one second that we should open the door to it. ] ] 10:08, 7 December 2024 (UTC)
*:::::There is no door. This is true for sockpuppetry too in my opinion. There can be a rule that claims there is a door, but it is more like a bead curtain. ] (]) 11:00, 7 December 2024 (UTC)
*:::::The Twitter stuff is not a good comparison here. Spam is already nukable on sight, mass disruptive bot edits are also nukable on sight, and it's unclear how static comments on Misplaced Pages would be the best venue to astroturf political opinions (most of which would be off-topic anyway, i.e., nukable on sight). I'd prefer if people didn't use ChatGPT to formulate their points, but if they're trying to formulate a real point then that isn't disruptive in the same way spam is. ] (]) 02:22, 10 December 2024 (UTC)
*::::::{{tq|it's unclear how static comments on Misplaced Pages would be the best venue to astroturf political opinions}} - by disrupting RFCs and talk page discussions a bad actor could definitely use chatgpt to astroturf. A large proportion of the world uses Misplaced Pages (directly or indirectly) to get information - it would be incredibly valuable thing to manipulate. My other point is that AI disruption bots (like the ones on twitter) would be indistinguishable from individuals using LLMs to "fix" spelling and grammar - by allowing one we make the other incredibly difficult to identify. How can you tell the difference between a bot and someone who just uses chatgpt for every comment? ] ] 09:16, 10 December 2024 (UTC)
*:::::::You can't. That's the point. This is kind of the whole idea of ]. ] (]) 20:22, 13 December 2024 (UTC)
*:::{{tqb|Those that use LLMs legitimately to tidy up their alledgedly competent, insightful and self-sourced thoughts should just be encouraged to post the prompts themselves instead of churning it through an LLM first.}}Social anxiety: Say "I" am a person unconfident in my writing. I imagine that when I post my raw language, I embarrass myself, and my credibility vanishes, while in the worst case nobody understands what I mean. As bad confidence is often built up through negative feedback, it's usually meritful or was meritful at some point for someone to seek outside help. ] (]) 23:46, 8 December 2024 (UTC)
*::::While I sympathise with that hypothetical, ] and we shouldn't make decisions that do long-term harm to the project just because a hypothetical user feels emotionally dependent on a high tech spellchecker. I also think that in general wikipedia (myself included) is pretty relaxed about spelling and grammar in talk/WP space. ] ] 18:45, 10 December 2024 (UTC)
*:::::We also shouldn't do long term harm to the project just because a few users are wedded to idea that LLMs are and will always be some sort of existential threat. The false positives that are an unavoidable feature of this proposal will do far more, and far longer, harm to the project than LLM-comments that are all either useful, harmless or collapseable/removable/ignorable at present. ] (]) 19:06, 10 December 2024 (UTC)
*::::::{{tq|The false positives that are an unavoidable feature of this proposal will do far more, and far longer, harm to the project}} - the same could be said for ]. The reason why its not a big problem for DUCK is because the confidence level is very high. Like I've said in multiple other comments, I don't think "AI detectors" should be trusted, and that the bar for deciding whether something was created via LLM should be very high. I 100% understand your opinion and the reasoning behind it, I just think we have differing views on how well the community at large can identify AI comments. ] ] 09:07, 11 December 2024 (UTC)
*:::::I don't see how allowing shy yet avid users to contribute has done or will do long-term harm. The potential always outweighs rational evaluation of outcomes for those with anxiety, a condition that is not behaviorally disruptive. ] (]) 02:47, 11 December 2024 (UTC)
*::::::I definitely don't want to disallow shy yet avid users! I just don't think having a "using chatgpt to generate comments is allowed" rule is the right solution to that problem, considering the wider consequences. ] ] 08:52, 11 December 2024 (UTC)
*:::::::Did you mean "... disallowed"? If so, I think we weigh-differently accessibility vs the quite low amount of AI trolling. ] (]) 14:10, 11 December 2024 (UTC)
* '''Support''' strikethroughing or collapsing per everyone else. The opposes that mention ESL have my sympathy, but I am not sure how many of them are ESL themselves. Having learnt English as my second language, I have always found it easier to communicate when users are expressing things in their own way, not polished by some AI. I sympathise with the concerns and believe the right solution is to lower our community standards with respect to ] and similar (in terms of ESL communication) without risking hallucinations by AI. ] (]) 02:52, 7 December 2024 (UTC)
* '''Oppose the use of AI detection tools'''. False positive rates for AI-detection are dramatically higher for non-native English speakers. . ~ ] (] • ]) 17:53, 8 December 2024 (UTC)
===Section break 5===
* '''Oppose''' - I'm sympathetic to concerns of abuse through automated mass-commenting, but this policy looks too black-and-white. Contributors may use LLMs for many reasons, including to fix the grammar, to convey their thoughts more clearly, or to adjust the tone for a more constructive discussion. As it stands, this policy may lead to dismissing good-faith AI-assisted comments, as well as false positives, without considering the context. Moreover, while mainstream chatbots are not designed to just mimic the human writing style, there are existing tools that can make AI-generated text more human-like, so this policy does not offer that much protection against maliciously automated contributions. ] (]) 01:12, 9 December 2024 (UTC)
*:'''Oppose''' What @] said is correct, basic AI tools like Grammarly should be allowed (note that grammarly can also change sentences and wording and has generative AI tools) but just blatantly asking ChatGPT to generate a administrator report is different. ] (]) 04:46, 1 January 2025 (UTC)
* '''Oppose''' – Others have cast doubt on the efficacy of tools capable of diagnosing LLM output, and I can't vouch for its being otherwise. If EEng's example of ChatBot output is representative—a lengthy assertion of notability without citing sources—that is something that could well be disregarded whether it came from a bot or not. If used carefully, AI can be useful as an aide-memoire (such as with a spell- or grammar-checker) or as a supplier of more felicitous expression than the editor is naturally capable of (e.g. Google Translate). ] (]) 10:27, 9 December 2024 (UTC)
* '''Comment''' / '''Oppose as written'''. It's not accurate that GPTZero is good at detecting AI-generated content. Citations (slightly out of date but there's little reason to think things have changed from 2023): https://www.aiweirdness.com/writing-like-a-robot/ , https://www.aiweirdness.com/dont-use-ai-detectors-for-anything-important/ . For those too busy to read, a few choice quotes: "the fact that it insisted even one excerpt is not by a human means that it's useless for detecting AI-generated text," and "Not only do AI detectors falsely flag human-written text as AI-written, the way in which they do it is biased" (citing https://arxiv.org/abs/2304.02819 ). Disruptive, worthless content can already be hatted, and I'm not opposed to doing so. Editors should be sharply told to use their own words, and if not already written, an essay saying we'd rather have authentic if grammatically imperfect comments than AI-modulated ones would be helpful to cite at editors who offer up AI slop. But someone merely citing GPTZero is not convincing. GPTZero will almost surely misidentify genuine commentary as AI-generated. So fine with any sort of reminder that worthless content can be hatted, and fine with a reminder not to use ChatGPT for creating Misplaced Pages talk page posts, but not fine with any recommendations of LLM-detectors. ] (]) 20:00, 9 December 2024 (UTC)
*:@], I can't tell if you also oppose the actual proposal, which is to permit hatting/striking obvious LLM-generated comments (using GPTzero is a very minor detail in JSS's background paragraph, not part of the proposal). ] (]) 01:47, 11 December 2024 (UTC)
*:::I support the proposal in so far as disruptive comments can already be hatted and that LLM-generated content is disruptive. I am strongly opposed to giving well-meaning but misguided editors a license to throw everyone's text into an AI-detector and hat the comments that score poorly. I don't think it was ''that'' minor a detail, and to the extent that detail is brought up, it should be as a reminder to use human judgment and ''forbid'' using alleged "AI detectors" instead. ] (]) 03:49, 11 December 2024 (UTC)
* '''Support''' collapsing AI (specifically, ]) comments by behavioral analysis (most actually disruptive cases I've seen are pretty obvious) and not the use of inaccurate tools like ZeroGPT. I thinking hatting with the title "Editors suspect that this comment has been written by a ]" is appropriate. They take up SO much space in a discussion because they are also unnecessarily verbose, and talk on and on but never ever say something that even approaches having substance. Discussions are for human Misplaced Pages editors, we shouldn't have to use to sift through comments someone put 0 effort into and outsourced to a robot that writes using random numbers (that's a major part of how tools like ChatGPT work and maintain variety). If someone needs to use an AI chatbot to communicate because they don't understand English, then they are welcome to contribute to their native language Misplaced Pages, but I don't think they have the right to insist that we at enwiki spend our effort reading comments they but minimal effort into besides opening the ChatGPT website. If really needed, they can write in their native language and use a non-LLM tool like Google Translate. The use of non-LLM tools like Grammarly, Google Translate, etc. I think should still be OK for all editors, as they only work off comments that editors have written themselves. ] <sup>]]</sup> 05:10, 10 December 2024 (UTC)
*:Adding that enforcing people writing things in their own words will actually help EAL (English additional language) editors contribute here. I world with EAL people irl, and even people who have almost native proficiency with human-written content find AI output confusing because it says things in the most confusing, verbose ways using difficult sentence constructions and words. I've seen opposers in this discussion who maybe haven't had experience working with EAL people go "what about EAL people?", but really, I think this change will help them (open to being corrected by someone who is EAL, tho). ] <sup>]]</sup> 05:17, 10 December 2024 (UTC)
*:Also, with regards to oppose comments that discussions are not a vote so closes will ignore AI statements which don't have merit - unedited LLM statements are incredibly verbose and annoying, and clog up the discussion. Imagine multiple paragraphs, each with a heading, but all of which say almost nothing, they're borderline ]y. Giving the power to HAT them will help genuine discussion contributors keep with the flow of human arguments and avoid scaring away potential discussion contributors who are intimidated or don't feel they have the time to read the piles of AI nonsense that fill the discussion. ] <sup>]]</sup> 06:38, 10 December 2024 (UTC)
* '''Support''' (removing) in general. How is this even a question? There is no case-by-case. It is a fundamental misunderstanding of how LLMs work to consider their output reliable without careful review. And which point, the editor could have written it themselves without inherent LLM bias. The point of any discussion is to provide analytical response based on the ''context'', not have some tool regurgitate something from a training set that sounds good. And frankly, it is disrespectuful to make someone read "AI" responses. It is a tool and there is a place and time for it, but not in discussions in an encyclopedia. — <small> ] <b>∣</b> ]</small> 15:41, 10 December 2024 (UTC)
*'''Strong Support'''. I'm very interested in what you (the generic you) have to say about something. I'm not remotely interested in what a computer has to say about something. It provides no value to the discussion and is a waste of time. ] (]) 18:06, 10 December 2024 (UTC)
*:Comments that provide no value to the discussion can already be hatted and ignored regardless of why they provide no value, without any of the false positive or false negatives inherent in this proposal. ] (]) 18:25, 10 December 2024 (UTC)
*::Indeed, and that's fine for one-offs when a discussion goes off the rails or what-have-you. But we also have ] for disruptive behavior, not working collaboratively, etc. I'm suggesting that using an AI to write indicates that you're not here to build the encyclopedia, you're here to have an AI build the encyclopedia. I reiterate my strong support for AI-written content to be removed, struck, collapsed, or hatted and would support further measures even beyond those. ] (]) 21:54, 11 December 2024 (UTC)
*:::There are two sets of people described in your comment: those who use AI and those who are NOTHERE. The two sets overlap, but nowhere near sufficiently to declare that everybody in the former set are also in the latter set. If someone is NOTHERE they already can and should be blocked, regardless of how they evidence that. Being suspected of using AI (note that the proposal does not require proof) is not sufficient justification on its own to declare someone NOTHERE, per the many examples of constructive use of AI already noted in this thread. ] (]) 22:03, 11 December 2024 (UTC)
*::::To reiterate, I don't believe that any use of AI here is constructive, thus using it is evidence of ], and, therefore, the set of people using AI to write is completely circumscribed within the set of people who are NOTHERE. Please note that I am referring to users who use AI-generated writing, not users suspected of using AI-generated writing. I won't be delving into how one determines whether someone is using AI or how accurate it is, as that is, to me, a separate discussion. This is the end of my opinion on the matter. ] (]) 23:26, 11 December 2024 (UTC)
*:::::You are entitled to your opinion of course, but as it is contradicted by the evidence of both multiple constructive uses and of the near-impossibility of reliably detecting LLM-generated text without false positives, I would expect the closer of this discussion to attach almost no weight to it. ] (]) 00:42, 12 December 2024 (UTC)
*:::::I am ESL and use LLMs sometimes because of that. I feel like I don't fit into the NOTHERE category. It seems like you do not understand what they are or how they can be used constructively. ] (]) 01:43, 12 December 2024 (UTC)
*::::::No, I understand. What you're talking about is no different from using Google Translate or asking a native-speaker to translate it. You, a human, came up with something you wanted to convey. You wrote that content in Language A. But you wanted to convey that message that you - a human - wrote, but now in Language B. So you had your human-written content translated to Language B. I have no qualms with this. It's your human-written content, expressed in Language B. My concern is with step 1 (coming up with something you want to convey), not step 2 (translating that content to another language). You write a paragraph for an article but it's in another language and you need the paragraph that you wrote translated? Fine by me. You ask an AI to write a paragraph for an article? Not fine by me. Again, I'm saying that there is no valid use case for AI-written content. ] (]) 15:59, 12 December 2024 (UTC)
*:::::::It seems very likely that there will be valid use cases for AI-written content if the objective is maximizing quality and minimizing errors. Research like demonstrate that there will likely be cases where machines outperform humans in specific Misplaced Pages domains, and soon. But I think that is an entirely different question than potential misuse of LLMs in consensus related discussions. ] (]) 16:25, 12 December 2024 (UTC)
*:::::::But your vote and the proposed above makes not distinction there. Which is the main issue. Also not to be pedantic but every prompted to a LLM is filled out by a human looking to convey a message. Every time someone hits publish on something here it is that person confirming that is what they are saying. So how do we in practice implement what you suggest? Because without a method better than vibes it's worthless. ] (]) 18:53, 12 December 2024 (UTC)
*::::::::The proposal specifies content ''generated'' by LLMs, which has a specific meaning in the context of generative AI. If a prompt itself conveys a meaningful, supported opinion, why not just post that instead? The problem comes when the LLM adds more information than was provided, which is the whole point of generative models. ] (]) 01:52, 13 December 2024 (UTC)
* '''Yes''' in principle. But in practice, LLM detectors are not foolproof, and there are valid reasons to sometimes use an LLM, for example to copyedit. I have used Grammarly before and have even used the Microsoft Editor, and while they aren't powered by LLMs, LLMs are a tool that need to be used appropriately on Misplaced Pages. ] ] 19:55, 10 December 2024 (UTC)
* '''Support'''. Using LLM to reply to editors is lazy and disrespectful of fellow editor's time and brainpower. In the context of AFD, it is particularly egregious since an LLM can't really read the article, read sources, or follow our notability guidelines. {{pb}} By the way. {{tq|gptzero and other such tools are very good at detecting this}}. I don't think this is correct at all. I believe the false positive for AI detectors is quite high. High enough that I would recommend not using AI detectors. –] <small>(])</small> 03:23, 11 December 2024 (UTC)
*'''Question''' @]: Since there appears to be a clear consensus against the AI-detectors part, would you like to strike that from the background? ] (]) 14:10, 11 December 2024 (UTC)
* '''Support'''. AI generated text should be removed outright. If you aren't willing to put the work into doing your own writing then you definitely haven't actually thought deeply about the matter at hand. ]]] 14:16, 11 December 2024 (UTC)
*:This comment is rather ironic given that it's very clear you haven't thought deeply about the matter at hand, because if you had then you'd realise that it's actually a whole lot more complicated than that. ] (]) 14:26, 11 December 2024 (UTC)
*::Thryduulf I don't think this reply is particular helpful, and it comes off as slightly combative. It's also by my count your 24th comment on this RFC. ] ] 19:20, 11 December 2024 (UTC)
*::I recognize that AI paraphrased or edited is not problematic in the same ways as text generated outright by an AI. I only meant to address the core issue at steak, content whose first draft was written by an AI system. ]]] 22:16, 17 December 2024 (UTC)
*'''Oppose''' {{re|Just Step Sideways}} The nomination's 2nd para run through https://www.zerogpt.com/ gives "11.39% AI GPT*":{{pb}}{{tqb|I've recently come across several users in AFD discussions that are using LLMs to generate their remarks there. As many of you are aware, gptzero and other such tools are very good at detecting this. I don't feel like any of us signed up for participating in discussions where some of the users are not using their own words but rather letting technology do it for them. Discussions are supposed to be between human editors. <mark>If you can't make a coherent argument on your own, you are not competent to be participating in the discussion.</mark> I would therefore propose that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner}}{{pb}}The nomination's linked https://gptzero.me/ site previously advertised https://undetectable.ai/ , wherewith how will we deal? Imagine the nomination was at AFD. What should be the response to LLM accusations against the highlighted sentence? ] (]) 17:41, 11 December 2024 (UTC)
* '''Support''' with the caveat that our ability to deal with the issue goes only as far as we can accurately identify the issue (this appears to have been an issue raised across a number of the previous comments, both support and oppose, but I think it bears restating because we're approaching this from a number of different angles and its IMO the most important point regardless of what conclusions you draw from it). ] (]) 19:24, 11 December 2024 (UTC)
*'''Strong support, limited implementation'''. {{tq|1=Misplaced Pages is written by volunteer editors}}, says our front page. This is who ''we'' are, and ''our'' writing is what Misplaced Pages is. It's true that LLM-created text can be difficult to identify, so this may be a bit of a moving target, and we should be conservative in what we remove—but I'm sure at this point we've all run across cases (whether here or elsewhere in our digital lives) where someone copy/pastes some text that includes "Is there anything else I can help you with?" at the end, or other blatant tells. This content should be deleted without hesitation. ] (]) 04:11, 12 December 2024 (UTC)
* '''Support in concept, questions over implementation''' — I concur with {{U|Dronebogus}} that users who rely on LLMs should not edit English Misplaced Pages. It is not a significant barrier for users to use other means of communication, including online translators, rather than artificial intelligence. How can an artificial intelligence tool argue properly? However, I question how this will work in practice without an unacceptable degree of error. <span style="font-family: monospace;">] (he/him)</span> 22:39, 12 December 2024 (UTC)
*:Many, possibly most, online translators use artificial intelligence based on LLMs these days. ] (]) 22:46, 12 December 2024 (UTC)
*::There is a difference between translating words you wrote in one language into English and using an LLM to write a comment for you. <span style="font-family: monospace;">] (he/him)</span> 22:59, 12 December 2024 (UTC)
*:::Neither your comment nor the original proposal make any such distinction. ] (]) 23:34, 12 December 2024 (UTC)
*::::Well since people keep bringing this up as a semi-strawman: no I don’t support banning machine translation, not that I ''encourage'' using it (once again, if you aren’t competent in English please don’t edit here) ] (]) 07:34, 13 December 2024 (UTC)
*:LLMs are incredible at translating, and many online translators already incorporate them, including Google Translate. Accomodating LLMs is an easy way to support the avid not only the ESL but also the avid but shy. It has way more benefits than the unseen-to-me amount of AI trolling that isn't already collapse-on-sight. ] (]) 00:05, 13 December 2024 (UTC)
*::Google Translate uses the same transformer architecture that LLMs are built around, and uses e.g. PaLM to develop more language support (through training that enables zero-shot capabilities) and for larger-scale specialized translation tasks performed through the Google Cloud "" API, but it does not incorporate LLMs into ''translating your everyday text input'', which still relies on NMTs. And even for the API features, the core constraint of ''matching'' input rather than ''generating content'' is still retained (obviously it would be very bad for a translation tool to insert material not found in the original text!). LLMs might be good for translation because they are better at evaluating semantic meaning and detecting context and nuance, but again, the ''generative'' part that is key to this proposal is not present. ] (]) 01:20, 13 December 2024 (UTC)
*:::{{tq|PaLM (Pathways Language Model) is a 540 billion-parameter transformer-based large language model (LLM) developed by Google AI.}} If you meant something about how reschlmunking the outputs of an LLM or using quite similar architecture is not really incorporating the LLM, I believe we would be approaching ] levels of recombination, to which my answer is it is the same ship.{{tqb|obviously it would be very bad for a translation tool to insert material not found in the original text!}} ] (]) 01:29, 13 December 2024 (UTC)
*::::PaLM2 is not used in the consumer app (Google Translate), it's used for research. Google Translate just uses non-generative NMTs to map input to its closes cognate in the target language. ] (]) 01:34, 13 December 2024 (UTC)
*:::::Well, is the NMT really that different enough to not be classified as an LLM? IIRC the definition of an LLM is something that outputs by predicting one-by-one what the next word/"token" should be, and an LLM I asked agreed that NMTs satisfy the definition of a generative LLM, though I think you're the expert here. ] (]) 02:01, 13 December 2024 (UTC)
*::::::Google Translate's NMT hits different enough to speak English much less naturally than ChatGPT 4o. I don't consider it a '''''L'''''LM, because the param count is 380M not 1.8T.
*::::::{{tq|the definition of an LLM is something that outputs by predicting one-by-one what the next word/"token" should be}} No, that def would fit ancient ] tech too. ] (]) 17:50, 13 December 2024 (UTC)
*:::::::Even if you don’t consider it L, I do, and many sources cited by the article do. Since we’ll have such contesting during enforcement, it’s better to find a way that precludes such controversy. ] (]) 20:44, 13 December 2024 (UTC)
*::::::::NMTs, LLMs, and the text-creation functionality of LLMs are fundamentally different in the context of this discussion, which is about content generated through generative AI. NMTs specifically for translation: they are trained on parallel corpora and their output is optimized to match the input as precisely as possible, ''not'' to create novel text. LLMs have different training, including way more massive corpora, and were designed specifically to create novel text. One of the applications of LLMs may be translation (though currently it's too computationally intensive to run them for standard consumer purposes), by virtue of their being very good at determining semantic meaning, but even if/when they do become mainstream translation tools what they'll be used for is still ''not'' generative when it comes to translation output. ] (]) 22:29, 13 December 2024 (UTC)
*:::::::::How will you differentiate between the use of LLM for copyediting and the use of LLM for generation? ] (]) 23:30, 13 December 2024 (UTC)
*::::::::::The proposal is for hatting obvious cases of LLM-generated comments. Someone who just uses an LLM to copyedit will still have written the content themselves and presumably their output would not have the obvious tells of generative AI. ] (]) 23:56, 13 December 2024 (UTC)
*:{{outdent|9}} Not when I tried to use it. Quantitatively, GPTZero went from 15% human to 100% AI for me despite the copyedits only changing 14 words. ] (]) 00:33, 14 December 2024 (UTC)
*::I think there is consensus that GPTZero is not usable, even for obvious cases. ] (]) 00:55, 14 December 2024 (UTC)
*:::Yes, but being as far as 100% means people will also probably think the rewrite ChatGPT-generated. ] (]) 01:18, 14 December 2024 (UTC)
*::::Does it really mean that? All you've demonstrated is that GPTZero has false positives, which is exactly why its use here was discouraged. ] (]) 05:26, 14 December 2024 (UTC)
*:::::My subjective evaluation of what I got copyediting from ChatGPT was that it sounded like ChatGPT. I used GPTZero to get a number. ] (]) 14:18, 14 December 2024 (UTC)
*::::::My guess is that the copyediting went beyond what most people would actually call "copyediting". ] (]) 18:04, 23 December 2024 (UTC)
*:::::::It changed only 14 words across two paragraphs and still retained the same meaning in a way that I would describe it as copyediting. Such levels of change are what those lacking confidence in tone would probably seek anyways. ] (]) 00:15, 24 December 2024 (UTC)
* On one hand, AI slop is a plague on humanity and obvious LLM output should definitely be disregarded when evaluating consensus. On the other hand, I feel like existing policy covers this just fine, and any experienced closer will lend greater weight to actual policy-based arguments, and discount anything that is just parroting jargon. <span class="nowrap">] <sub>]</sub> <sup>(] • ])</sup></span> 23:21, 12 December 2024 (UTC)
*'''Support in principle''', but we cannot rely on any specific tools because none are accurate enough for our needs. Whenever I see a blatant ChatGPT-generated !vote, I ignore it. They're invariably poorly reasoned and based on surface-level concepts rather than anything specific to the issue being discussed. If someone is using AI to create their arguments for them, it means they have no actual argument besides ] and are looking for arguments that support their desired result rather than coming up with a result based on the merits. Also, toasters do not get to have an opinion. <span style="font-family:Papyrus, Courier New">]</span><sup><span style="font-family:Papyrus"><small>'']''</small></span></sup> 05:17, 13 December 2024 (UTC)
*'''Oppose'''. For creating unnecessary drama. First of, the "detector" of the AI bot is not reliable, or at least the reliability of the tool itself is still questionable. If the tool to detect LLM itself is unreliable, how can one reliably point out which one is LLM and which one is not? We got multiple tools that claimed to be able to detect LLM as well. Which one should we trust? Should we be elevating one tool over the others? Have there been any research that showed that the "picked" tool is the most reliable? Second, not all LLMs are dangerous. We shouldn't treat LLM as a virus that will somehow take over the Internet or something. Some editors use LLM to smooth out their grammar and sentences and fix up errors, and there is nothing wrong with that. I understand that banning obvious LLM text per ] are good, but totally banning them is plain wrong. ] ] 22:56, 15 December 2024 (UTC)
*:@], the proposal is to permit editors to collapse/strike ''obvious LLM text'', not to "ban LLM totally". If LLM use is imperceptible, like for tweaking grammar, it's not going to be affected. ] (]) 20:17, 19 December 2024 (UTC)
*'''Support''' with some kind of caveat about not relying on faulty tools or presuming that something is LLM without evidence or admission, based on the following reasons:
*# We have stricter rules around semi-automated editing (rollback, AutoWikiBrowser, etc.) and even stricter rules around fully automated bot editing. These cleanup edits are widely accepted as positive, but there is still the concern about an overwhelming amount of bad edits to wade through and/or fix. A form of that concern is relevant here. Someone could reply to every post in this discussion in just a minute or so without ever reading anything. That's inherently disruptive.
*# Nobody who is voting "oppose" is using an LLM to cast that vote. The LLM comments have been left by those supporting to make a point about how problematic they are for discussions like this. I think this reflects, even among oppose voters, a developing community consensus that LLM comments will be disregarded.
*# If the rule in practice is to disregard LLM comments, not writing that rule down does not stop it from being the rule, consensus, or a community norm. It just makes the rule less obvious and less clear.
*# It's disrespectful for an editor to ask someone to spend their time reading a comment if they couldn't be bothered to spend any time writing it, and therefore a violation of the policy ], "{{tq|treat your fellow editors as respected colleagues with whom you are working on an important project.}}"
* Also, I don't read the proposal as a ban on machine translation in any way. ] (]) 00:01, 18 December 2024 (UTC)
*:@], above @] said their !vote was created by LLM. ] (]) 20:14, 19 December 2024 (UTC)
* I am '''strongly opposed''' to banning or ignoring LLM-made talk page comments ''just'' because they are LLM-made. I'm not a big fan of LLMs at all; they are actually useful only for some certain things, very few of which are directly relevant to contributing to Misplaced Pages in English or in any other language. However, some of those things ''are'' useful for this, at least for some humans, and I don't want to see these humans being kicked out of the English Misplaced Pages. I already witnessed several cases in which people whose first language is not English tried writing talk page responses in the English Misplaced Pages, used an LLM to improve their writing style, and got their responses ignored ''only'' because they used an LLM. In all those cases, I had strong reasons to be certain that they were real humans, that they meant what they wrote, and that they did it all in good faith. Please don't say that anyone who wants to contribute to the English Wikipeida should, in the first place, know English well enough to write a coherent talk page comment without LLM assistance; occasionally, I kind of wish that it was like that myself, but then I recall that the world is more complicated and interesting than that. Uses of LLMs that help the English Misplaced Pages be more inclusive for good-faith people are good. Of course, defining what good faith means is complicated, but using an LLM is not, ''by itself'', a sign of bad faith. --] (]) 04:52, 19 December 2024 (UTC)
*:Those concerned about their English should use translation software rather than an llm. Both might alter the meaning to some extent, but only one will make things up. (It's also not a sure assumption that llm text is coherent talkpage text.) ] (]) 07:44, 19 December 2024 (UTC)
*::@] The dividing line between translation software and LLM is already blurry and will soon disappear. It's also rare that translation software results in coherent talkpage text, ''unless'' it's relying on some (primitive) form of LLM. So if we're going to outlaw LLMs, we would need to outlaw any form of translation software, and possibly any text-to-speech software as well. <span style="font-family:cursive">]]</span> 23:41, 19 December 2024 (UTC)
*:::The distinctions have already been covered above, and no we would not have to. There is an obvious difference between software intended to translate and software intended to generate novel text, and users are likely to continue to treat those differently. ] (]) 02:49, 20 December 2024 (UTC)
*'''Strong support'''. LLM-generated content has no place anywhere on the encyclopedia. ] (]) 10:27, 19 December 2024 (UTC)
*'''Strong oppose''' to the proposal as written. Misplaced Pages already suffers from being ] in a ] ] and a refusal to move with the technological times. Anyone who remembers most Wikipedians' visceral reaction to ] and ] when they were first introduced will observe a striking similarity. Yes, those projects had serious problems, as do LLM-generated comments. But AI is the future, and this attitude of "]" will ultimately lead Misplaced Pages the way of ''Encyclopædia Britannica''. Our discussion needs to be how best to change, not how to avoid to change. <span style="font-family:cursive">]]</span> 23:54, 19 December 2024 (UTC)
*:{{smalldiv|1=The main objection to VE and a major objection to FLOW was the developers' insistence on transforming Wikitext to HTML for editing and then transforming that back to Wikitext. ] (]) 01:31, 20 December 2024 (UTC)}}
*::True. Then, as now, there were many valid objections. But IIRC, there was limited discussion of "Let's figure out a better way to improve", and lots of "Everything is fine; don't change anything, ever." That attitude concerns me. <span style="font-family:cursive">]]</span> 01:52, 20 December 2024 (UTC)
*:I oppose the proposal but I think the comparison to FLOW and VisualEditor is beyond silly. Those things did not exist outside of a MediaWiki context. LLMs are a global issue. ] (]) 17:11, 28 December 2024 (UTC)
*'''Support'''. I'm not even slightly swayed by these "it'll be too hard to figure out" and "mistakes could be made" and "we can't be 100% certain" sorts of arguments. That's true of {{em|everything}} around here, and its why we have an admins-must-earn-a-boatload-of-community-trust system, and a system of review/appeal of decisions they (or of course non-admin closers) make, and a consensus-based decisionmaking system more broadly. {{U|JoelleJay}} has it exactly right: {{tq|having a policy that permits closers to discount apparently-LLM-generated contributions will discourage good-faith editors from using LLMs irresponsibly and perhaps motivate bad-faith editors to edit the raw output to appear more human, which would at least involve some degree of effort and engagement with their "own" arguments.}} And as pointed out by some others, the "it'll hurt non-native-English speakers" nonsense is, well, nonsense; translation is a different and unrelated process (though LLMs can perform it to some extent), of remapping one's {{em|own}} material onto another language.<!-- --><p>I'm also not in any way convinved by the "people poor at writing and other cognitive tasks needs the LLM to help them here" angle, because ] is required. This is work (albeit volunteer work), it is ] a game, a social-media playground, a get-my-ideas-out-there soapbox, or a place to learn how to interact e-socially or pick up remedial writing skills, nor a venue for practicing one's argument techiques. It's an encyclopedia, being built by people who – to be productive contributors instead of a draining burden on the entire community – {{em|must}} have: solid reasoning habits, great judgement (especially in assessing reliability of claims and the sources making them), excellent writing skills of a highly particularized sort, a high level of fluency in this specific language (in multiple registers), and a human-judgement ability to understand our thick web of policies, guidelines, procedures, and often unwritten norms, and how they all interact, in a specific contextual way that may vary greatly by context. None of these is optional. An LLM cannot do any of them adequately (not even write well; their material sticks out like a sore thumb, and after a while you can even tell which LLM produced the material by its habitual but dinstictive crappy approach to simulating human thought and language).</p><!-- --><p>In short, if you {{em|need}} an LLM to give what you think is meaningful input into a decision-making process on Misplaced Pages (much less to generate mainspace content for the public), then you {{em|need}} to go find something else to do, something that fits your skills and abilities. Saying this so plainly will probably upset someone, but so it goes. I have a rep for "not suffering fools lightly" and "being annoying but correct"; I can live with that if it gets the right decisions made and the work advanced. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 05:49, 22 December 2024 (UTC)</p><p>PS, something that came up more recently than my original post above: If anyone's wondering why some of us are such "AI" skeptics, its because the technology is badly, badly faulty, producing multiple blatant factual errors even in short material, entirely fictive "hallucinations", direct forgery of sourcing, nested chains of error compounded upon error when context isn't gleaned properly, disingenuous attempts to hide that it is lying, and worse. A few days ago, I got ChatGPT 4o to literally {{em|lose its f#*$ing mind}}: I had it generate some short code (very simple one-liner regex) with a really obvious error, so I pointed out the error and gave it documentation that proved it was an error. It conceded the error and even explained what the error was and why it was erroneous, then said how it was going to fix it. And ... proceeded to output the same error again (in just one of three examples, the other two being correct). Fascinated and horrified by this, I tried for over half an hour to get it to produce a correct example, and it was utterly incapable of doing it. It knew the error was an error and what that error was and why, spelled out what the correct approach should be, then repeated the error {{em|every single time}} (always at the first occurrence, or always if the only occurrence). I've captured that session and will be doing a write-up about it. This is much, much worse that a "hallucination", being an abject inability to stop doing what it already knows is absolutely wrong. When people have fears like "If I had a house AI, and it was in control of the bathwater temperature, it might boil my children alive", they are not paranoid or unreasonable. My experiment with ChatGPT proves this conclusively. If the AI can (with trivial effort) be put into a crazy failure-looping state where it knows it's doing or about to do something wrong but insists on doing it anyway – i.e. during its take-an-action phase it completely loses connection to reality, even it's internal reality much less external input telling it "no!" – then we are in grave danger. This is essentially the mental state of a psychopath: "I know I shouldn't grab my neighbor's little daughter and strangle her to death, but I just can't stop myself." <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:42, 28 December 2024 (UTC)</p>
*:The problem with all that is that we ''already'' have a policy that allows the hatting or removal of comments that are actually problematic because of their content (which are the only ones that we should be removing) without regard for whether it was or was not written by LLM. Everything that actually should be removed can be removed already. ] (]) 11:39, 22 December 2024 (UTC)
*::If that's "the problem with all that", then it is not any kind of problem at all. It's entirely normal in our ] material to reiterate a principle defined in one place for contextual application at another, and to extrapolate from a general principle to a more specific application. We do this often to cut through the exact kind of wikilawyering we're facing over this issue: there's not a {{em|specific rule}} against LLM-generated !voting, so the argument is (again and again in this thread) to permit it (unless it's such senseless gibberish that it would be removed anyway even if no LLM were involved). The community clearly doesn't actually want that result (or more accurately, there is not a consensus in favor of it), though this {{em|specific}} proposal's approach to thwarting the "AI"-spamming of our decision-making processes might not be perfect. To me, it's a step in the right direction. If it were implemented this way and some uncommon issue arose with that implementation, then we'd tweak it to address that micro-problem. We must not continue to avoid addressing the macro-problem just because someone can imagine edge cases that might not work out ideally. That, too, is true of all of our P&G and process. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:15, 28 December 2024 (UTC)
*:People who have good reading skills, great judgement, and solid reasoning habits enough to find problems in existing articles don't necessarily have great interpersonal writing/communication skills or the confidence. Meanwhile, for all LLM is bad at, it is very good at diluting everything you say to become dry, dispassionate, and thus inoffensive. ] (]) 15:26, 22 December 2024 (UTC)
*::I doubt that anyone would seriously object to some ultra-hothead running their post through an LLM with a query like "Can you see anything in this that might come off as aggressive or offensive, and suggest a revision that only affects that aspect of the material?" The result might not even be noticeable as LLM-modified. If it doesn't stick out as LLM garbage, there there is no way for this proposal to affect such a post, because no one here is a mind-reader (we cannot magically detect through remote sensing that someone toned their rant down with LLM help). So, this proposal is not broken (at least not with regard to that scenario). That said, the main reason that WP:COMPETENCE was written (and it's one of the essays that, like ] and ], has become "operative" within the community as if a policy or guideline) is the very "don't necessarily have great interpersonal ... skills" issue you mention. That is, lacking those skills to a serious enough degree makes one not competent to work on a collaborative encyclopedia project, and one will eventually be ejected after causing enough disruption. Something we don't need is LLMs masking for a while that someone has this kind of competence failure; it will just drag out the inevitable. By way of analogy: if I were a kleptomaniac and just unable to stop myself from shoplifting, it would not be okay for me to use a device that scrambled stores' surveillance camera footage to make it more likely for me to get away with more shoplifting (and there would certainly be no obligation on the part of the store owner to turn their cameras off, or to take no action if they catch me stealing, just because I tell them I'm a kleptomaniac and my unconstructive behavior isn't something I can manage. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:15, 28 December 2024 (UTC)
*:::People who can't communicate that well often won't attempt to burn others down. I don't think there's any disruption or substantial additional investment in accommodating those who won't burn others down (which I'd say is the majority) by reading their perfectly comprehensible AI-diluted arguments. (Scrambling footage is like erasing the memories of the incident, which I don't think is a good analogue of the issue at hand. I'd say it's more like working with someone who stinks and masks that with perfume.) ] (]) 00:05, 29 December 2024 (UTC)
*:I'm pretty sure most people here understand why there are AI skeptics. I also hate ChatGPT. But there's a difference between my personal opinion of ChatGPT and the fact that someone using ChatGPT to communicate is still communicating. The risk of your house AI hallucinating is that your children get boiled alive. The risk of ChatGPT hallucinating on a talk page is that they make a dumb, disregardable argument, of the kind that humans pump out by the thousands. (Someone linked an example of some AfD delete !votes generated by AI and frankly they're better reasoned than a lot of the stuff humans post.) ] (]) 17:32, 28 December 2024 (UTC)
*:(The bigger issue is people using Misplaced Pages ''as ChatGPT'' -- i.e. posting the prompts, not the responses -- but, like much of what is being discussed here, that is already stuff that can be removed.) ] (]) 17:36, 28 December 2024 (UTC)
*ok, I agree with @], so therefore my vote is '''Support.''' ] (]) 12:41, 25 December 2024 (UTC)
*'''Support'''. Sure I have questions about detection, but I don't think it means we shouldn't have a policy that explicitly states that it should not be used (and can be ignored/hatted if it is). Judging solely based on content (and no wp:bludgeoning, etc.) is unsustainable IMO. It would mean taking every wall of text seriously until it's clear that the ''content'' is unhelpful, and LLMs are very good at churning out plausible-sounding bullshit. It wastes everyone's time. If cognitive impairments or ESL issues make it hard to contribute, try voice-to-text, old-school translation software, or some other aid. LLMs aren't really ''you''.--] (]) 11:27, 23 December 2024 (UTC)
* '''Comment'''. While I agree with the sentiment of the request, I am at a loss to see how we can identify LLM generated comments in a consistent manner that can scale. Yes, it might be easier to identify egregious copy paste of wall of text, but, anything other than that might be hard to detect. Our options are:
:# Robust tooling to detect LLM generated text, with acceptably low levels of false positives. Somewhat similar to what Earwig does for Copyvios. But, someone needs to build it and host it on WMTools or at a similar location.
:# Self certification by editors. Every edit / publish dialogbox should have a checkbox for "Is this text LLM generated" with y/n optionality.
:# Editors playing a vigilante role in reading the text and making a personal call on other editors' text. Obviously this is least preferred.
: These are my starting views. ] (]) 00:37, 24 December 2024 (UTC)
::A couple of days ago, an editor ran a new article through GPTzero, and was told that it was 99.8% likely to be AI-generated. I ran the same revision of the same article through the same tool the next day, and it told me that it was 98.3% likely to be human-written.
::Now we're left scratching our heads: Why the difference? Which answer is correct? ] (]) 04:36, 26 December 2024 (UTC)
*'''Strong oppose''' as it's impossible to enforce. Also LLMs are a valid and useful ] tool. – ] 05:18, 24 December 2024 (UTC)
*'''Bonus suggestion!''': I'm curious what Wikipedians think about this so let's try this. Many of the comments here discuss the impracticality of determining whether a user's comments are AI generated (i.e. gptzero isn't perfect), and many give valid arguments for using LLMs (i.e. ]). If an argument is suspected to be written by LLM, I propose that editors should examine the user. Take a look at their listed contributions, and if they seem to have a habit of using AI, open a discussion on their talk page. If the user has a habit of using AI and doesn't recognize the inherent problems and refuses to change, this can be brought to ] for potential blocks. If (and only if) the person is blocked for using AI, their comments can be ignored. Or just ask ChatGPT to summarize them for you lol ] (]) 06:12, 25 December 2024 (UTC)
*:I think that the general idea here is good: As much as possible, treat each account individually, and handle LLM use as a behavioral problem when it's actually a practical problem (i.e., not when it seems to be accurate and seems to be appropriate). ] (]) 04:38, 26 December 2024 (UTC)
*:Except a substantial portion of the input in this thread is disagreement with the idea that English being someone's second language is an excuse for LLM-generated content at all. Translation of one's own material is an entirely different process (even if often leveraged by LLMs set to a different task than trying to generate what they "think" is new material that will pass as human-authored). I'm skeptical that any of the other things you're accepted as "valid arguments" from the pro-LLM or LLM-accepting side of this debate have consensus as valid, either. But go ahead and spell them out and we'll see. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:30, 28 December 2024 (UTC)
* '''Strong support''' the removal of any obvious, low effort AI-generated post. I recently came across a user such examples. When called out on it and posted a comment saying, amongst other things "''HAHAHAHHAHAHAHAHAHAHHAHAHAHAHAHA. Yes, some of it might be. Because I don't have time to argue with, in my humble opinion, stupid PHOQUING people.''" and "''YOUUUUUUUUUUUUUUUUUUUUUUUUUUUU are assuming bath faith in me.''"
:They were later blocked as a sock evading a global lock.
:Currently it is too easy for trolls to game ] and AI to waste people's time arguing with their bot-generated replies. Using AI to write your posts for you makes it difficult for others to assume good faith. I am ok with obvious exceptions like a non-native speaker using AI to help them articulate their point. ] (]) 21:29, 25 December 2024 (UTC)
* '''Support''' for any and all reasons above. I'd be in favor of entirely banning AI-written text on the platform in articlespace as well. <!-- Template:Unsigned --><small class="autosigned">— Preceding ] comment added by ] (] • ]) 00:05, 27 December 2024 (UTC)</small>
*'''Support''' though with caution, as there are the possibility for false positives. ] ''<span style="font-size:small; vertical-align:top;">]</span>''·''<span style="font-size:small; vertical-align:bottom;">]</span>'' 00:14, 29 December 2024 (UTC)
*'''Support''' for now. I believe the foundation should be busy ramping up support in this arena of distraction. IMHO, we are in the calibration phase of the use of these models. We don't feed trolls and we shouldn't tutor LLMs. Since assumption of good faith is not suicide pact, we shouldn't rely overmuch for guidance on edge cases. The issues as I see them are attribution (how do I know where your idea has been?), obedience to social norms (I not-here blocked someone recently for brazenly using ChatGPT to lie about using LLMs; the user proceeded to use GPT to post unblock requests), and a vast canyon between the limited human and financial resources of the foundation and the unlimited resources of bad actors with vast sums of money who would like to see Misplaced Pages less able. I have hopes we can get some higher visibility anti-LLM support (like a flag in my mouseover which always reports a percentage, so I know to check). This fire is burning now. It would be unwise to ignore this much longer. ] (]) 16:28, 29 December 2024 (UTC)
*'''Support''' with the clarification that use of AI assistance is not prohibited, as long as its contribution is <<50%. For example, using Grammarly for spell check and grammar/syntax is OK, but using AI to do your homework is not. ] (]) 02:45, 30 December 2024 (UTC)
*:How do you propose to determine whether an AI's contribution is or is not "<<50%"? ] (]) 12:22, 2 January 2025 (UTC)
*'''Support''' a ban on comments that were primarily generated by AI, with such comments to be deleted or struck-through as appropriate, because it's inherently misleading to pass off a chatbot's words as your own. Using ML-based spell-checkers is fine. I've seen some users call ChatGPT an "accessibility tool", but if you're not capable of communicating on English Misplaced Pages without a LLM doing it for you, then I don't think English Misplaced Pages is a good community for you to participate in. <!-- Template:Unsigned --><small class="autosigned">— Preceding ] comment added by ] (] • ]) 21:45, 31 December 2024 (UTC)</small>
*:Just read ], where an editor was indeffed per ] after exclusively using LLMs to edit, even when responding within that very thread. The situation was a clear case of ], which I surely would've cited in my original comment had the page name come to mind. <span class="nowrap">—] (] | ])</span> 04:34, 3 January 2025 (UTC)
*::That they were banned for CIR shows we don't need anything new to deal with disruption specifically caused by people using LLMs. ] (]) 05:29, 3 January 2025 (UTC)
*'''Support''' A popular notion in many, many other discussions is "our most valuable resource is editor time". This applies here more than in most instances - editors cannot be expected to wear themselves out in engaging at length with the results of someone's one-line prompt to an LLM. Where LLM use in articles is destructive of content and source reliability, in discussions it is destructive of editor good faith. If you can't be bothered to put your arguments into intelligible form, don't participate. If your language capacity is lacking to the extent that you have to have a program ''generate'' (as opposed to polish) your stuff, you probably don't have any business participating either. Human detection ability seems quite sufficient for these cases (and once it ceases to, well, we'll deal with that when it becomes an issue). --<span style="font-family:Courier">]</span> <small>(] · ])</small> 12:00, 2 January 2025 (UTC)
*:{{tpq|Human detection ability seems quite sufficient for these case}} these discussions have already proven that human detection is not reliable, with human-generated comments labelled as AI and AI-generated comments labelled as human. Why should we prohibit LLM-generated content that is accurate, relevant and intelligible? We can already ignore/remove content that is none of those things regardless of whether it is LLM-generated or not. ] (]) 12:21, 2 January 2025 (UTC)
:::If you want a pithy in-a-nutshell: personal effort is buy-in in a discussion among equals. If your personal effort in a discussion is an LLM prompt, no editor should be expected to engage with you. --<span style="font-family:Courier">]</span> <small>(] · ])</small> 12:42, 2 January 2025 (UTC)
::::What matters is whether people are engaging with each other constructively and in good faith. Whether one or both parties is using an LLM is completely irrelevant to both aspects. ] (]) 13:29, 2 January 2025 (UTC)
:::::What matters is whether editors wish to engage with an LLM on Misplaced Pages. https://news.mit.edu/2024/large-language-models-dont-behave-like-people-0723 I don't mind interacting with an LLM for my own use, just not on here. ] (]) 13:42, 2 January 2025 (UTC)
::::::Nobody is forcing you to engage with anybody or anything you don't want to engage with, but you do not get to state who other people are allowed to choose to engage with. As long as someone is engaging constructively and in good faith I don't care whether they are human or machine, because (a) I have no reliable way of knowing, and (b) it is literally irrelevant to me. ] (]) 14:14, 2 January 2025 (UTC)
:::::::{{tq|you do not get to state who other people are allowed to choose to engage with}} Strawman, since I didn't do that. Only you are doing that. ] (]) 14:26, 2 January 2025 (UTC)
::::::::Quite the contrary - you are saying that nobody should be allowed to engage with someone using an LLM because you do not want to engage with someone using an LLM. My position is that everybody should be allowed to choose who they want and do not want to engage with for themselves. ] (]) 14:42, 2 January 2025 (UTC)
*'''Support in principle''' - Using entirely AI-generated text in discussion is not a valuable contribution, since ultimately it is not capable of thought, but there should be leniency for those who are simply using AI to improve something they already wrote. ] (]) 14:55, 2 January 2025 (UTC)
*'''Support in principle''' We don't want LLMs opinions. IF and WHEN we do we'll ask for an extension with some AI making an openig analysis of nominations. But we can not, and want not, to excludes cases where some user forms their opinion chating with some AI, as it was brillianttely shoen above, nor we want to exclude anyone lee proficient with the language just "because it looks like a bot". - ] (]) 18:13, 2 January 2025 (UTC)
*'''Support the principle''' per Nabla. ] (]) 21:23, 2 January 2025 (UTC)
*'''Support in principle, ''strongly'' concerned in potential practice''' - I like the idea of removing what is verifiably generated by a LLM. On the other hand, I've read that autistic writers may be more likely to have their (completely non-AI) writing flagged as potential AI use by automated detectors. I think it could be a problem if a rule that's good in principle could start disproportionately affecting some editors (who are not doing the thing) more than others (who are not doing the thing) in practice, whether that come from human (i.e. other editor) bias or automated tools. - ] (]) 18:36, 3 January 2025 (UTC)
*'''Strongly support''' per ChatGPT (EEng) and SMcC; I'm not at all concerned about edit accessibility to non-native speakers; ], after all, is required to contribute to this project. I also oppose any breaking of the line against AI-generated plausible-sounding and -looking slop. We can't have a Misplaced Pages of LLMs talking to LLMs on how to make LLM content for LLM articles. ]<span style="color: #3558b7;"><sup>]</sup>]</span> 21:53, 4 January 2025 (UTC)
*'''Support''' per SMcCandlish. If someone needs to use a LLM to be able to contribute and is unable to convert the output into something that is not obviously AI-generated, then ] likely applies. It'll be impossible to stop minimal usage cases, but having such a rule in place would at least encourage editors to review their output and stop the unhelpful posting off entire ChatGPT essays to discussion spaces. -- ] - <sup>]</sup>/<sub>]</sub> 01:41, 6 January 2025 (UTC)
*'''Strong... opinion''' -- I think the nuance required here in part is the difference between someone using '''any''' automated tool for assistance, versus true bot-like behavior. I believe that unauthorized bot behavior is already prohibited, which should help address the concerns that we mere humans cannot keep up with LLM bots. I agree, we cannot, but I don't see much of that. I am also not inclined to the "if you cannot write, you cannot contribute"... I can imagine 15 years ago some of us might have made the same statement about spelling and grammar; if you cannot spell properly without auto-correct you have no right to edit an encycolopedia. The are significant number of very intentilligent people who are afflicted with things like dyslexia, aspurgers, etc. who have been contributing using various technology tools for assistance. How may of us have Grammarly or similar running on their web browser? And beyond that tools and what they're called will continue to evolve. I am very much against just banning LLM use; largely because it can turn into an unnecessary witch hunt. There are people who will use the tools constructively, and those who will not. I can see some places where it should ''probably'' be banned (such as using a LLM to determine consensus on a discussion that needs closing (AfD, RM, etc)). But even in those areas, I think many of our existing policies and guidelines already address most of the actual concerns we're seeing when it comes to that activity. Cheifly that as long as people are being held accountable for how they use the tools, then who cares what the tool is called in 2000, 2020 or 2040? So I think the course forward is best served by (1) Consider refinement to ] so that we're encapsulating LLM type bot behavior, as well as some sort of threshold on "non-human" capable editing limits (perhaps as part of ]; (2) make a policy or guidelines very clear, bright line, that a user will be treated the same regardless of what tools they use, LLM or otherwise, and that disruptive editing will be handled accordingly. (2a) perhaps a single-warning template reflective of such, to welcome people who appear to be using LLM, and that they are responsible for their adherence to policy and that LLMs tend to get policy wrong. ] ] 02:48, 7 January 2025 (UTC)
*:I like these proposal ideas, and I believe you've hit the nail on the head on the issue. ] (]) 13:14, 7 January 2025 (UTC)
*:+1 ] 15:16, 7 January 2025 (UTC)
*:The proposal is focused on comments that are '''obviously generated''' by LLM, which would not include non-generative AI processes like Grammarly or translation. The whole issue is arguments that were clearly created by a chatbot etc. doing ''its own'' analysis of a discussion and an editor just pasting that output rather than forming the argument themselves, which results in large amounts of text that other editors/closers then have to read and respond to. ] (]) 22:26, 7 January 2025 (UTC)
*::Right, where one doesn't feel like one is talking with ]. ] (]) 22:52, 7 January 2025 (UTC)
*::To be honest, that's my concern. What if something seems obviously generated by LLM but is entirely human-written? What if certain groups of editors are more likely to produce seemingly LLM text that isn't generated by any LLM at all? Is there a way to control for that? How do we consistently enforce this kind of thing without too many false positives ''or'' false negatives?
*::Replying to the top-level opinion at this point: Most autistic people who would have in the past received an Asperger's diagnosis, barring some other reason, would IMO not be more likely to "need" more assistive technology (LLM or otherwise) to contribute to Misplaced Pages articles and discussions than any other user. However, there have been reports that autistic people may be more likely to produce text that is ''falsely'' positive in AI detection tools. See (I had a second example, I thought, except that I've apparently read my last free article on that site (I bet I read said last article when looking up the ''same'' article when I wrote my !vote a few days back, {{facepalm}}). Not gonna link what I can't (quickly) verify!)) <small>(As an aside, I think ] can come across as a bit... charged? Just something to note.)</small>
*::The mention of Data in particular only heightens my concern because--while no one has accused me yet of using LLM when I write--I ''have'' (on other sites, not here) been accused of being a bot before because of the style of writing I adopt at times. What if editor bias disproportionately plays into ''who'' is suspected of LLM use and who isn't? What if imperfections in automated AI detection only serve to cement the bias? - ] (]) 01:25, 8 January 2025 (UTC)
*:::These questions around controlling for false positives and false negatives are not new, we face them all the time already, for example distinguishing vandalism from good faith contributions. We work through them, but they don't mean we don't have a policy on vandalism. ] (]) 01:41, 8 January 2025 (UTC)
*::::Indeed, that's why my original !vote is (in short) "support but concerned". I definitely think I'd support a policy; I'm just raising questions/concerns I think are worth considering in the process of creating such a policy. I think some part of me is just remembering times I've seen bias negatively affect the project in the past and that part of me is coming out here trying to prevent another situation like that by laying the concerns out. I dunno. - ] (]) 03:59, 8 January 2025 (UTC)
*::::It's much easier to distinguish good-faith contributors: see if they change. ] (]) 04:06, 8 January 2025 (UTC)
*::I think Joelle what you're overlooking in that statement is that ''obviously generated'' is something that is going to be short lived, meaning that it will not be very long before the LLM generated content will be far harder to distinguish. Just like how just a year ago any generative image AI would often get the number and/or placement of fingers wrong on a person's hand, in less than a years time that appears to generally be solved. Today the tell tail signs is even if you ask for someone who is left handed, you'll almost always get an image of a right handed person... But that too will go away shortly. I believe it is (scarily) not too far off, when LLMs can determine the prompt is for Misplaced Pages (by way of seeing the wikimarkup or references to normal wiki policies), and among other things, write in the style of experienced editors, perhaps modeled off of some of us in this very discussion. That will be much more difficult to tell, especially when it learns how to ''not be soo overly polite and apologetic''. Beyond that, I believe there are a lot of people successfully and positively using LLMs already on WP. For those reasons, I proffer that we focus on refining the definitions and parameters for general disruptive editing (such as EW, RRR, etc), what a bot edit/activity is, and perhaps a standardized "friendly welcome" and "friendly notice" for those suspected of using LLMs, and reinforce that the tool matters less than the behavior. I think the analogy I'm going for is that of how we handle socks -- it is not against policy to have multiple accounts, however, when it is disruptive, it is blatantly prohibited. But the signs and symptoms of socks is really what we care about. ] ] 05:02, 8 January 2025 (UTC)
*:::Something can be prohibited even if it is or will be difficult to identify it. Just because we can anticipate AI-generated slop becoming harder to detect doesn't mean it's not still disruptive or that we shouldn't be able to strike it when it is obvious. ] (]) 23:41, 9 January 2025 (UTC)
*'''Strong support''' for striking AI-generated comments. Detection of course will be up to admin discretion, but so is things like incivility and personal attacks; while short snippets of AI generated text are hard to detect, lengthy paragraphs are quite easy to eyeball, and from my experience that's the area where it's most likely to come up and most immediately disruptive. <small> ] (]) (it/she) </small> 22:25, 9 January 2025 (UTC)
*'''Support''' {{TQ|for striking AI-generated comments. Detection of course will be up to admin discretion}} as are other behavioural preoblems. Having read most of the discussion, and having been astonished by the 'individuality' of some machine-generated content, nonetheless, while detection may be less-than-foolproof, I still think we should make the point that such content isn't acceptable. It should be within our capacity to make the distinction between 'machine-generated' content and the use of software to correct grammar or to translate, neither of which should be directly outlawed.] (]) 07:18, 10 January 2025 (UTC)
*:But ''why'' should such content be deemed unacceptbale when there are no problems with it? When there are problems with it, it can and should be dealt with in the same way that those problems are dealt with when written by humans. ] (]) 18:25, 10 January 2025 (UTC)
=== Request for closure ===
I'm not sure this is the right place for the discussion, please forgiev me and show me the way to the correct place in this case.
IMHO, since we're over 30 days and the argument consensus seems lopsided, the community would do well to close this rapidly (as opposed to waiting for additional comments). ] (]) 21:04, 2 January 2025 (UTC)
:Sure it looks lopsided if you only read what has been bolded. When you look beyond at what those bolding support are actually supporting it's not at all clear there is a consensus. Then when you actually look at the arguments made it seems that there is not actually a consensus for anything other more than "some users vocally dislike AI". ] (]) 21:59, 2 January 2025 (UTC)
in '']'', we can read
::If that's so, I'm sure the closer will figure it out. ] (]) 22:14, 2 January 2025 (UTC)
: Race: A character's species, ethnicity, type, or other description of their physical and cultural heredity. Role-playing games often include fantasy races, mutants, robots and other non-human types.
:::I was merely pointing out that BusterD's stated reason for calling for closure now is incorrect. That doesn't mean closing now would necessarily be wrong, just that overwhelming consensus is not a reason for it. ] (]) 22:25, 2 January 2025 (UTC)
This imho obviously extends usual definition of a race, e.g. in '']''
::::As a sysop, reacting to LLM-related abuse is virtually all I've done in the last week or so. We have a pressing need for some help from the community, and while I'm open to discussion on this, it's unreasonable to expect humans to keep up with bot-like behavior. I've made my argument above, and I'll not disagree further here. ] (]) 00:08, 3 January 2025 (UTC)
:* A group of sentient beings, particularly people, distinguished by common heritage or characteristics
::Many on the “support” side are also supporting with conditions instead of an unconditional support. For instance, many have suggested that LLM that supported grammars are okay.
:* A population geographically separated from others of its species that develops significantly different characteristics; an informal term for a subspecies.
::The closer must also take it into account. ] ] 11:02, 3 January 2025 (UTC)
(although in the first definition, "sentient beings" could be wide enough to enclose ]s). Am I right or am I flawed by the fact that I'm not a native english speaker?
* There are multiple breaks and 391 comments now. At this scale, it becomes difficult for a human to digest and summarise it all. AI technology seems well suited to this and so asked Gemini again "Please summarise the consensus of the following RFC:" giving it all the discussion above. Its response was much as before:
If I'm right -- and even if I'm wrong, the problem could be for another topic --, can I then cite a definition of the dictionary and mention this discrepancy, or would it be considered as an original analysis of primary sources and thus an ]?
{{tqb|
]|] 09:53, 11 May 2015 (UTC)
The RFC on LLM/chatbot comments in discussions is contentious, with a significant number of editors on both sides of the issue.
'''Support'''
:Anyone can edit ] so it shouldn't be used as a source per ]. Furthermore, the lead of ] is clear that the shown meanings are in the context of role-playing games. Words often have different meanings or nuances in different contexts so citing a "discrepancy" with a reliable dictionary would also be bad, unless that dictionary specifically talks about the meaning of "race" in role-playing games. Such games are full of supernatural and fictional beings so it's hardly surprising if the terminology doesn't adhere strictly to the common usage for real beings. And we certainly don't want users going through ] and point out whenever a field gives a new or modified meaning to an existing word. ] (]) 20:33, 11 May 2015 (UTC)
:: Thanks for your answer. I used the Wiktionary because I don't know reliable online English dictionaries and don't have a paper English dictionary with me (I'm not a native English speaker); but the question is about any reliable dictionary, online or paper.
:: I agree with you that the definition of some words ''is'' different in fictional works and in common usage, the question is: is it possible write that it is different, just refering to the definition of a reliable dictionary, or would it be considered as an original research? (The aim is not to point out every word in the glossary; but it can be relevant in some cases.)
:: ]|] 07:54, 12 May 2015 (UTC)
:: OK, maybe I could be a bit more specific. I wrote the article '']''. It was a draft until a few hours, and was accepted sooner than I expected (I won't complain (-: ). The aim of my question was to clarify a point to be sure it would be accepted, but my question remains.
:: I wrote : "The term “race” is even broader than the usual meaning, as it also includes extra-terrestrial beings, vegetal beings — e.g. the Aldryami in '']'' (1978), the Sylvanians in '']'' (2010) — and robots — e.g. Artificials in ''Fantasy Craft'' or the Forgeborn/Dwarf-forged optional race in '']'' (2013)."
:: Notice that I even didn't cite a dictionary (which would be a primary source). Can I write this without a secondary source stating this ?
:: It may look ridiculous as this, because this statement is quite obvious. But obviousness is a valid arguument for ], it is not for Misplaced Pages. And, believe it or not, this statement caused me some problem in the French wiki, on the same topic.
:: So, is it the same on the English WP? Would someone add {{Tl|refneeded}} or is the statement acceptable as this?
:: ]|] 20:29, 12 May 2015 (UTC)
:::]. In cases like this though, citing a definition to a defining source would be appropriate, I believe. So yes, you can cite a dictionary (like Oxford or Merriam-Webster, or a game’s rulebook). —] (]) 22:42, 12 May 2015 (UTC)
:::: OK, I'm a bit paranoid then (-:
:::: I realise that the main problem is not on the content of the article itself, but on the language. The english word "race" was initially translated as ''{{lang|fr|race}}'' in French; in French, it was used for both humans ''and'' for animals (means "breed"). In the early 1980's, when ''D&D'' was first translated in French, this was still accurate, although a bit outdated. But things evolved, essentially pushed by the bad memories of the WWII and the evolution of genetics. A 1991 French dictionary already notes that the notion of race "is to be rejected" for humans (but still give the definition, which is OK because we need to understand outdated texts). Now the consensus is that ''{{lang|fr|race}}'' can only be used for "breed", and is banned for humans (we use ] or type instead); the word ''{{lang|fr|race}}'' was even banned from the laws which punishes ] (16 May 2013, ).
:::: So it is ''obvious'' to me (as the skye is blue) that "race" has become a ] (see table below), but well, this is quite new, and there is no source that really states "race is a faux ami", all I have are dictionaries. And thus it is obvious to me that the title of the French article cannot be "race" and I used the word ''{{lang|fr|peuple}}'' (people) instead. But as the word "race" is still widely used in role-playing game rulebooks in French, I don't have a secondary source citing "people" (but have some primary ones), and "race" is what comes up with Google, so many claim that the notion of "people" does ''not'' exist in RPG and that it is an original research of mine. See the point?
:::: So, that does not concern the English WP, but I wanted to explain why I asked that silly question. Sorry for the disturbance.
:::: ]|] 12:31, 13 May 2015 (UTC)
{| class="wikitable"
|+ Race in modern English and in modern French
|-
! Modern English !! Modern French
|-
| race || {{lang|fr|éthnie}}, {{lang|fr|type}}
|-
| breed || {{lang|fr|race}}
|}
Many editors support the proposal to discount or remove LLM-generated comments in discussions. Their arguments include:
* A similar question has also come up at ], in such rancorous debate at ] that resolution has been stalled for many months. In that case, one editor wants to include in the lead some wording from and a citation to a general dictionary, and a similar one from an internal regulatory document of the FAO. Meanwhile another editor wants to limit the article's examination of definitional issues to a terminology section devoted to that, including more precise and nuanced definitions from topically-specialized sources, and have the lead only present an overview of what the term refers to, without citing either the dictionary or FAO sources, detailing in the terminology section why these two sources may be questionable on the matter. Each editor has made ] and ] claims against the other over this editing dispute (see ], and some earlier threads, for details). It needs some new eyes, preferably ones of editors who do not have any vested interest in domestic animal topics. Obviously I am the second of the two editors in this dispute. Both of us are making an effort to avoid further interpersonal conflict, so I think it would be especially helpful in this case for non-involved editors to weigh in on this matter, and others raised on the same talk page. A cursory scan of the article shows that it's stuck in the same in-between state it has been for months, with the dictionary definition moved to the terminology section, but the FAO definition retained in the first sentence of the lead. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 12:01, 24 May 2015 (UTC)
::Hi {{u|SMcCandlish}}, If it's just the two editors involved in the content dispute, have you considered requesting a third opinion at ]? If you don't get anything there, I'll try to have a look myself, but it might be a day or so. Hope this helps. - ] <sup>]</sup> 12:20, 24 May 2015 (UTC)
:::{{Ping|Ryk72}} I've attempted formal ] with the editor before, but this was rebuffed. I'm skeptical that the opinion of a single additional voice via WP:3O would help much. Rather, multiple editors applying critical thinking about what constitutes ]/] is needed. Each editor claims that the other is engaging in novel synthesis, and it's unlikely that they can both be right, when the edits they make are back-and-forth, directly opposite edits to the same small bit of the lead. (Of course it's possible for two editors to engage in SYNTH in different ways on the same page.) Either a vague dictionary definition and an out-of-context NGO one from a house organ can be used in place of more particular, secondary, journal sources, or they can't. PS: A third editor might already be involved (one that the other enlists against me in a ] on virtually every page in which we come into conflict, for around 18 months now), so WP:3O might not even be available. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 14:45, 25 May 2015 (UTC)
* LLMs do not have original thoughts or arguments and therefore do not contribute meaningfully to discussions.
== RfC: Guidance on commas after Jr. and Sr. ==
* LLM-generated comments can be disruptive, wasting editors' time and derailing discussions.
* LLMs can be used by bad-faith actors to manipulate consensus or spread misinformation.
*Editors should be encouraged to participate in discussions using their own words and thoughts.
'''Oppose'''
{{rfc|style|policy|rfcid=4C7322F}}
Other editors oppose the proposal, arguing that:
The previous ] has been closed with the decision to allow the comma before ''Jr.'' or ''Sr.'' to be optional provided that each article is interally consistent. Accordingly, {{multi-section link|Misplaced Pages:Manual of Style/Biographies|Names|First mention|Child named for parent or predecessor}} has been amended to read: <blockquote>Editors may use or omit a comma before ''Jr.'' or ''Sr.'' so long as each article is internally consistent. Do not place a comma before a Roman numeral designation. Examples: {{xt|Sammy Davis Jr.}}; {{xt|Martin Luther King, Sr.}}; {{xt|Otis D. Wright II}}, not {{!xt|Otis D. Wright, II}}.</blockquote>
* LLMs can be useful tools for editors who have difficulty expressing themselves in English, such as non-native speakers or those with disabilities.
Hopefully this will avoid ongoing arguments on which is the "right" form for individual subjects (based on their preferences or sources' preferences) and won't lead to editwarring (see ] for the guideline avoiding similar editwarring over date formats).
* LLM-generated comments should be evaluated on their merits, not their origin.
* Detection of LLM-generated comments is unreliable and could lead to false positives.
* A ban on LLM-generated comments could discourage participation from editors who rely on these tools.
'''Additional points'''
As flagged in the previous discussion, this raises the issue of commas appearing '''after''' ''Jr.'' and ''Sr.''. All style guides state that, if a comma is used before, a matching comma must appear afterwards if the sentence continues—acting as an ], much like commas after dates in MDY format (]) and after city–state combinations (]).
* There is disagreement about whether machine translation should be considered LLM-generated content.
{{collapse|bg=#EFEFEF|2=Style guides on commas before and after ''Jr.'' and ''Sr.''|1=
* Some editors believe that LLMs could be used constructively in discussions, for example, to summarize arguments or provide alternative perspectives.
<ul><li>: <blockquote style="font-size:80%"><p><strong>Q. John Smith Jr. or John Smith, Jr.? John Smith III or John Smith, III?</strong></p><p><strong>A.</strong> Traditionally, it would be John Smith, Jr., and John Smith III. But beginning with the fourteenth edition of The Chicago Manual of Style (1993), the recommendation is to use no commas in either case (see paragraph 6.47 of the sixteenth edition):</p> <blockquote>John Smith Jr.</blockquote> <p>But please note that within text, {{highlight|if you decide to use the more traditional comma before Jr. or Sr., the function of the comma is to set off these abbreviations, so an additional comma is needed after the abbreviation if the sentence continues}} (as in my first sentence above).</p></blockquote></li></ul>
* Others are concerned about the potential for LLMs to be used maliciously, for example, to flood discussions with irrelevant comments or to impersonate other editors.
*: <blockquote style="font-size:80%"><p>Jr. and Sr. are preceded {{highlight|and followed by}} comma in full name:</p><blockquote><p>John M. Fahey, Jr. (left), went to...</p><p>''but'' John Jr. hurried...</p></blockquote></blockquote>
*: <blockquote style="font-size:80%"><p>'''Rule 8.''' Traditionally, if a person's name is followed by ''Sr.'' or ''Jr.'', a comma follows the last name: ''Martin Luther King, Jr.'' This comma is no longer considered mandatory. However, {{highlight|if a comma does precede ''Sr.'' or ''Jr.'', another comma must follow the entire name when it appears midsentence}}.</p><p>'''Correct:''' ''Al Mooney Sr. is here.''</p><p>'''Correct:''' ''Al Mooney, Sr., is here.''</p><p>'''Incorrect:''' ''Al Mooney, Sr. is here.''</p></blockquote>
*: <blockquote style="font-size:80%">Use a comma or commas to set off the abbreviations ''Jr.'', ''Sr.'', and ''Esq.'' Example: Carl Harris, {{highlight|Jr.,}} is here now.</blockquote>
*: <blockquote style="font-size:80%"><p>A comma would be used {{highlight|both before and after}} then designations of "Jr." or "Sr.," as long as the sentence continues. If the designation is at the end of the sentence, then a comma is used only before it.</p><p>For example: John James, Sr., was well regarded in the community. However, the community had no use for John James, Jr.</p></blockquote>
*: <blockquote style="font-size:80%"><p>Sometimes the simplest point can cause us a problem when writing. For example, should "Jr." or "Sr." in a name be preceded by a comma?</p><p>Some stylebooks say no, others say yes, but the "nos" outnumber the "yeses."</p><p>However, those that specify no comma say you should follow the person's preference if you know it.</p><p>A point to remember is, {{highlight|if you use a comma before either of these designations, you must use one after it}}.</p></blockquote>
}}
'''Overall'''
Unfortunately, many editors are not aware of this rule in English and sometimes argue against it. Therefore, I recommend this section be further amended as follows:
There is no clear consensus on whether to ban or allow LLM-generated comments in discussions. The discussion highlights the challenges of balancing the potential benefits and risks of using LLMs in a collaborative environment like Misplaced Pages.
<blockquote><p>Editors may use or omit a comma before ''Jr.'' or ''Sr.'' so long as each article is internally consistent ({{xt|Sammy Davis Jr.}} or {{xt|Martin Luther King, Sr.}}). If using a comma before, also include a comma after ''Jr.'' or ''Sr.'' if the sentence continues ({{xt|John D. Rockefeller, Jr., was an American financer and philanthropist...}}).</p><p>Do not place a comma before a Roman numeral designation ({{xt|Otis D. Wright II}}, not {{!xt|Otis D. Wright, II}}).</p></blockquote>
===Guidance on commas after Jr. and Sr.: Comments===
{{hatnote|Please add your comments below.}}
* Yes, if a comma goes before, it goes after. Standard logical clause construction. NB. Much prefer the British style where Jr and Sr do not need the period. --] (]) 06:21, 14 May 2015 (UTC)
*'''Support''' the use of proposed addition. Consistency is a poor justification for going against WP:UCRN. ]] 06:34, 14 May 2015 (UTC)
*:] - what does requiring the second comma have to do with WP:UCRN? ] (]) 16:54, 14 May 2015 (UTC)
*::] My personal preference is that we should generally use a form of name that corresponds to ] and ]. Unless there are other pressing concerns, these are the considerations we, I think, should predominantly follow the way things are normally done for that person. WP:UCRN presents that: "{{tq|Misplaced Pages prefers the name that is most commonly used (as determined by its prevalence in ]) as such names will be the most recognizable and the most natural.}}" ]] 18:56, 14 May 2015 (UTC)
*:::] - agreed. But again, what does that have to do with whether we allow "John Smith, Jr., was..." and/or "John Smith, Jr. was..."? This RfC is only about whether we require that second comma after Jr. or not, not how we present the name (except for cases below like the Rockefeller library). I'm still confused about the relevance of wp:ucrn. ] (]) 19:04, 14 May 2015 (UTC)
:::::] My apologies for not understanding what you were saying. My support is mainly for the inclusion of examples such as "{{tq|Sammy Davis Jr. or Martin Luther King, Sr.}}". I still think the commas content makes reasonable sense but you are right to point that this has nothing to do with issues relating to prevalence of use. ]] 19:40, 14 May 2015 (UTC)
*<s>'''Oppose''' - What are you trying to do? The whole proposal that you have supported had no consensus. I checked the closed discussion, and you're still persistent on having all commas before successor or predecessor omitted. Also, you haven't contacted or pinged ], who accurately closed the previous discussion. Well, I'm still in favor of omitting a comma, but not when sources are divided or when consensus opposes it. This is instructional creep. --] (]) 07:04, 14 May 2015 (UTC)</s>
::{{reply|George Ho}} What are you on about? This RfC isn't about the comma before ''Jr.'' or ''Sr.''—it's about the separate issue of providing guidance for the comma '''after''' ''Jr.'' or ''Sr.'' '''All style guides say''' if there's a comma before there must be a comma after. That's all this RfC seeks to add to the guideline for clarification. <small>—''']''' ]</small> 15:21, 14 May 2015 (UTC)
::Note that this proposal was already flagged in the previous RfC: {{talkquote|'''Note''': This RfC only concerns the comma ''before'' Jr. and Sr. If the result allows for that comma, then a follow-up discussion may be necessary regarding guidance on a comma ''after'' Jr. or Sr.}} The result of that RfC allows for the comma ''before'', so this RfC is about the comma ''after'', exactly as previously stated. <small>—''']''' ]</small> 15:47, 14 May 2015 (UTC)
:::My bad. If you're concerned about a comma ''after'' Jr or Sr, perhaps I was mistaken. I struck original vote, so I will make a fresher one. ] (]) 18:37, 14 May 2015 (UTC)
:::'''Weak support''' - Look like an instructional creep, but a comma after Jr/Sr makes more sense ''when'' a comma before Jr/Sr is added. No comma before, no comma after, however. And I wouldn't care about regional differences as long as commas are properly used.
*'''Oppose''', it's an archaic style that's still listed in quite a few places and used in even less. The Jr. or Sr. without a comma has been the standard way of using the style as long as Jr. and Sr. have existed, or at least in my experience, which is almost as long. Official names, such as the Martin Luther King, Jr. Memorial, don't use it, probably because it makes things look worse instead of better and is so uncommon that the mind latches onto it and won't let go, like some kind of little dog sitting there growling at the preceding period. ] 10:54, 14 May 2015 (UTC)
::{{reply|Randy Kryn}} That would be a good argument to do away with the commas altogether, but that argument has been and gone. English construction and style guides universally agree that a comma ''before'' requires a comma ''after''. The fact that some sources flout this rule is no reason for this encyclopedia to follow in their folly. <small>—''']''' ]</small> 15:56, 14 May 2015 (UTC)
*'''Oppose''' - The recently closed RFC closure on the issue of commas ''before'' Jr. or Sr. (essentially saying that we should have no rule other than "be internally consistent" within an article) reflected a practical and common sense approach that accounts for our lack of consensus on the issue. I think the same approach should be applied to the question of commas ''after''... The important thing is for the style to be internally consistent within any given article. More than that is unnecessary instruction creep. ] (]) 13:33, 14 May 2015 (UTC)
::{{reply|Blueboar}} Style guides generally agree that commas may be included or omitted (the trend is to omit them) but '''all agree''' that a comma before requires a comma after. If we're consistent within each article about whether or not to have the comma before, "common sense" requires that we also be consistent about whether or not to include the comma after. <small>—''']''' ]</small> 15:24, 14 May 2015 (UTC)
*'''Oppose''' I'm fairly certain this covention is completely unknown in British English - were any of the "all style guides" for BE? People should be more careful about this. Even in AE it doesn't seem to me to be what is usual. Just in case it is adopted it should be made clear that this applies within AE only, for ENGVAR purposes. ] (]) 14:01, 14 May 2015 (UTC)
*'''Support''' – The following comma is required in both British English and American English, and always has been (I'm a Briton). If the form with the comma before is to be allowed, the following comma must also be required. ] — ] 14:24, 14 May 2015 (UTC)
:::This is simply nonsense! ] (]) 15:17, 18 May 2015 (UTC)
::::There is nothing "nonsense" about it. Yes, we don't generally use "junior" and "senior" suffixes in British English. However, the rules of comma usage remain the same. Completing the apposition requires a following comma. Take a look at this guide here, which explains the use of commas quite well. In the American context, one might look at this , which notes the necessary nature of the following comma. ] — ] 15:09, 21 May 2015 (UTC)
*'''Support''' Now I know why the British omit the period, so you do not have to argue of the mid sentence period. I agree that you should have a comma after a mid sentence period, except after Mr. and Dr. and others that are name prefixes, but that has nothing to do with changing the titles of articles. --] (]) 15:52, 14 May 2015 (UTC)
*'''Oppose'''. It may be that all style guides ''that address the issue'' recommend using the second comma, but there are two complications. 1) Not all style guides even discuss this relatively minor point of punctuation. 2) In practice, many reputable sources leave out the second comma, regardless of the preferences of style guides. For example:
::Routledge: Cromwell, Adelaide M. . p.31. 2014.
::Oxford University Press: Lischer, Richard. . p.197. 1995.
::Many more (see for yourself with ).
:We have also already come across the case where WP editors have decided that the second comma might not be a part of the name of something. For example:
::]
:Leaving out the second comma in general does nothing to change the ability of our readers to comprehend the meaning of the sentence. Despite style guides' efforts, the second comma is quite often left out, even in reputable, professionally edited sources. Real-world usage shows that '''''both using and leaving out the second comma is acceptable''''' in English. WP should therefore allow both styles, as long as an article is internally consistent. Any particularly strong argument for including or omitting the second comma should be taken up on a case-by-case basis. ] (]) 16:41, 14 May 2015 (UTC)
:::{{reply|Dohn joe}} The fact that some sources don't follow proper punctuation is no reason for this encyclopedia to follow in their folly. Cases like the Memorial Parkway (where even the "official" sources disagreed on the punctuation) show exactly why we ''should'' have proper guidance on this to avoid recurring debates by editors who are singularly focussed on particular articles without a considered understanding of this specific punctuation issue. <small>—''']''' ]</small> 03:55, 15 May 2015 (UTC)
::::] - the point is that style guides do not have a monopoly on what is "proper punctuation." Usage in reputable, professionally edited sources is good evidence of what is proper usage. When a significant portion of sources use a style (as with not using a second comma after Jr.), then WP should be allowed to permit usage of that style. ] (]) 15:36, 15 May 2015 (UTC)
:::::{{reply|Dohn joe}} Prescriptivism vs descriptivism. I would rather defer to style guides on matters of style. If there was some leeway in some style guides then I might accept the argument, but all the style guides I've seen say comma before requires a comma after; none concede that the comma after is optional when the comma before is used. It's poor form for an encyclopedia's style guide to go against all style guides on proper punctuation. <small>—''']''' ]</small> 04:22, 16 May 2015 (UTC)
::::::If this is folly, as you repeat, then the U.S. government is guilty of folly (not for the first time, if truth be told) over and over again. The comma after a Jr. or Sr. would change the name of institutions and memorials, of books and beanstalks. As I said, the use of comma after such a word combination misses the point of clear and clean language, and just adds more data into something which doesn't need to be explained. ] 11:10, 17 May 2015 (UTC)
:::::::The comma is there precisely because it makes for "clear" language by following standard logical rules, as explained by the mentioned style guides. Some sources fail (for example, it has been said that newspapers omit the comma after MDY dates and city–state conjunctions to economise on space in narrow columns) and often disagree (for example, the same geographical feature is "officially" named as "John D. Rockefeller, Junior, Memorial Parkway" in ; "John D. Rockefeller Jr. Memorial Parkway" on and ; and "John D. Rockefeller, Jr. Memorial Parkway" on ). Where others fail, we should strive for accuracy and encyclopedic standards. <small>—''']''' ]</small> 11:40, 17 May 2015 (UTC)
*'''Support''' - As far as I am concerned, ] uses' this standard. '''<font face="Arial">] <small>]</small></font>''' 23:12, 14 May 2015 (UTC)
*'''Support'''—if editors are going to use a comma before Sr./Jr., then some form of punctuation is necessary to close the appositive. By default that is another comma, but it could be a semicolon, dash or terminal punctuation. We do this with constructions like "Milwaukee, Wisconsin", so we should be doing this with these types of names. (Dropping the comma completely in these names would simplify things greatly, of course.) <span style="background:#006B54; padding:2px;">'''] ]'''</span> 05:32, 15 May 2015 (UTC)
*:The comma in the Jr. or Sr. is part of a person's proper name. "Milwaukee" is a proper name on its own, as is "Wisconsin", so in that form the comma is needed, but not if the comma is part of the proper name. ] 1:38, 22 May 2015 (UTC)
:::Except his name is often given simply as "Martin Luther King" and the "Jr." is only added as a distinguishing feature when needed; and in any case, this involves the rules of English punctuation which are supported by the cited style guides—you have provided '''no''' style guide references to contradict this. <small>—''']''' ]</small> 01:43, 22 May 2015 (UTC)
::::King himself used the comma as part of his proper name. The U.S. government, in its naming of the Martin Luther King, Jr. Memorial and Martin Luther King, Jr. Day have set the style in his case. ] 1:48, 22 May 2015 (UTC)
*'''Support''' - on the basis of completing the apposition. ] (]) 00:52, 16 May 2015 (UTC)
*'''Support''' as proposed. If anyone doubts this lack of clarity results in editwarring, {{diff|Martin Luther King, Sr.|663482132|663480780|guess}} {{diff|Martin Luther King, Jr.|663482292|663481843|again}}. <small>—''']''' ]</small> 01:38, 22 May 2015 (UTC)
*:You began that editwar (I'd rather call it an edit disagreement, or edit snowball fight) by choosing the very prominent Dr. King page to place the awkward after-proper-name commas without a consensus being reached. The consistency in Misplaced Pages of not using the comma after King's name is present in using the names that the U.S. government has given to the ] and ]. ] 1:54, 22 May 2015 (UTC)
:::You may think it "awkward", but it's English. The alternative was to do away with commas before "Jr."/"Sr.", but the consensus went against that. Americans failing English punctuation is no excuse for Misplaced Pages to pander to them. <small>—''']''' ]</small> 01:59, 22 May 2015 (UTC)
::::Eh, it's generally everyone {{em|but}} American's who are dropping the commas, though. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 09:53, 24 May 2015 (UTC)
:::::{{reply|SMcCandlish}} I was responding to ]'s comment about US government sources. I don't care who's dropping the comma after; mismatched commas are '''wrong''' and an encyclopedia shouldn't settle for sub-standard punctuation. <small>—''']''' ]</small> 17:47, 24 May 2015 (UTC)
* '''Support''' a comma after when there is one before. <span style="color:#666">– ]]</span> 15:15, 24 May 2015 (UTC)
* '''Support''': Yes, this is basic English punctuation. I'm skeptical that a Village pump (policy) RfC was needed for this. Minor clarification edits to MOS pages are discussed at their talk pages, or at the main ] talk page if the MOS subpage's talk page is poorly attended. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 14:56, 25 May 2015 (UTC)
::I posted it here because the antecedent ] was posted here, and that was because it was considered that MOS was not sufficiently patrolled for a previous RfC. Notification was also posted at {{mslink|Misplaced Pages talk:Manual of Style/Biographies|RfC: Comma or no comma before Jr. and Sr.|New RfCs}}. <small>—''']''' ]</small> 02:16, 26 May 2015 (UTC)
::By the way, I would have hoped this wouldn't be controversial, but alas my fear that this would court controversy was realised. <small>—''']''' ]</small> 02:23, 26 May 2015 (UTC)
:::It courts controversy only because MOS-bashing has become a wikisport (and a team one at that), while not everyone who writes Misplaced Pages has much training in writing, plus the human tendency to believe that a rule someone doesn't want to be bothered with is a ] in the world. Competent writers, and reliable sources on English-language usage, all know that commas are balanced in cases like this. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 00:36, 28 May 2015 (UTC)
::::It's controversial simply because competent writers, and editors, such as the ones cited above from Routledge and Oxford, do in fact sometimes omit a following comma. An acceptable option in reliable sources should be an option here on WP. ] (]) 17:00, 28 May 2015 (UTC)
:::::Evidence of {{em|usage}} that has managed to make it into print doesn't constitute reliable sourcing that such a style choice is widely acceptable in a formal register like encyclopedia writing. Routledge and Oxford as publishers have little to do with the output of Cromwell and Lischer, the authors of the books in question. While the writers were surely subject to some level of editorial revision, we have no insider data on why this usage was not corrected to something more standard; we can't suppose it was because officials at the publishers preferred it, or it was just an oversight, or the authors in each case lobbied hard for it because they thought their audience didn't like commas, or what. There's no evidence.</p><p>It certainly isn't the case that Oxford can be cited as some kind of authority of in favor of omitting that comma, or even being neutral on it. Oxford's own style guide under various titles doesn't address this exact case, but they do address the general case. With the comma in such a name, "Jr." or "Sr." is an appositive, a qualifier, added to the name. Oxford is clear on these in general: "Use a pair of commas when the apposition falls in the middle of a sentence; they function like a pair of parentheses or dashes, though they imply a closer relationship with the surrounding text". (''New Harts Rules: The Handbook of Style for Writers and Editors'', p. 68, Oxford U. Pr., 2005). That even neatly explains why we use commas, instead of some other convention like "Martin Luther King (Jr.)".<p>So, we {{em|do}} have four things here: 1) style/usage guides recommending commas before and after "Jr." and "Sr."; 2) guides not addressing this specific question but giving more general advice that inexorably leads to the same conclusion; 3) guides recommending or at least permitting the dropping of both commas (mostly ] guides, with focus on expediency); and 4) guides offering no applicable advice at all. The one relevant thing we do {{em|not}} have is style guides recommending dropping the second comma if the first is used. Even if a style manual can be found somewhere recommending no second comma, it would be dwarfed by the stack of books contradicting it. So there's really no debate to continue with on this point. It remains well sourced (in this thread and many before it) that reliable sources on English-language usage consistently say that commas are balanced in cases like this. The dropping of the second comma is fairly common in vernacular and journalistic writing (including books written by journalists). I catch myself doing it out of expediency pretty often. But it's not formal, precise writing, and it can lead to sentences that are difficult to parse correctly. Finally, WP is not bound to do what a numeric majority of external style guides do, anyway. MOS recommends what our consensus (collectively built and refined) determines is best for the encyclopedia's purpose and readership, not for the approval of pundits at any external publisher of style guides. An enormous number of ]-related and ]-related arguments are predicated on approaching MOS/AT as if we're writing a style guide / naming convention for the world, instead of an in-house one for a single publication. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 18:24, 28 May 2015 (UTC)</p>
== English policy: So blindly obvious, but... ==
Over the weekend I had an incident on Misplaced Pages that convinced me the following needs to be proposed as policy:
{{User:sroc/box||
=== All entries in article space need to be in English ===
{{nutshell|English is the language of this particular Wiki. This helps us to assure that anything posted in article space meets the five pillars, as well as any other relevant policy.}}
=== Preamble ===
That was a good answer but I wanted to get a rough headcount and so asked a supplementary question, "What was the count of the number of support and opposing votes in the discussion?" The answer was:
In order to assure all involved that any article satisfies the ] of Misplaced Pages, as well as ] the article needs to be able to be read. Since English is the language of this particular wiki, most users on this Misplaced Pages read English and communicate in English. Further, most of the users on this Misplaced Pages do ''not'' read any other language. Therefore it would be impossible to assure that any article meets the aforementioned Five Pillars and guidelines without being able actually understand what's being written. Therefore any article ''in the article namespace'' needs to be in English.
{{tqb|
Unfortunately, a precise count of support vs oppose votes in that discussion is difficult to determine definitively for a few reasons:
* '''Some votes are unclear''': Several editors express nuanced positions or change their vote during the discussion.
=== Instructions ===
* '''"Strong" votes aren't quantified''': While many editors use "Strong support" or "Strong oppose", these don't carry extra weight in a simple tally.
* '''Focus shifts''': The initial focus on AI-generated comments broadens to include AI-assistance, making some votes less clear-cut.
However, based on a rough manual count:
Since ], articles not in English can be moved to the Draft namespace and a tag requesting translation can be added there. That way, there is a mechanism for allowing a non-English submission to be considered for Misplaced Pages. Once the article is translated in Draft namespace and judged to meet all policies and applicable guidelines, it can ''then'' be moved to the article namespace.
* '''Support''': Around 60-70 votes clearly favor discounting or removing AI-generated comments.
Any article not in English posted in article namespace should be moved into the Draft namespace and a note to the submitting author must be sent informing them what has happened.
* '''Oppose''': Roughly 30-40 votes lean against the proposal, with varying degrees of opposition.
'''Important Note''': This is an approximation. The actual consensus in such discussions is determined by the closer, who weighs the arguments' quality and policy relevance, not just the number of votes.
This is being done to verify that the article in question doesn't violate copyright, which is a pretty serious issue here, doesn't violate any office actions, and more simply put, that it doesn't violate any Misplaced Pages policy or guideline. This cannot be done if it's in a language that cannot be read on this Misplaced Pages (i.e. English). We have other vrrsions of Misplaced Pages for other languages, therefore, it's not an issue of ''exclusion'', but rather one of making sure that the article meets all guidelines and policies.
This seems to be another good answer – better than we get from most human closes. I made a rough manual count to confirm that the numbers given are reasonable ballpark figures. And it seems to have an impressive grasp of nuance – noticing that several editors were qualifying their votes as strong/weak and that some editors changed their vote. ]🐉(]) 22:02, 10 January 2025 (UTC)
=== English policy: Support ===
:These feel (from my memory of when I skimmed over the discussion several days ago before my original !vote/comment) like they might be leaving out some relevant points that came up. (Unfortunately I can't quantify that without taking a look which I don't have time to do right now (other than the fact my own concerns didn't make it into the summary, which... fair, I guess, considering I was the only one who raised that specific issue).) <small>(I'm also very surprised it came up with something coherent as well as on topic, but that just has more to do with the fact Gemini (or at least whatever AI summarizes Google searches) told me extremely recently that I could get to Alaska by car without a passport if I drove through the ocean. Not took a ferry but drove... through the water... in a car.)</small> - ] (]) 07:02, 11 January 2025 (UTC)
::Your !vote was a qualified support with concern about false positives affecting editors such as the autistic. That's then a nuanced, both-ways vote and the Gemini summary seems to capture that reasonably well. ]🐉(]) 09:43, 11 January 2025 (UTC)
=== Alternate proposal ===
*'''Support ''' as proposer, not to mention it's so blindly obvious <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 11:02, 18 May 2015 (UTC)
{{discussion top|result=Redundant proposal, confusingly worded, with no support, and not even any further discussion interest in 10 days. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 05:23, 22 December 2024 (UTC)}}
*'''<s>Support</s>''' <s>all</s> non-English articles should <u>generally</u> be moved to draftspace <s>on sight</s> <u>when they don't qualify for speedy deletion but also can't be fixed up in a short amount of time</u>. With the current process, if someone creates an article about some non-notable nonsense in English then it gets speedied in five seconds, but if the article happens to be in some other language then we give it a two-week grace period to see if it gets translated and/or it may get forgotten entirely -- this doesn't make any sense to me and dealing with these articles is pretty annoying. — ] <sup>(])</sup> 11:36, 18 May 2015 (UTC) amended — ] <sup>(])</sup> 17:23, 18 May 2015 (UTC)
Whereas many editors, including me, have cited problems with accuracy in regards to existing tools such as ZeroGPT, I propose that '''remarks that are blatently generated by a LLM or similar automated system should be discounted/removed/collapsed/hidden'''. ] <sup>] / ]</sup> 10:00, 10 December 2024 (UTC)
**Amending my !vote: this doesn't necessarily have to be a new policy page, it can also be written into some other policy or information page, and described as a standard/approved/okay method of dealing with non-English articles. But also it doesn't have to be ''mandatory'' to move every non-English article into draftspace (if an editor feels that it will be easy enough to turn that article into something worthy of inclusion on Misplaced Pages, i.e. they understand what the topic is and have the time to work on it). — ] <sup>(])</sup> 14:55, 18 May 2015 (UTC)
:::I think this is the essence of ]! If you can translate the article, do it! But if you can't or don't have the time right now, add it to the list at WP:PNT and you or someone else can get to it soon. Is it easy enough to move an article back from Drafts to the mainspace, or does this require an admin to move over a redirect? <small>—''']''' ]</small> 15:58, 18 May 2015 (UTC)
:::: After moving an article to draftspace, the redirect that gets created after the move should be speedied as ] -- articlespace redirects that redirect to the Draft namespace should get deleted. So, assuming some time has passed and the redirect has been deleted, it will be easy to move the draft back to mainspace. — ] <sup>(])</sup> 16:11, 18 May 2015 (UTC)
::::: Yeah, I just saw this. All the more reason to move the article to drafts if you can't fix it right away, and it can be moved back when it's done. Not that the move needs to be ''mandatory'', but they shouldn't linger in the article space unnecessarily. <small>—''']''' ]</small> 16:58, 18 May 2015 (UTC)
**Another amendment: as said I don't necessarily support the creation of a new policy, but, wherever it is written, we should not include this part: "This cannot be done if it's in a language that cannot be read on this Misplaced Pages (English)." -- we can indeed judge articles even if they're in a language we can't understand, it can often be possible to determine (like by using a translator) if an article is total baloney or not. We can do it and we're allowed to, too. (And then tag for speedy (with an explanation for deleting admin if necessary) instead of moving to draftspace.) — ] <sup>(])</sup> 17:14, 18 May 2015 (UTC)
*'''Support'''-ish. I don't see that we need to enshrine in policy the fact that this is the English Misplaced Pages, but I'm a big fan of the idea of automatically moving non-English submissions into Draft-space. ] ]] 11:58, 18 May 2015 (UTC)
::{{reply|Yunshui}} What do you think of ] below? <small>—''']''' ]</small> 14:11, 18 May 2015 (UTC)
*'''Support''' – Anything that makes ] stronger is welcome in my view. --] (]) 13:06, 18 May 2015 (UTC)
*'''Support''' - yes, I think that this should be obvious; however, I think that draftifying non-English articles is better than either keeping them in the mainspace or deleting them outright. ] ] 13:10, 18 May 2015 (UTC)
::{{reply|Od Mishehu}} What do you think of ] below? <small>—''']''' ]</small> 14:11, 18 May 2015 (UTC)
*'''Support''' This will only have positive effects.] (]) 13:11, 18 May 2015 (UTC)
*'''Support''' As per above. A no-brainer IMO. Regards <span style="border:1px solid #FFFFFF">] ]</span> 13:13, 18 May 2015 (UTC)
*'''Support''' I don't know if there's something in the water but there seem to be more and more non-English articles turning up at NPP (or simply I'm noticing them more), and investigating why people are not inclined to put them in the right language Misplaced Pages is probably also worth investigating. ] ] ] 13:52, 18 May 2015 (UTC)
*'''Support''' as per above. But are there any non-English articles in mainspace, or is this preventive? ] (]) 13:54, 18 May 2015 (UTC)
:{{ping|Robert McClenon}} See ]. ] ] 13:58, 18 May 2015 (UTC)
*'''Support''' This is a fairly common sense proposal. It is preferable to the current status quo of tagging them for translation and leaving them in article space. ] ] 13:58, 18 May 2015 (UTC)
::{{reply|Winner 42}} So move them and tag them. We don't need a policy for this. See ] below. <small>—''']''' ]</small> 14:11, 18 May 2015 (UTC)
*'''Support''', I ''have'' seen non-English articles in mainspace before, most of which get mopped up in the NPP process. I have also seen articles that have been vandalized and left with completely non-English text for months though, so I would add the cautionary note of "any editor who is preparing to move a non-English page to the draft namespace must check the edit history to see if there is an English version that can be restored". ] ] 14:26, 18 May 2015 (UTC)
*'''Support'''. Duh. This is the English wiki, if someone wants an article in a different language, it should be directed to that language's wiki. <span style="border:1px solid #900;padding:2px;background:#fffff4">] ]</span> 15:19, 18 May 2015 (UTC)
*'''Support'''. Lingua anglicana est universale.--] (]) 22:55, 18 May 2015 (UTC)
*'''Support''' it really is a no-brainer. Get them into draft space so they can be translated and verified more easily. ] (]) 04:53, 22 May 2015 (UTC)
:'''Oppose''' as completely unnecessary and far too prone to error per the above discussion. Any comment that is good (on topic, relevant, etc) should be considered by the closer regardless of whether it was made with LLM-input of any sort or not. Any comment that is bad (off-topic, irrelevant, etc) should be ignored by the closer regardless of whether it was made with LLM-input of any sort or not. Any comment that is both bad and disruptive (e.g. by being excessively long, completely irrelevant, bludgeoning, etc) should be removed and/or hatted as appropriate, regardless of whether it was made with LLM-input of any sort. The good thing is that ''this is already policy'' so we don't need to call out LLMs specifically, and indeed doing so is likely to be disruptive in cases where human-written comments are misidentified as being LLM-written (which ''will'' happen, regardless of whether tools are used). ] (]) 11:19, 10 December 2024 (UTC)
=== English policy: Oppose ===
:I think this proposal is not really necessary. I support it, but that is because it is functionally identical to the one directly above it, which I also supported. This should probably be hatted. ] ] 18:32, 10 December 2024 (UTC)
*'''Oppose''' creating a new policy to say we can do this. There is nothing in any policy that says we can not ] (not ]) an article that is not ready from the mainspace to the draft space. An article that is not written in English is not ready for the mainspace so there is nothing stopping us from moving it. The creator should be notified where the article was moved to and why, so they can work on it. -- ] ] 12:14, 18 May 2015 (UTC)
:What does '''blatantly generated''' mean? Does you mean only where the remark is signed with "I, Chatbot", or anything that ''appears'' to be LLM-style? I don't think there's much in between. <span style="font-family:cursive">]]</span> 19:21, 10 December 2024 (UTC)
** Well that's an option too: we don't need a policy for this, if an editor is still allowed to move an article into draftspace for the main reason that it's not in English. — ] <sup>(])</sup> 12:31, 18 May 2015 (UTC)
:'''Procedural close''' per BugGhost. I'd hat this myself, but I don't think that'd be appropriate since it's only the two of us who have expressed that this proposal is basically an exact clone. ] (]) 03:00, 11 December 2024 (UTC)
*'''Oppose''' the proposed policy as unnecessary. I have ] set out below which I think is a lot simpler and easier to implement. <small>—''']''' ]</small> 14:05, 18 May 2015 (UTC)
{{discussion bottom}}
*'''Oppose''' This is a good example of an idea with a lot of merit, but some flaws that need addressing. A candidate for the ] to work out the kinks before asking for an up or down vote. Examples of kinks:
**Suppose I run across an article in mainspace in another language, which when translated, is absolute gibberish, and qualifies as a G1. Of course, after moving to draft space I can delete it as a G1, but this policy, as written, '''requires''' that I move it to draft space first. If I do not, I am potentially santionable for violating policy.
**Rinse and repeat for an article which is a clear copyvio, but in another language.
**Or an article which is an attack. Yes, this could be fixed, but there are other issues to address. It states that the article will be moved to draft '' to verify that the article in question doesn't violate copyright ''. Moving an article to draft space doesn't solve the copyright problem. We don't have an exception that allows copyvios in draft space. There are other issues as well, so it isn't the case that a couple minor copy edits will make this acceptable as is. That said, it has promise.--]] 14:57, 18 May 2015 (UTC)
*** These are problems that we already have. Currently it's not possible to speedy an article simply because it's non-English, and often that's a problem because we can't tell whether the article complies with policy or not. It could be blatant vandalism but we have to keep it for at least two weeks until someone can identify what we're dealing with. Moving that kind of an article out of mainspace (and to somewhere where search engines can't find it) is a good compromise. — ] <sup>(])</sup> 15:07, 18 May 2015 (UTC)
::::Yes, it is possible to speedy an existing article in another language. (After re-reading, I guess you are saying that simply being in non-English is not a sufficient reason for CSD, but as I'll explain, I can identify valid CSDs even though my language skills are minimal.) I can tell that something is a copyvio if it is clearly an exact copy of a published item. Google translate is deficient for some purposes, but if Google Translate produces ''John Doe is a well-know child molester'' I don't need a competent human translator to tell me it can be deleted. If the article is created by a banned or blocked user, I don't even need to translate the content. Yet, this proposed policy says I should move it to draft space first. Why?--]] 16:57, 18 May 2015 (UTC)
::::: Does it really say that? That you ''must''? I'm not seeing it. If you can tell that an article qualifies for speedy then of course you can speedy it, I don't think anyone would argue that. Though in cases like this you may have to leave a note behind explaining how it qualifies, if it's not immediately obvious to admins who do the deleting. — ] <sup>(])</sup> 17:03, 18 May 2015 (UTC)
*'''Oppose''' as unnecessary bureaucracy. Speaking as one of the half dozen or so editors who handle non-English articles at PNT every single day, we always deal with these articles in the best and most efficient way possible. This can be one of many ways, sometimes they're translated, becoming valuable articles, sometimes they are speedy deleted if they meet a criteria (and yes I'll admit that I usually IAR delete the essays and rants we often get), sometimes they are prodded/blpprodded or afd'd if we think they're not worth translating, if we think they are worth an article but can't translate them ourselves we leave them (and after two weeks they are prodded and deleted it not translated) and yes we sometimes userfy them if we feel they were created in good faith and that . To just point out how small a problem this is, currently there are 6 articles (out of {{NUMBEROFARTICLES}}) that are entirely not in English, 3 of which are currently prodded. Trying to enforce a firm rule that all non-English articles be immediately userfied is just overkill, and a good way to prevent potential good articles, the current system works just fine, the ] which started this whole drama-fest being a perfect example.--] ] 17:18, 18 May 2015 (UTC)
*'''Oppose''' per ]. We already have processes for non-English articles. While they are not perfect they work well enough, better than this clunky idea would anyway. ] (]) 18:04, 18 May 2015 (UTC)
*'''Oppose''' per Jac16888 who says the current system is working fine. Also, we assume good faith until shown otherwise. We don't assume the article may be "dodgy" just because we can't read it. ]] 18:22, 18 May 2015 (UTC)
*'''Oppose''' There is already an established procedure for translating non-English articles, ]. This happened to me once. I created a new article by copy-pasting the French language version, then proceeded to translate it in place. I expected this to be a quick task, but got sidetracked and then interrupted by an offline event. (I should have created it in the draft space, but this requires an admin request.) For my trouble I got templated that I should first list the article for translation, and then come back and translate it. ] (]) 20:07, 18 May 2015 (UTC)
:: *''' Comment ''' Actually it doesn't require admin permissions. I've created a draft space article and I'm definitely not an admin. <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 20:14, 18 May 2015 (UTC)
::: Even IPs can create draftspace pages. o_O — ] <sup>(])</sup> 20:16, 18 May 2015 (UTC)
:::: True! But unfortunately moving the draft article to the mainspace causes a redirect to be left behind, which then requires a CSD (admin request) to delete. So I try to avoid this whenever I possibly can. Sorry, I did not make myself clear. ] (]) 02:53, 19 May 2015 (UTC)
::::: Redirects from draftspace to mainspace are okay. AFC reviewers leave them behind all the time. — ] <sup>(])</sup> 09:06, 19 May 2015 (UTC)
::::: {{ping|Hawkeye7}} When moving an article there is an option to ''not'' leave behind a redirect = uncheck the "leave a redirect behind" box. --User:Ceyockey (<small>'']''</small>) 00:42, 22 May 2015 (UTC)
:::::: {{re|Ceyockey}} Not true if you aren't an admin. Though I have been pushing for allowing this permission for non admins recently, it has been met with resistance. ''']'''<sup><small>(])</small></sup> 00:45, 22 May 2015 (UTC)
::::::: {{re|EoRdE6}} Ahhh. I did not realize this was an admin-only function. Apologies and thanks for highlighting that. --User:Ceyockey (<small>'']''</small>) 00:58, 22 May 2015 (UTC)
*'''Oppose''' revoking ] without the proposer either acknowledging its long-standing acceptance or notifying the page that he hopes to revoke it (perhaps he just didn't know that it exists? Nobody can keep up with everything around here, because there are so many pages). In fact, most of the above "votes" don't seem to know that we have a procedure for handling such pages. I expect they all would have guessed that "edit-war to blank the page" isn't it, though. ], ], ], ], ], ], ], ], ], ], ], I'd be interested in knowing how many of you were aware of the standard procedure before this discussion, and whether you think that years-old advice is probably an adequate approach, or if you still think we need yet another policy or guideline for the occasional article that isn't written in English. ] (]) 21:39, 18 May 2015 (UTC)
::I was aware of the standard procedure when !voting, and have looked at and speedied persian article on WP:PNT from time to time. I voted under the assumption that if this passed, PNT would still function, only pages translated would be temporarily moved to draftspace first. This seems like the most common sense solution.] (]) 21:50, 18 May 2015 (UTC)
:::I can see why a reasonable person might hope for that, but this policy would actually preclude the standard procedure. The proposed policy prohibits leaving a non-English article in the mainspace for two weeks (= it prohibits "the standard procedure"). The editors at PNT do not handle articles anywhere else (by choice, and those ] are the only ones who get to make that choice). It is not possible to have "the new policy" and "the standard procedure" operating at the same time. "There must never be articles needing translation in the mainspace" and "We only translate articles in the mainspace" cannot function at the same time.
:::The potential for confusion is why I'm unhappy about the failure to be more explicit about the policy's effects. I am worried that some people are voting for a benign-sounding, commonsensical statement without understanding that the intended outcome is to eliminate a long-standing process. This proposal amounts to revoking PNT's standard procedure, although it doesn't come out and say so in ways that will be clearly understood by everyone. If you want to change an old process, that's fine, but IMO you should say so, using words that cannot possibly be misunderstood (e.g., "I propose stopping the bad old way and replacing it with this obviously better idea:").
:::The immediate history also gives me pause: The precipitating incident is that the proposer blanked an article (three times in three hours, if the comment below is correct) and was told that the standard procedure is to tag it and wait for two weeks. He was not satisfied with waiting for two weeks, so he proposes here a policy to override it. However, he does not mention the existing standard procedure. He gives only the briefest mention that he lost a dispute because of it. The sole practical effect of his proposed policy is to revoke the process that caused him to lose the dispute. He makes no acknowledgement of how this proposal affects longstanding processes. I've spent years around policy pages, and I can tell you that this situation is a fairly reliable recipe for disaster and drama. If you want to kill an old process, then you need to tell to people that you're doing it.
:::Note that I don't mind changing old processes, if that's what people want to do. I've done it myself. My only requirement is that supporters understand that's the point of the proposal and say that they're intentionally replacing an old process. ] (]) 23:38, 18 May 2015 (UTC)
::::I think it's very simple to keep the old and new processes in place at the same time. You just apply all the same rules to the drafts that you would to non english articles, and speedy them if no one translates after two weeks. A venue for translation is still maintained and you don't end up with old non-english articles on god-knows-what languishing about in draftspace. Best of both worlds.] (]) 23:46, 18 May 2015 (UTC)
:::::# This proposal doesn't actually do what you want it to do. (The alternate below does something close, but the original does not.)
:::::# In my experience it is never "simple" to force volunteers do things that they do not choose to do, and the volunteers at PNT have already said that they have no interest in doing what you want them to do. ] (]) 01:43, 19 May 2015 (UTC)
:::::: First of all '''I am''' someone who volunteers from time to time at PNT (as is GregJackP who supported the proposal and responded to you below), and in my capacity as someone who does so I believe its better to not have completely non-english articles languishing about in mainspace, and I would completely willingly move non-english articles to draft space. Also can you point me to exactly where the collective you refer to as the "volunteers at PNT" have unanimously opposed this decision? As for the proposal not doing what i think its supposed to do, this seems to be another example of an incredibly simple and beneficial change being bogged down in Village pump bureaucracy. I'm sure the closing admin will be able to interpret what I mean.] (]) 16:48, 19 May 2015 (UTC)
::::::::I base my statement about the volunteers at PNT on the comment below: "There is a long-held consensus, re-affirmed just a few weeks ago, at PNT that draft articles do not fall within our scope of work..." by ]. ] (]) 17:13, 19 May 2015 (UTC)
:::::::::Thanks for directing me to that. Although I'd forgotten about it, I actually ] and at the time (although I didnt write it because enough other people had) was opposed to the idea of putting all non-english drafts in PNT. However, I think this case is very different to that, as only drafts that were intitially posted in article space would be brought to PNT for temporary holding, as opposed to any gibberish written in draftspace. I think it's an apples and oranges situation. ] (]) 20:22, 19 May 2015 (UTC)
::I was aware also, and have tagged many such articles. I've also watched articles not be translated for significant periods of time. However, I don't think that we need to keep articles which are not written in English. BTW, your comment was very condescending, I guess us mere non-WMF editors wouldn't have thought of other options. <span style="border:1px solid #900;padding:2px;background:#fffff4">] ]</span> 22:53, 18 May 2015 (UTC)
:::It's worth noting that the existing standard procedure predates the existence of the Draft namespace, and therefore might be due an overhaul with the new option in mind. That's probably something for the appropriate talkpage, though. It's my opinion that the suggestions offered here, especially the alternative version below, constitute an improvement on the current process. ] ]] 07:50, 19 May 2015 (UTC)
== RfC: Voluntary RfA after resignation ==
*'''Oppose''' Over at ] we use a template called ], not everything should be in English per ]. - ] (]) 23:59, 18 May 2015 (UTC)
<!-- ] 22:01, 19 January 2025 (UTC) -->{{User:ClueBot III/DoNotArchiveUntil|1737324070}}
*'''Oppose''' I agree with {{u|Beeblebrox}} that this is nothing but ]. There is no need to have a policy or guideline to state that the English Misplaced Pages should in English. —''']''' (] | ]) 00:31, 19 May 2015 (UTC)
{{rfc|policy|rfcid=5F11665}}
*'''Oppose''' (a) the proposal incorrectly implies that there is a single english language and (b) articles have very good and well established grounds for using non-English languages (be it Japanese, Arabic; Latin or native american languages) in places (alternative names, linguistic examples, etc, etc); many articles would be significantly impaired with those. ] (]) 10:43, 19 May 2015 (UTC)
*'''Oppose''' per several comments above. Most notably, we already delete or translate articles written in foreign languages, so this proposed policy does not actually accomplish anything. As such, it is unnecessary ]. ]] 14:10, 19 May 2015 (UTC)
::*'''Comment ''' {{U|Knowledgekid87}} Bias huh ? Note the proposal is for articles not templates (I'm also a self-described Otaku :) ) {{U|TheFarix}} I actually agree, this shouldn't ''have'' to be policy, I would have thought it common sense, however ] told me otherwise. {{U|SpinningSpark}} AGF is not a suicide pact, further, author editors, even in good faith sometimes run afoul of copyright concerns because they're not aware of how ours works (and BLP as well ). <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 15:42, 19 May 2015 (UTC)
:::*The template makes both Japanese and English text appear on the page, we also have Japanese names as article titles and as character names (as such the name would be included in the article's body) per ]. By all in English do you mean all content of a given article? I want to have an open mind but please specify as it sounds too broad if I read "All entries in article space need to be in English" right. - ] (]) 16:29, 19 May 2015 (UTC)
:::*{{ping|User:KoshVorlon}} I would support your proposal for entries that are written fully in another language or a certain percentage of the article, there has to be some kind of footnotes/exceptions though if this is to become policy. - ] (]) 16:40, 19 May 2015 (UTC)
::::Kosh, you continue to refer to your "little incident" as why this change needs to be made, and yet the article which started all of this (] for anyone not already aware), was, once properly reported to PNT, translated and then prodded within a few hours of being created, similarly a dozen+ other articles have been created and dealt with in the time since then - I don't see how any of this is problematic. If anything your incident shows that, when procedure if actually followed, the system we have works great --] ] 20:41, 19 May 2015 (UTC)
:::*"]" or in this case bad policy/guidelines. It's clear in that discussion that you didn't follow already existing procedures for handling such types of articles. But I honestly don't see the need for a policy over just one incident. —''']''' (] | ]) 20:20, 19 May 2015 (UTC)
*'''Oppose'''. If it ain't broken, don't fix it. The current process is working fine, and no non-English article is kept any longer than necessary. ] (]) 18:30, 19 May 2015 (UTC)
*'''Oppose''': no pressing need to adopt an ] policy for the first appearance of an article. A working proceedure is in place. — ] (]) 21:22, 19 May 2015 (UTC)
* '''Comment''' For those opposing, please see ] where the the reverse happened. Just so I'm totally clear, I'm not suggesting that if we have an article about a Japanese term, or a Spanish term, that we can't use the Spanish or Japanese word itself, nor am I suggesting that that word be written out in the English alphabet. What I'm suggesting is that any article in '''article space''' needs to be in English, currently we're getting entries in article space that are 100% not English. I'm suggesting that they be placed in draft space where they can be translated , then judged to be in compliance with all applicable Misplaced Pages policies and guildelines. That's it, simple, obvious and very much common sense. <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 11:00, 20 May 2015 (UTC)
::You mean the posting which shows that when a non-english article is submitted to the proper place, it is dealt A perfect example to me of how well the current PNT system works, when of course it it is actually used rather than ignored--] ] 16:32, 20 May 2015 (UTC)
::: Except that '''article space''' is the '''wrong place''' for non-English articles. So no, it wasn't in the proper place. <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 16:42, 21 May 2015 (UTC)
::::Not sure if you're intentionally misunderstood my point there or not. By "proper place", I mean PNT, as in, a user followed procedure and logged it there, and then it was resolved shortly afterwards. In fact had you done so yourself, or had you actually moved it to the draftspace properly (that being one way we do deal with non-english articles already anyway), there would have been no issue. I feel I have to ask this, as you've never actually addressed this: please can you tell me that you understand why blanking a page or copying and pasting it to another place is a bad thing--] ] 17:00, 21 May 2015 (UTC)
::::: Jac16888 - yeah, I did. I consider article space to not be the proper place for articles not in English, rather I'd say Draft space is. The article was in article space when I first ran across it. Yes, I agree PNT acted correctly by translating the article, I wasn't trying to change the process that got the article translated, rather the fact that the article should have been in article space prior to translation. <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 15:29, 22 May 2015 (UTC)
*'''Oppose''' - you lost me at "Further, most of the users on this Misplaced Pages do not read any other language." That's absurd. Where did you get this information? I don't remember indicating what languages I can read when I created an account. It seems that, because you can't read any other languages, you assume everyone is the same? Otherwise why would you assume this? Further, how often are there articles that are entirely in another language that are not copyright violations or able to be removed for another basic reason? Why is this policy necessary? I looked at the ] and I agree with Jac16888 - your insistence that you should be able to blank a page because it's in another language is not sound. It's laziness at best, censorship at worse. ]<sup>]</sup> 😜 00:28, 22 May 2015 (UTC)
:: Actually, what I mean is the language of this Misplaced Pages is English. I see your name is in Russian (ok, Cryllic , so it might not be Russian as other languages use the Cryllic Alphabet ) assuming you ARE Russian, would it make sense to have an article in ru.wikipedia.org in English rather than in Russian, even though there may be people on that Misplaced Pages that read English ? Of course not, it's common sense, the lingua franca on that Misplaced Pages is Russian, just the the lingua franca on this wikipedia is English. Articles should conform to the lingua franca, obviously there may be portions of the article that need to be in a different language (reliable references in other languages, a term in another language that needs to be in. That kind of thing. ). What we should '''not''' have in an article of any sort , written completely in another language. <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 15:29, 22 May 2015 (UTC)
:::What irks me more is how we have maps that are written in different languages being used (Examples: Battle maps, road maps, ect...). Yeah the maps are encyclopedic but unless you speak the language there is no way to understand them. - ] (]) 15:54, 22 May 2015 (UTC)
::::A good caption on the map can usually address that problem adequately. There's also a brand-new tool for making charts and maps (links at ]) that should make it much easier to translate vector-based maps. ] (]) 17:32, 22 May 2015 (UTC)
*'''Oppose''': We don't need a ] for this. That's overkill. Userspacing or deleting these things is already standard operating procedure. <small></small> <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 09:47, 24 May 2015 (UTC)
*'''Oppose''' per ]. ] (]) 03:45, 30 May 2015 (UTC)
*'''Oppose''' PNT works pretty well as far as I have seen, don't fix what ain't broke. This proposal also seems to me. ] (]) 23:19, 31 May 2015 (UTC)
Should ] be amended to:
=== English policy: Discussion ===
* '''Option 1'''{{snd}}Require former administrators to request restoration of their tools at the ] (BN) if they are eligible to do so (i.e., they do not fit into any of the exceptions).
* Why is this necessary? We already have {{section link|Misplaced Pages:Manual of Style|National varieties of English}} ("The English Misplaced Pages prefers no major national variety of the language over any other") and ] ("This version of Misplaced Pages is written in ]") for example, and it's inherent in the fact that this is the English Misplaced Pages (there are other language varieties). Is this really a problem? Or a ]? <small>—''']''' ]</small> 11:50, 18 May 2015 (UTC)
* '''Option 2'''{{snd}}<s>Clarify</s> <ins>Maintain the status quo</ins> that former administrators who would be eligible to request restoration via BN may instead request restoration of their tools via a voluntary ] (RfA).
::I can see that ] had an issue ({{section link|Misplaced Pages:Administrators' noticeboard|Behavior of Jac16888}}) after {{diff|Detective Willy|662806778|662806608|blanking}} ({{diff|Detective Willy|662826797|662826719|three}} {{diff|Detective Willy|662832430|662830118|times}} in three hours) the article ] which was written in Spanish (it was {{diff|Detective Willy|662843562|662840953|translated into English}} within two hours afterwards).
* '''Option 3'''{{snd}}Allow bureaucrats to SNOW-close RfAs as successful if (a) 48 hours have passed, (b) the editor has right of resysop, and (c) a SNOW close is warranted.
::] (]) provides a process encouraging translation before hasty deletion, which may be a useful approach. It worked for the above-mentioned article and, if the article survives proposed deletion on notability grounds, it will be a good addition to Misplaced Pages. PNT isn't a policy or guideline, but if the policy proposed here were adopted, it would need to be completely re-worked. Accordingly, I have flagged this discussion on its talk page ({{section link|Misplaced Pages talk:Pages needing translation into English|Proposed policy to move articles in foreign languages to draft space}}).
::<small>—''']''' ]</small> 12:36, 18 May 2015 (UTC)
::: I don't see why an article could not both be (1) moved into draftspace and (2) listed at PNT. Wholly non-English articles where it's hard to even determine the subject, are not ready for articlespace, and they shouldn't be immune from our usual deletion criteria (like A7) simply because we can't understand what's going on in those articles. — ] <sup>(])</sup> 12:42, 18 May 2015 (UTC)
::::{{reply|Jeraphine Gryphon}} I don't think {{section link|Misplaced Pages:Criteria for speedy deletion|A7. No indication of importance (individuals, animals, organizations, web content, events)}} necessarily applies just because an article is in a foreign language; however, you're quite right that an article which has no (or barely any) English-language content doesn't belong in article space. {{multi-section link|Misplaced Pages:Deletion policy|Alternatives to deletion|Incubation}} can be applied to move them to draft space while they are being re-worked.
::::I note that some of the articles listed at {{section link|Misplaced Pages:Pages needing translation into English|Pages for consideration}} have some English-language content and some foreign-language content requiring translation, so these would not be ripe for deletion and leaving them in article space may attract users to bring them up to grade. There are some articles, however, that are entirely in a foreign languages and have been listed for some time:
::::*] (since 25 April, 23 days ago)
::::*] (since 29 April, 19 days ago)
::::*] (since 1 May, 17 days ago)
::::*] (since 3 May, 15 days ago)
::::That's just the ones that are over the two-week period. This shows that while the system can sometimes work quickly (as in the case of ]), articles can languish in article space waiting for attention. This being the case, I would support WP:PNT being revised to encourage moving articles to draft space until they are translated, perhaps then allowing a longer period before nominating them for deletion to give them a better chance of being salvaged. I'm not convinced this needs to be enshrined in a separate policy, however. <small>—''']''' ]</small> 13:43, 18 May 2015 (UTC)
'''Background''': This issue arose in one ] and is currently being discussed in an ]. ] (]/]) 21:14, 15 December 2024 (UTC)<br />
:* This has nothing to do with varieties of English. — ] <sup>(])</sup> 12:30, 18 May 2015 (UTC)
'''Note''': There is an ongoing related discussion at {{slink|Misplaced Pages:Village pump (idea lab)#Making voluntary "reconfirmation" RFA's less controversial}}.<br />
* ''Question:'' Will this be appended to, or be a new part of, the pre-existing ]? Or will these be merged together? If not, how will this work?... --] (]) 12:33, 18 May 2015 (UTC)
'''Note''': Option 2 was modified around 22:08, 15 December 2024 (UTC).
:: {{U|IJBall}} I'd suggest making this part of ]. <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 13:03, 18 May 2015 (UTC)
:: {{U|Sroc}} You're right. That's what started this proposal. <span style="font face="Papyrus" size="4" font-weight:bold">] ]</span> 13:03, 18 May 2015 (UTC)
*'''2''' per ]. If an admin wishes to be held accountable for their actions at a re-RfA, they should be allowed to do so. ] ] 21:22, 15 December 2024 (UTC)
::] is actually ], which I see as interpreting ] policy, so I don't think it can simply be appended there -- at least not without additional changes. This new rule would apply to the whole article, more like ]. I see this new rule as based more on the policy ] or ], where the English-language Misplaced Pages should be defined as written in English. --] (]) 13:40, 18 May 2015 (UTC)
*:Also fine with 3 ] ] 22:23, 15 December 2024 (UTC)
::::I agree that this should not be part of ]. There's a section ] which discusses moving articles from mainspace to draft space. Maybe a paragraph about when this is appropriate could be added there, including pages not in English.—] (]) 13:47, 18 May 2015 (UTC)
* There is ongoing discussion about this at ]. ] (]) 21:24, 15 December 2024 (UTC)
::::: ''Suggestion:'' As this is the case, I suggest that the new policy's "shortcut" should become "]" if adopted, and the "old" WP:ENGLISH's shortcut should become something line ] or some such... --] (]) 13:53, 18 May 2015 (UTC)
** '''2''', after thought. I don't think 3 provides much benefit, and creating separate class of RfAs that are speedy passed feels a misstep. If there are serious issues surrounding wasting time on RfAs set up under what might feel to someone like misleading pretenses, that is best solved by putting some indicator next to their RFA candidate name. Maybe "Hog Farm ('''RRfA''')". ] (]) 14:49, 16 December 2024 (UTC)
::::::] is a bit vague, and ] may be better. However, a new policy may not be needed; instructions to move pages awaiting translation to Draft space can be added at ].—] (]) 13:59, 18 May 2015 (UTC)
**:{{tq|best solved by putting some indicator next to their RFA candidate name. Maybe "Hog Farm (RRfA)"}} - I like this idea, if option 2 comes out as consensus I think this small change would be a step in the right direction, as the "this isn't the best use of time" crowd (myself included) would be able to quickly identify the type of RFAs they don't want to participate in. ] ] 11:05, 17 December 2024 (UTC)
::::::: ] would also work. --] (]) 14:02, 18 May 2015 (UTC)
**::I think that's a great idea. I would support adding some text encouraging people who are considering seeking reconfirmation to add (RRfA) or (reconfirmation) after their username in the RfA page title. That way people who are averse to reading or participating in reconfirmations can easily avoid them, and no one is confused about what is going on. ] (]) 14:23, 17 December 2024 (UTC)
:::::::: Changing the target of shortcuts if often a bad idea, because previous usages of the shortcut will then all point to the wrong target. — ] <sup>(])</sup> 14:33, 18 May 2015 (UTC)
::::::::: Yes, agreed. But if this proposal passes, I think itmay be warranted.Atleast, it shouldbediscussed. --] (]) 15:54, 18May2015 (UTC)
**::I think this would be a great idea if it differentiated against recall RfAs. ] (]) 18:37, 17 December 2024 (UTC)
**:::If we are differentiating three types of RFA we need three terms. Post-recall RFAs are referred to as "reconfirmation RFAs", "Re-RFAS" or "RRFAs" in multiple places, so ones of the type being discussed here are the ones that should take the new term. "Voluntary reconfirmation RFA" (VRRFA or just VRFA) is the only thing that comes to mind but others will probably have better ideas. ] (]) 21:00, 17 December 2024 (UTC)
::::: I think changing the description of the process would be better than a "policy" change, but am still wondering about whether any change in normal practice is necessary. In any case, it might be appropriate to change ] into something like a disambiguation page pointing to a number of pages that also deal with the use of English (e.g. pages needing translation, diacritics, transliteration etc.).--] (]) 19:27, 18 May 2015 (UTC)
* '''1''' ] ] 21:25, 15 December 2024 (UTC)
::::::Or at least to add a hatnote to ENGLISH that directs people to ]. ] (]) 23:42, 19 May 2015 (UTC)
*'''2''' I don't see why people trying to do the right thing should be discouraged from doing so. If others feel it is a waste of time, they are free to simply not participate. ] ] 21:27, 15 December 2024 (UTC)
{{comment}} In at least one country where English is the most widely used language, ''requiring'' English, or ''mandating'' English is a politically fraught topic (see ]). Also in en.Misplaced Pages, it seems. Better to ease along with what has worked for 5,000,000 articles. — ] (]) 02:22, 31 May 2015 (UTC)
*'''2''' Getting reconfirmation from the community should be allowed. Those who see it as a waste of time can ignore those RfAs. ] ] 21:32, 15 December 2024 (UTC)
*Of course they may request at RfA. They shouldn't but they may. This RfA feels like it does nothing to address the criticism actually in play and per the link to the idea lab discussion it's premature to boot. ] (]) 21:38, 15 December 2024 (UTC)
===Alternative proposal for dealing with foreign-language articles===
*'''2''' per my comments at the idea lab discussion and Queent of Hears, Beeblebrox and Scazjmd above. I strongly disagree with Barkeep's comment that "They shouldn't ". It shouldn't be made mandatory, but it should be encouraged where the time since desysop and/or the last RFA has been lengthy. ] (]) 21:42, 15 December 2024 (UTC)
The proposed new policy is unnecessary and would conflict with existing processes, such as ] (]), which would then need to be re-worked. Instead, in order to streamline things and avoid fracturing, I would recommend amending WP:PNT to change the process for dealing with articles ''entirely'' (or almost entirely) in foreign languages as follows:
*:When to encourage it would be a worthwhile RfC and such a discussion could be had at the idea lab before launching an RfC. Best, ] (]) 21:44, 15 December 2024 (UTC)
*::I've started that discussion as a subsection to the linked VPI discussion. ] (]) 22:20, 15 December 2024 (UTC)
#Move the article into the ] namespace.
*'''1''' <ins>or '''3'''</ins>. RFA is an "expensive" process in terms of community time. RFAs that qualify should be fast-tracked via the BN process. It is only recently that a trend has emerged that folks that don't need to RFA are RFAing again. 2 in the last 6 months. If this continues to scale up, it is going to take up a lot of community time, and create noise in the various RFA statistics and RFA notification systems (for example, watchlist notices and ]). –] <small>(])</small> 21:44, 15 December 2024 (UTC)
#List the article at {{section link|Misplaced Pages:Pages needing translation into English|Pages for consideration}}.
*:Making statistics "noisy" is just a reason to improve the way the statistics are gathered. In this case collecting statistics for reconfirmation RFAs separately from other RFAs would seem to be both very simple and very effective. ''If'' (and it is a very big if) the number of reconfirmation RFAs means that notifications are getting overloaded, ''then'' we can discuss whether reconfirmation RFAs should be notified differently. As far as differentiating them, that is also trivially simple - just add a parameter to ] (perhaps "reconfirmation=y") that outputs something that bots and scripts can check for. ] (]) 22:11, 15 December 2024 (UTC)
#Articles that are not likely to survive may be proposed for deletion according to the usual ] or ] to the extent that they apply to drafts (see {{section link|Misplaced Pages:Drafts|Deleting a draft}}).
*:Option 3 looks like a good compromise. I'd support that too. –] <small>(])</small> 22:15, 15 December 2024 (UTC)
*:I'm weakly opposed to option 3, editors who want feedback and a renewed mandate from the community should be entitled to it. If they felt that that a quick endorsement was all that was required then could have had that at BN, they explicitly chose not to go that route. Nobody is required to participate in an RFA, so if it is going the way you think it should, or you don't have an opinion, then just don't participate and your time has not been wasted. ] (]) 22:20, 15 December 2024 (UTC)
<small>—''']''' ]</small> 14:03, 18 May 2015 (UTC)
*'''2'''. We should not make it ''more difficult'' for administrators to be held accountable for their actions in the way they please. ]<sub>]<sub>]</sub></sub> (]/]) 22:00, 15 December 2024 (UTC)
* Added '''option 3''' above. Maybe worth considering as a happy medium, where unsure admins can get a check on their conduct without taking up too much time. ] (] • she/her) 22:11, 15 December 2024 (UTC)
:::I'd like to take this opportunity to acknowledge ]'s insight in highlighting this issue and getting the discussion going.
*'''2''' – If a former admin wishes to subject themselves to RfA to be sure they have the requisite community confidence to regain the tools, why should we stop them? Any editor who feels the process is a waste of time is free to ignore any such RfAs. — ] ⚓ ] 22:12, 15 December 2024 (UTC)
:::I would like to add that my proposed process doesn't need to be mandatory: if an article in a foreign language is obviously a copyvio, vandalism, etc., it can be sent straight to speedy deletion as usual without having to be moved to Draft first. This process is intended for articles that could survive if they are translated into English. <small>—''']''' ]</small> 17:08, 18 May 2015 (UTC)
*:*I would also support option '''3''' if the time is extended to 72 hours instead of 48. That, however, is a detail that can be worked out after this RfC. — ] ⚓ ] 02:05, 16 December 2024 (UTC)
*'''Option 3''' per leek. ] (]/]) 22:16, 15 December 2024 (UTC)
*'''Support''' - Not because I disagree with us KoshVorlon's idea, but because we don't need a policy, we need a process. As a new page patroller, I routinely move articles to draft space as an alternative to deletion, or as an alternative to leaving really incomplete content in article space. If either of these proposals passes, someone should follow up with the Twinkle developers to make sure that this multi-step process can be semi-automated.- ]] 14:35, 18 May 2015 (UTC)
*:A further note: option 3 gives 'crats the discretion to SNOW close a successful voluntary re-RfA; it doesn't require such a SNOW close, and I trust the 'crats to keep an RfA open if an admin has a good reason for doing so. ] (]/]) 23:24, 16 December 2024 (UTC)
*'''Support''' I'd be equally happy with this proposal (and hear hear to getting the process Twinklified). ] ]] 14:39, 18 May 2015 (UTC)
*'''2''' as per {{noping|JJPMaster}}. Regards, --] (]) 22:20, 15 December 2024 (UTC)
*'''Support''' Has the same net effect as the above policy, but is a more efficient implementation. Per MrX I would like to see Twinkle support moving articles to draft space more easily. I would also like to here other editors thoughts on moving other types of very-low quality articles by new editors into draft space without going through AfD to do it. ] ] 14:44, 18 May 2015 (UTC)
*'''Option 2''' (no change) – The sample size is far too small for us to analyze the impact of such a change, but I believe RfA should always be available. Now that ] is policy, returning administrators may worry that they have become out of touch with community norms and may face a recall as soon as they get their tools back at BN. Having this familiar community touchpoint as an option makes a ton of sense, and would be far less disruptive / demoralizing than a potential recall. Taking this route away, even if it remains rarely used, would be detrimental to our desire for increased administrator accountability. – ] 22:22, 15 December 2024 (UTC)
* '''Support''' – OK, this sounds good as well. --] (]) 15:57, 18 May 2015 (UTC)
*{{ec}} I'm surprised the response here hasn't been more hostile, given that these give the newly-unresigned administrator a ] for a year. —] 22:25, 15 December 2024 (UTC)
* '''Support''' It seems clear that KoshVorlon's idea is based on an actual problem (and not an imaginary one) but I am skittish about adding still more rules to Misplaced Pages's already large collection. This looks like it would dovetail well with the existing structure. Also, "most, if not all read no other language"? Mis seis años de clases de español no están de acuerdo contigo. WP:COMMONSENSE already covers the idea that the English Misplaced Pages must be in English, and this looks like it would protect Misplaced Pages from copyright violations without overdoing it. ] (]) 16:15, 18 May 2015 (UTC)
*:@] hostile to what? ] (]) 22:26, 15 December 2024 (UTC)
*'''Oppose''' As noted above, there are articles entirely in non-English that may qualify as a CSD. If this policy is approved, it means if I find an article in Spanish written by a banned user, I cannot simply delete it as a G5, but I must first move it to Draft space. This is the very definition of silly bureaucracy. On a more general note, what is the reluctance to use the Idea Lab to sort out a sensible approach?--]] 17:05, 18 May 2015 (UTC)
*'''2, distant second preference 3'''. I would probably support 3 as first pick if not for recall's rule regarding last RfA, but as it stands, SNOW-closing a discussion that makes someone immune to recall for a year is a non-starter. Between 1 and 2, though, the only argument for 1 seems to be that it avoids a waste of time, for which there is the much simpler solution of not participating and instead doing something else. ] and ] are always there. <span style="font-family:courier"> -- ]</span><sup class="nowrap">[]]</sup> <small>(])</small> 23:31, 15 December 2024 (UTC)
*:This would not be a policy. It would be a process that you can choose to use, or not. Neither this nor the previous proposal would prevent other deletion processes from being used as needed. You say that this is the definition of a silly bureaucracy, but suggest sending it to the Idea Lab. Irony?- ]] 17:23, 18 May 2015 (UTC)
* 1 would be my preference, but I don't think we need a specific rule for this. -- ] (]) 23:36, 15 December 2024 (UTC)
::{{reply|Sphilbrick}} Are you saying this to oppose Kosh's proposed policy or my proposed amendment to WP:PNT? Articles could still be deleted without being moved to Draft first, at least with my proposal, so your reasoning doesn't hold. <small>—''']''' ]</small> 17:58, 18 May 2015 (UTC)
*'''Option 1'''. <s>No second preference between 2 or 3.</s> As long as a former administrator didn't resign under a cloud, picking up the tools again should be low friction and low effort for the entire community. If there are issues introduced by the recall process, they should be fixed in the recall policy itself. ] (]) 01:19, 16 December 2024 (UTC)
:::Given that the original was proposed as a new Policy, and this is labeled as an Alternate proposal, I thought it was intended to be alternative proposal for a policy. I now see it is an alternate proposal for a rewording of a process, so it doesn't contain the same weight as a policy. Still, my objection remains. The proposal step one says ''Move the article into the Draft namespace''. I disagree. I'd start with ''Determine whether it qualifies as a CSD as is.If not, or indeterminate, move into the Draft namespace'' But this is OTTOMH and could use word smithing. Re "irony" I think it is misplaced. I am a big fan of bureaucracy, when sensible. We ought to have well-thought out rules for handling solutions, and well-thought out processes for dealing with issues. What I oppose is mindless bureaucracy, such as moving an article to Draft space, then deleting it when it is perfectly obvious it should be deleted as is. The entire concept of the Idea Lab is that it is difficult, if not impossible, to write up new Policies, and there ought to be a place to work on them, and get them ready for an up or down vote. Both the original and the alternate proposals qualify. Neither were ready for prime time. Both has some good ideas that I could support if the issues were addressed. The Idea Lab is intended as a place to address them. I get why people want to come here first, because they think their idea is so good it can be supported exactly as worded, or maybe with a tiny word change, but they miss that it often takes a robust discussion of issues to come up with good wording for a new proposal. This is more true today than it was in the early days of WP, when there was so low-hanging fruit, and it might have been reasonable to slap together a policy and approve it.--]] 18:09, 18 May 2015 (UTC)
*:After considering this further, I prefer option 3 over option 2 if option 1 is not the consensus. ] (]) 07:36, 16 December 2024 (UTC)
:::{{ping|Sroc}} I oppose the policy proposed by Kosh as written, for the reasons I outlined (and there are more objections, I just didn't think it was necessary to be exhaustive.) I oppose the alternative wording of WP:PMT. The existing process has a set of steps for entire articles. Your proposed step 1, which presumably replaces the existing step 1, says ''Move the article into the Draft namespace''. Maybe you think it is implicit that you can delete via CSD before this step, but that's not what it says.--]] 18:16, 18 May 2015 (UTC)
*'''Option 2''', i.e. leave well enough alone. There is really not a problem here that needs fixing. If someone doesn’t want to “waste their time” participating in an RfA that’s not required by policy, they can always, well, not participate in the RfA. No one is required to participate in someone else’s RfA, and I struggle to see the point of participating but then complaining about “having to” participate. ] (]) 01:24, 16 December 2024 (UTC)
::::{{reply|Sphilbrick}} Nothing in my proposal seeks to usurp current deletion policy, and I've expressly said in my further comment that articles could still be deleted as usual without having to move them to Draft namespace first. I haven't set out the exact wording as I was just seeking ro assess general support—the exact implementation might be put to an RfC if necessary—but I was especially hoping to point out that although Kosh's intentions were good, that doesn't mean we have to leap to the first proposal (i.e., a new policy) and alternatives should be considered. <small>—''']''' ]</small> 19:08, 18 May 2015 (UTC)
*'''Option 2''' nobody is obligated to participate in a re-confirmation RfA. If you think they are a waste of time, avoid them. ] (]) 01:49, 16 December 2024 (UTC)
*'''Oppose''' also per ]. We don't need a new policy, or a new process. And I do not like setting a precedent that anyone can just move an article into draft space on a whim, that will put us on a slippery slope. The correwct way to currently deal with such issues is to put the great big {{tl|translate}} tag on the article, list it at pages needing translation, and add one the appropriate tag from ] to the creating user's talk page. I don't see how temporarily hiding it in the draft namespace on top of all that is any better. ] (]) 18:12, 18 May 2015 (UTC)
* '''1 or 3''' per Novem Linguae. <span style="padding:2px 5px;border-radius:5px;font-family:Arial black;white-space:nowrap;vertical-align:-1px">] <span style=color:red>F</span> ]</span> 02:35, 16 December 2024 (UTC)
:: I don't disagree with {{ping|Beeblebrox}} on many things, so I'm probably wrong here, but I wouldn't mind if we were more aggressive in moving articles into draft space. However, I'd prefer to do it as part of a comprehensive overhaul of the review process, in which articles which aren't quite ready for prime time were moved to Draft space, and I see articles written in a foreign language (which are otherwise not eligible for CSD) as an important special case. However, I worry that Draft may become a wasteland, so I wouldn't support it unless we had some good processes for clearing it out. I'm struggling with this because my position is closer to Kosh's and Sroc's than my opposes may suggest. I, too, have run across articles in main space, written entirely in another language, and thought that moving them into the Draft space might be a good next step. But while I can think of such examples, getting from a couple examples to a policy or even a process is trickier than some seem to realize.--]] 18:25, 18 May 2015 (UTC)
*'''Option 3''': Because it is incredibly silly to have situations like we do now of "this guy did something wrong by doing an RfA that policy explicitly allows, oh well, nothing to do but sit on our hands and dissect the process across three venues and counting." Your time is your own. No one is forcibly stealing it from you. At the same time it is equally silly to let the process drag on, for reasons explained in ]. ] (]) 03:42, 16 December 2024 (UTC)
::{{reply|Beeblebrox}} My counter-proposal is not really a "new process" but refining an existing one. In fact, moving an article to Draft namespace may save potential articles that just need to be translated that might otherwise be hastily deleted just because the current (arbitrary) two-week time limit has passed. <small>—''']''' ]</small> 19:12, 18 May 2015 (UTC)
*:Update: Option 2 seems to be the consensus and I also would be fine with that. ] (]) 18:10, 19 December 2024 (UTC)
:::I now see the language in ] I had missed earlier ''Articles that are not in English are still subject to all other forms of speedy deletion should they meet the criteria''. That mitigates my concern, but emphasizes the need to improve that page. When I see a process page with a list of steps, it seems reasonable that I should start with step 1.
*'''Option 3''' per Gnoming. I think 2 works, but it is a very long process and for someone to renew their tools, it feels like an unnecessarily long process compared to a normal RfA. ] (]) 04:25, 16 December 2024 (UTC)
:::In fact, one is expected to carry out some unnumbered steps first, which I will number, with the smartaleck convention of keeping the existing numbering intact:
*As someone who supported both WormTT and Hog Farm's RfAs, option 1 > option 3 >> option 2. At each individual RfA the question is whether or not a specific editor should be an admin, and in both cases I felt that the answer was clearly "yes". However, I agree that RfA is a very intensive process. It requires a lot of time from the community, as others have argued better than I can. I prefer option 1 to option 3 because the existence of the procedure in option 3 implies that it is a good thing to go through 48 hours of RfA to re-request the mop. But anything which saves community time is a good thing. <b>]]</b> (] • he/they) 04:31, 16 December 2024 (UTC)
:::Step -2: If someone speaks the language the article is written in and can state that it is not worth translating, the item should be moved to AfD or tagged with <nowiki>{{prod}}</nowiki>
*:I've seen this assertion made multiple times now that {{tpq| requires a lot of time from the community}}, yet nowhere has anybody articulated how why this is true. What time is required, given that nobody is required to participate and everybody who does choose to participate can spend as much or as little time assessing the candidate as they wish? How and why does a reconfirmation RFA require any more time from editors (individually or collectively) than a request at BN? ] (]) 04:58, 16 December 2024 (UTC)
:::Step -1: If the article is a mere copy of (all or part of) an article in a foreign-language Misplaced Pages, it can just be tagged with <nowiki>{{db-foreign}}</nowiki> to get added to Misplaced Pages:Candidates for speedy deletion
*::I think there are a number of factors and people are summing it up as "time-wasting" or similar:
:::Step 0: Check to see if other CSD criteria apply
*::# BN Is designed for this exact scenario. It's also clearly a less contentious process.
:::Step 1 (existing): Use the notice <nowiki>{{notenglish|NameOfLanguage}}</nowiki> ...
*::# Snow closures a good example of how we try to avoid wasting community time on unnecessary process and the same reasoning applies here. Misplaced Pages is not a bureaucracy and there's no reason to have a 7-day process when the outcome is a given.
:::Step 1 (proposed by you):Move the article into the Draft namespace.
*::# If former administrators continue to choose re-RFAs over BN, it could set a problematic precedent where future re-adminship candidates feel pressured to go through an RFA and all that entails. I don't want to discourage people already vetted by the community from rejoining the ranks.
:::Did you ever read the book ]? (I loved it, my daughter hated it), John <s>was</s><u>wanted</u> a barn door hinge for the door on his house, because the wood is so rotten, standard house hinges won't hold. The town decides that they shouldn't just do the minor fix, they should replace the whole house. It goes badly. Which is unfortunate for me, because I'm looking at your proposed replacement of step 1 with a different step, and I'm noticing that the house is falling down, and think we ought to fix the house, while the lesson in the story is that this approach ends badly. So I don't know what to do, but I am still unhappy about tinkering with a process and ignoring the glaring problems.--]] 20:35, 18 May 2015 (UTC)
*::# The RFA process is designed to be a thoughtful review of prospective administrators and I'm concerned these kinds of perfunctory RFAs will lead to people taking the process less seriously in the future.
::::{{reply|Sphilbrick}} I haven't read that book, but I see your point. I agree WP:PNT could use some work and can probably be simpler to follow. I would support a re-working of WP:PNT to solve the underlying issues and incorporate the use of Draft namespace (at whatever stage); I think that would be more productive than a new policy (which would only make WP:PNT harder to follow).
*::] (]) 07:31, 16 December 2024 (UTC)
::::The comments here suggest an emerging consensus that: (1) something needs to be done to prompt utilising the Draft namespace for articles in languages other than English that need attention before being re-admitted to article namespace; (2) a new policy is not necessary or desirable to achieve this; (3) WP:PNT should be re-worked to address this (amongst fixing the barn generally). Perhaps this should be workshopped on the ] talk page? <small>—''']''' ]</small> 21:27, 18 May 2015 (UTC)
*::Because several thousand people have RFA on their watchlist, and thousands more will see the "there's an open RFA" notice on theirs whether they follow it or not. Unlike BN, RFA is a process that depends on community input from a large number of people. In order to even ''realise that the RFA is not worth their time'', they have to:
*::* Read the opening statement and first few question answers (I just counted, HF's opening and first 5 answers are about 1000 words)
*'''Oppose''' per Beeblebrox and SPhilbrick. <span style="border:1px solid #900;padding:2px;background:#fffff4">] ]</span> 19:19, 18 May 2015 (UTC)
*::* Think, "oh, they're an an ex-admin, I wonder why they're going through RFA, what was their cloud"
*I feel I need to make another clarification here in regards to this counter-proposal, it will read a bit odd at first, but bear with me. WP:PNT is not a translation project (keep going): it is an article crisis-centre, along the lines of ], ], ] and more. Just like those pages we focus on a specific issue and we fix it however we can. There is a long-held consensus, re-affirmed just a few weeks ago, at PNT that draft articles do not fall within our scope of work, as they do not fall under many other "problem article" pages, to change that would be to swamp us with hundreds of pages that are simply not a problem for Misplaced Pages. ] is the translation project, it is there that editors specifically looking at translating articles (properly I mean, not just dropping non-English articles into the articlespace) --] ] 21:40, 18 May 2015 (UTC)
*::* Read through the comments and votes to see if any issues have been brought up (another ~1000 words)
::{{reply|Jac16888}} Thanks for the insight. Do you think this would work better if articles that have not received attention after the two-week period, and which otherwise do not obviously meet any deletion criteria, be moved to the Draft namespace then? Thus, all articles in foreign languages: (1) would be marked with a maintenance tag and listed at WP:PNT, as they are now; (2) after two weeks, would then moved to Draft namespace where someone could recover it in due course if they felt inclined; (3) could be deleted at any time just as with any article or draft subject to the deletion criteria. <small>—''']''' ]</small> 22:35, 18 May 2015 (UTC)
*::* None have
:::That could be done, but chances are that if after two weeks a page hasn't been translated by the creator or anybody else, it never will be.--] ] 23:02, 18 May 2015 (UTC)
*::* Realise your input is not necessary and this could have been done at BN
*'''Support''' I dont see the earlier proposal as clashing with this one, but oh well.] (]) 20:15, 19 May 2015 (UTC)
*::This process will be repeated by hundreds of editors over the course of a week. ] ] 08:07, 16 December 2024 (UTC)
*'''Oppose''' - first, there is already a process that works fine. If the good people who patrol ] felt there needed to be a new policy and their current routine wasn't working, I would defer to them. Instead this seems to me to be about an editor who randomly came across a page in Spanish and doesn't like that his decision to blank it kept getting reverted. Secondly, moving them to userspace decreases the likelihood that an editor who doesn't patrol WP:PNT will come across the article and help translate it. I strongly feel tagging the article with "please translate me if you can" is the best approach. ]<sup>]</sup> 😜 00:38, 22 May 2015 (UTC)
*:::That they were former admins has always been the first two sentences of their RfA’s statement, sentences which are immediately followed by that they resigned due to personal time commitment issues. You do not have to read the first 1000+ words to figure that out. If the reader wants to see if the candidate was lying in their statement, then they just have a quick skim through the oppose section. None of this should take more than 30 seconds in total. ] (]) 13:15, 16 December 2024 (UTC)
*'''Oppose, but do clarify''': Existing processes are working. User:Sphilbrick's note above about "Step -2", etc., indicates that extant procedure needs clarification, but that can be done without a proposal like this, simply by amending the PNT instructions. His "smartaleck" list (with adjusted numbering) is actually a good draft of what to use. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 15:05, 25 May 2015 (UTC)
*::::Not everyone can skim things easily - it personally takes me a while to read sections. I don't know if they're going to bury the lede and say something like "Also I made 10,000 insane redirects and then decided to take a break just before arbcom launched a case" in paragraph 6. Hog Farm's self nom had two paragraphs about disputes and it takes more than 30 seconds to unpick that and determine if that is a "cloud" or not. Even for reconfirmations, it definitely takes more than 30 seconds to determine a conclusion. ] ] 11:21, 17 December 2024 (UTC)
*:::::They said they resigned to personal time commitments. That is directly saying they wasn’t under a cloud, so I’ll believe them unless someone claims the contrary in the oppose section. If the disputes section contained a cloud, the oppose section would have said so. One chooses to examine such nominations like normal RfAs. ] (]) 18:47, 17 December 2024 (UTC)
== RfC: Should the holder of a political office be linked within an ] more than once (i.e. as the successor), when they have already been linked (e.g. as the vice president, predecessor, lieutenant, etc.)? ==
*::::::Just to double check, you're saying that whenever you go onto an RFA you expect any reason to oppose to already be listed by someone else, and no thought is required? I am begining to see how you are able to assess an RFA in under 30 seconds ] ] 23:08, 17 December 2024 (UTC)
*:::::::Something in their statement would be an incredibly obvious reason. We are talking about the assessment whether to examine and whether the candidate could've used BN. ] (]) 12:52, 18 December 2024 (UTC)
===Opening rationale and instructions===
*::@] let's not confuse "a lot of community time is spent" with "waste of time". Some people have characterized the re-RFAs as a waste of time but that's not the assertion I (and I think a majority of the skeptics) have been making. All RfAs use a lot of community time as hundreds of voters evaluate the candidate. They then choose to support, oppose, be neutral, or not vote at all. While editor time is not perfectly fixed - editors may choose to spend less time on non-Misplaced Pages activities at certain times - neither is it a resource we have in abundance anymore relative to our project. And so I think we, as a community, need to be thought about how we're using that time especially when the use of that time would have been spent on other wiki activities.Best, ] (]) 22:49, 16 December 2024 (UTC)
*:::Absolutely nothing compels anybody to spend any time evaluating an RFA. If you think your wiki time is better spent elsewhere than evaluating an RFA candidate, then spend it elsewhere. That way only those who do think it is a good use of their time will participate and everybody wins. You win by not spending your time on something that you don't think is worth it, those who do participate don't have ''their'' time wasted by having to read comments (that contradict explicit policy) about how the RFA is a waste of time. Personally I regard evaluating whether a long-time admin still has the approval of the community to be a very good use of community time, you are free to disagree, but please don't waste my time by forcing me to read comments about how you think I'm wasting my time. ] (]) 23:39, 16 December 2024 (UTC)
<small>some possible</small> Reasons to '''Support'''-
*::::I am not saying you or anyone else is wasting time and am surprised you are so fervently insisting I am. Best, ] (]) 03:34, 17 December 2024 (UTC)
*Ease of navigation
*:::::I don't understand how your argument that it is not a good use of community time is any different from arguing that it is a waste of time? ] (]) 09:08, 17 December 2024 (UTC)
*] (certain parts)
*'''Option 2''' I don't mind the re-RFAs, but I'd appreciate if we encouraged restoration via BN instead, I just object to making it mandatory. ] <sup>(]) </sup> 06:23, 16 December 2024 (UTC)
*Conformity with articles where this issue does not occur
*'''Option 2'''. Banning voluntary re-RfAs would be a step in the wrong direction on admin accountability. Same with SNOW closing. There is no more "wasting of community time" if we let the RfA run for the full seven days, but allowing someone to dig up a scandal on the seventh day is an important part of the RfA process. The only valid criticism I've heard is that folks who do this are arrogant, but banning arrogance, while noble, seems highly impractical. ] </span>]] 07:24, 16 December 2024 (UTC)
*], occasional exceptions to rules
*Option 3, 1, then 2, per HouseBlaster. Also agree with Daniel Quinlan. I think these sorts of RFA's should only be done in exceptional circumstances. ] (]) 08:46, 16 December 2024 (UTC)
<small>some possible</small> Reasons to '''Oppose'''-
* '''Option 1''' as first preference, option 3 second. RFAs use up a lot of time - hundreds of editors will read the RFA and it takes time to come to a conclusion. When that conclusion is "well that was pointless, my input wasn't needed", it is not a good system. I think transparency and accountability is a very good thing, and we need more of it for resyssopings, but that should come from improving the normal process (BN) rather than using a different one (RFA). My ideas for improving the BN route to make it more transparent and better at getting community input is outlined over on the ] ] 08:59, 16 December 2024 (UTC)
*] (spirit of the guideline) and that this issue is already covered there
* '''Option 2''', though I'd be for '''option 3''' too. I'm all for administrators who feel like they want/should go through an RfA to solicit feedback even if they've been given the tools back already. I see multiple people talk about going through BN, but if I had to hazard a guess, it's way less watched than RfA is. However I do feel like watchlist notifications should say something to the effect of "A request for re-adminship feedback is open for discussion" so that people that don't like these could ignore them. <span>♠] ]</span>♠ 09:13, 16 December 2024 (UTC)
*'''Option 2''' because ] is well-established policy. Read ], which says quite clearly, {{tpq|Regardless of the process by which the admin tools are removed, any editor is free to re-request the tools through the requests for adminship process.}} I went back 500 edits to 2017 and the wording was substantially the same back then. So, I simply do not understand why various editors are berating former administrators to the point of accusing them of wasting time and being arrogant for choosing to go through a process which is ''specifically permitted by policy''. It is bewildering to me. ] (]) 09:56, 16 December 2024 (UTC)
Having recently closed an ] '']'' at an ] regarding <s>this</s> a similar issue, I will not be expressing an opinion here (in the spirit of neutrality). I'm simply advocating '''consistency''', in the hope to unify the style that should be used when this occurs throughout the ]. <small>—]</small><sup>(]</sup><sub style="margin-left:-2.0ex;">])</sub> 05:23, 19 May 2015 (UTC)
*'''Option 2 & 3''' I think that there still should be the choice between BN and re-RFA for resysops, but I think that the re-RFA should stay like it is in Option 3, unless it is controversial, at which point it could be extended to the full RFA period. I feel like this would be the best compromise between not "wasting" community time (which I believe is a very overstated, yet understandable, point) and ensuring that the process is based on broad consensus and that our "representatives" are still supported. If I were WTT or Hog, I might choose to make the same decision so as to be respectful of the possibility of changing consensus. ] (]) | :) | he/him | 10:45, 16 December 2024 (UTC)
*'''Option 2''', for lack of a better choice. Banning re-RFAs is not a great idea, and we should not SNOW close a discussion that would give someone immunity from a certain degree of accountability. I've dropped an idea for an option 4 in the discussion section below. ] (]) 12:08, 16 December 2024 (UTC)
<br>
*'''Option 1''' I agree with Graham87 that these sorts of RFAs should only be done in exceptional circumstances, and BN is the best place to ask for tools back. – ] <small>(])</small> 12:11, 16 December 2024 (UTC)
*'''Option 2''' I don't think prohibition makes sense. It also has weird side effects. eg: some admins' voluntary recall policies may now be completely void, because they would be unable to follow them even if they wanted to, because policy prohibits them from doing a RFA. (maybe if they're also 'under a cloud' it'd fit into exemptions, but if an admins' policy is "3 editors on this named list tell me I'm unfit, I resign" then this isn't really a cloud.) {{pb}} Personally, I think Hog Farm's RFA was unwise, as he's textbook uncontroversial. Worm's was a decent RFA; he's also textbook uncontroversial but it happened at a good time. But any editor participating in these discussions to give the "support" does so using their own time. Everyone who feels their time is wasted can choose to ignore the discussion, and instead it'll pass as 10-0-0 instead of 198-2-4. It just doesn't make sense to prohibit someone from seeking a community discussion, though. For almost anything, really. ] (]) 12:33, 16 December 2024 (UTC)
"equal out the reasons.... ... fair" <small></small>
*'''Option 2''' It takes like two seconds to support or ignore an RFA you think is "useless"... can't understand the hullabaloo around them. I stand by what I said on ] regarding RFAs being about evaluating trustworthiness and accountability. Trustworthy people don't skip the process. —] <span title="Canadian!" style="color:red">🍁</span> (] · ]) 15:24, 16 December 2024 (UTC)
<br><small>some more possible</small> Reasons to '''Oppose'''-
*'''Option 1''' - Option 2 is a waste of community time. - ] (]) 15:30, 16 December 2024 (UTC)
*It looks less professional and more cluttered
*:Why? ] (]) 15:35, 16 December 2024 (UTC)
*Harder on the eyes to follow with continual alternating colors
*'''2''' is fine. '''Strong oppose''' to 1 and 3. Opposing option 1 because there is nothing wrong with asking for extra community feedback. opposing option 3 because once an RfA has been started, it should follow the standard rules. Note that RfAs are extremely rare and non-contentious RfAs require very little community time (unlike this RfC which seems a waste of community time, but there we are). —] (]) 16:59, 16 December 2024 (UTC)
*Multiple links in an infobox are simply unnecessary
*'''2''', with no opposition to 3. I see nothing wrong with a former administrator getting re-confirmed by the community, and community vetting seems like a good thing overall. If people think it's a waste of time, then just ignore the RfA. ] (]) 17:56, 16 December 2024 (UTC)
] (]) 23 May 2015 (UTC) <small>'''('''''Restored {{ping|Fyunck(click)}}'s here, as opposed to changing my opening post.''<small>—]</small><sup>(]</sup><sub style="margin-left:-2.0ex;">])</sub> 09:43, 23 May 2015 (UTC)''')'''</small>
*'''2''' Sure, and clarify that should such an RFA be unsuccessful they may only regain through a future rfa. — ] <sup>]</sup> 18:03, 16 December 2024 (UTC)
*'''Option 2''' If contributing to such an RFA is a waste of your time, just don't participate. ] (]) 18:43, 16 December 2024 (UTC)
===Support (names ''should'' be linked more than once)===
*:No individual is wasting their time participating. Instead the person asking for a re-rfa is ''using'' tons of editor time by asking hundreds of people to vet them. Even the choice not to participate requires at least some time to figure out that this is not a new RfA; though at least in the two we've had recently it would require only as long as it takes to get to the RfA - for many a click from the watchlist and then another click into the rfa page - and to read the first couple of sentences of the self-nomination which isn't terribly long all things considered. Best, ] (]) 22:55, 16 December 2024 (UTC)
#'''Strong support''' - any place where readers are likely to expect links, we should give them those links. While in prose text there are issues with some browsers (so I ubderstand, when it comes to browsers for the blind), these issues don't come up as much in infoboxes. And if someone wants to follow up, for example, on all Israeli prime ministers since 1990, they would expect a link to the next prime minister for the 1992-1995 term of ]. ] ] 13:06, 20 May 2015 (UTC)
*::I agree with you (I think) that it's a matter of perspective. For me, clicking the RFA link in my watchlist and reading the first paragraph of Hog Farm's nomination (where they explained that they were already a respected admin) took me about 10 seconds. Ten seconds is nothing; in my opinion, this is just a nonissue. But then again, I'm not an admin, checkuser, or an oversighter. Maybe the time to read such a nomination is really wasting their time. I don't know. ] (]) 23:15, 16 December 2024 (UTC)
#'''Support''' - WP:OVERLINK does exist for a reason, and it is best that we apply it where practical; however, we need to actually apply common sense before going to endless lengths to ensure that every last policy or guideline is met. ] ] 11:35, 21 May 2015 (UTC)
*:::I'm an admin and an oversighter (but not a checkuser). None of my time was wasted by either WTT or Hog Farm's nominations. ] (]) 23:30, 16 December 2024 (UTC)
#'''Support''' - ] says "Generally, a link should appear only once in an article, but if helpful for readers, a link may be repeated in infoboxes". That seems pretty explicit, so why is IAR listed under "some possible Reasons to Support"? There's no IAR necessary. Unlike an article, which has a top-to-bottom flow/narrative, infoboxes and tables are things people scan for particular information -- and we should have that information linked. To be clear, though, I don't think this requires additional language be added to any of the guidelines unless consensus ''opposes''. If supported it's just a reaffirmation of what ] already says. — <tt>] <sup style="font-size:80%;">]</sup></tt> \\ 14:53, 21 May 2015 (UTC)
*'''2'''. Maintain the ''status quo''. And stop worrying about a trivial non-problem. --] (]) 22:57, 16 December 2024 (UTC)
#'''Support''' I try to use common sense as well. While I hate overlinking (everyone knows what an rabbit is) I frequently relink when a lot of names are being used or when information is lenghty and/or difficult to understand, as in a medical article. I try to put myself in the place of a person that has no previous knowledge of the subject. ] (]) 15:13, 21 May 2015 (UTC)
*'''2'''. This reminds me of banning plastic straws (bear with me). Sure, I suppose in theory, that this is a burden on the community's time (just as straws do end up in landfills/the ocean). However, the amount of community time that is drained is minuscule compared to the amount of community time drained in countless, countless other fora and processes (just like the volume of plastic waste contributed by plastic straws is less than 0.001% of the total plastic waste). When WP becomes an efficient, well oiled machine, then maybe we can talk about saving community time by banning re-RFA's. But this is much ado about nothing, and indeed this plan to save people from themselves, and not allow them to simply decide whether to participate or not, is arguably more damaging than some re-RFAs (just as banning straws convinced some people that "these save-the-planet people are so ridiculous that I'm not going to bother listening to them about anything."). And, in fact, on a separate note, I'd actually love it if more admins just ran a re-RFA whenever they wanted. They would certainly get better feedback than just posting "What do my talk page watchers think?" on their own talk page. Or waiting until they get yelled at on their talk page, AN/ANI, AARV, etc. We say we want admins to respect feedback; does it '''have''' to be in a recall petition? --] (]) 23:44, 16 December 2024 (UTC)
#:This is a good point. Often in wiki table usage we relink things because to re-find the first linked instance isn't always easy when you want to click on it for more info. In prose it disrupts flow of reading. In an infobox some readers expect all names to be linked because they specifically use it to navigate. ] (]) 19:43, 21 May 2015 (UTC)
*:What meaningful feedback has Hog Farm gotten? "A minority of people think you choose poorly in choosing this process to regain adminship". What are they supposed to do with that? I share your desire for editors to share meaningful feedback with administrators. My own attempt yielded some, though mainly offwiki where I was told I was both too cautious and too impetuous (and despite the seeming contradiction each was valuable in its own way). So yes let's find ways to get meaningful feedback to admins outside of recall or being dragged to ANI. Unfortunately re-RfA seems to be poorly suited to the task and so we can likely find a better way. Best, ] (]) 03:38, 17 December 2024 (UTC)
#'''Support'''. I think it's useful there. I've used those links to navigate, and I know others have, too. And, as noted above, there's a clear exception in the overlink policy that supports useful links in infoboxes.--] (]) 15:58, 21 May 2015 (UTC)
*:Let us all take some comfort in the fact that no one has yet criticized this RfC comment as being a straw man argument. --] (]) 23:58, 18 December 2024 (UTC)
#'''Support'''. ] explicitly says links can be repeated in infoboxes. It benefits readers to have the links repeated there and it does not clutter the page like overlinking in the prose does. ] ]|] 16:05, 21 May 2015 (UTC)
*'''No hard rule, but we should socially discourage confirmation RfAs''' There is a difference between a hard rule, and a soft social rule. A hard rule against confirmation RfA's, like option 1, would not do a good job of accounting for edge cases and would thus be ultimately detrimental here. But a soft social rule against them would be beneficial. Unfortunately, that is not one of the options of this RfC. In short, a person should have a good reason to do a confirmation RfA. If you're going to stand up before the community and ask "do you trust me," that should be for a good reason. It shouldn't just be because you want the approval of your peers. (Let me be clear: I am not suggesting that is why either Worm or Hogfarm re-upped, I'm just trying to create a general purpose rule here.) That takes some introspection and humility to ask yourself: is it worth me inviting two or three hundred people to spend part of their lives to comment on me as a person?{{pb}}A lot of people have thrown around ] in their reasonings. Obviously, broad generalizations about it aren't convincing anyone. So let me just share my own experience. I saw the watchlist notice open that a new RfA was being run. I reacted with some excitement, because I always like seeing new admins. When I got to the page and saw Hogfarm's name, I immediately thought "isn't he already an admin?" I then assumed, ah, its just the classic RfA reaction at seeing a qualified candidate, so I'll probably support him since I already think he's an admin. But then as I started to do my due diligence and read, I saw that he really, truly, already had been an admin. At that point, my previous excitement turned to a certain unease. I had voted yes for Worm's confirmation RfA, but here was another...and I realized that my blind support for Worm might have been the start of an entirely new process. I then thought "bet there's an RfC going about this," and came here. I then spent a while polishing up my essay on editor time, before taking time to write this message. All in all, I probably spent a good hour doing this. Previously, I'd just been clicking the random article button and gnoming. So, the longwinded moral: yeah, this did eat up a lot of my editor time that could have and was being spent doing something else. And I'd do it again! It was important to do my research and to comment here. But in the future...maybe I won't react quite as excitedly to seeing that RfA notice. Maybe I'll feel a little pang of dread...wondering if its going to be a confirmation RfA. We can't pretend that confirmation RfA's are costless, and that we don't lose anything even if editors just ignore them. When run, it should be because they are necessary. ] <sup>]</sup>] 03:29, 17 December 2024 (UTC)
#'''Support''' The whole purpose of the infobox is to present material in a succinct manner. ] (]) 22:03, 21 May 2015 (UTC)
*:And for what its worth, support '''Option 3''' because I'm generally a fan of putting more tools in people's toolboxes. ] <sup>]</sup>] 03:36, 17 December 2024 (UTC)
#'''Support''' Of course it's helpful to repeat links, and we should do it. Not everybody reads articles top to bottom. Some just look at the infobox, some only read the text without the infobox, many only read a particular section (and we have links to sections all over the place), in some cases users might skip to the navboxes at the bottom. We should be accommodating all of these reading styles, and that means repeating links, sometimes 5 to 10 times in an article. ] (]) 22:13, 21 May 2015 (UTC)
*:{{tpq|In short, a person should have a good reason to do a confirmation RfA. If you're going to stand up before the community and ask "do you trust me," that should be for a good reason. It shouldn't just be because you want the approval of your peers.}} Asking the community whether you still have their trust to be an administrator, which is what an reconfirmation RFA is, ''is'' a good reason. I expect getting a near-unanimous "yes" is good for one's ego, but that's just a (nice) side-effect of the far more important benefits to the entire community: a trusted administrator.
#'''Support''' As a matter of common sense, it makes navigating Misplaced Pages easier for readers. ] is a policy designed to prevent linking to the same article multiple times within the body, which makes sense because if someone is reading through the page, they've already seen the available wikilink. However, when navigating through successive offices (or for that matter NFL seasons, NBA seasons, Artist singles, etc.) using the infobox, it is best to have everything linked for convenience. Yes, this means sometimes people who hold multiple offices will be linked more than once, but for the sake of sanity we should just link them all, if we have to go through each article and determine which ones to do de-link it will be a headache for editors and readers alike, and only serve to cause confusion. We have a hard enough time enforcing ] within the bodies of articles, let's not give ourselves extra work for no good reason. -] (]) 23:32, 21 May 2015 (UTC)
*:The time you claim is being eaten up unnecessarily by reconfirmation RFAs was actually taken up by you choosing to spend your time writing an essay about using time for things you don't approve of and then hunting out an RFC in which you wrote another short essay about using time on things you don't approve of. Absolutely none of that is a necessary consequence of reconfirmation RFAs - indeed the response consistent with your stated goals would have been to read the first two sentences of Hog Farm's RFA and then closed the tab and returned to whatever else it was you were doing. ] (]) 09:16, 17 December 2024 (UTC)
#'''Support''' per all the sound reasons listed above ]<sup>]</sup> 😜 00:40, 22 May 2015 (UTC)
*:WTT's and Hog Farm's RFAs would have been completely uncontentious, something I hope for at RfA and certainly the opposite of what I "dread" at RfA, if it were not for the people who attack the very concept of standing for RfA again despite policy being crystal clear that it is absolutely fine. I don't see how any blame for this situation can be put on WTT or HF. We can't pretend that dismissing uncontentious reconfirmation RfAs is costless; discouraging them removes one of the few remaining potentially wholesome bits about the process. —] (]) 09:53, 17 December 2024 (UTC)
#'''Support''' because it allows much more easy navigation and helps spread knowledge by making it easier to access. ] (]) 21:32, 22 May 2015 (UTC)
*:@] Would you find it better if Watchlist notices and similar said "(re?)confirmation RFA" instead of "RFA"? Say for all voluntary RFAs from an existing admin or someone who could have used BN?
#'''Support'''—it helps with navigation, and ] specifically says it can be repeated. <span style="background:#006B54; padding:2px;">'''] ]'''</span> 04:34, 23 May 2015 (UTC)
*:As a different point, I would be quite against any social discouraging if we're not making a hard rule as such. Social discouraging is what got us the opposes at WTT/Hog Farm's RFAs, which I found quite distasteful and badgering. If people disagree with a process, they should change it. But if the process remains the same, I think it's important to not enable RFA's toxicity by encouraging others to namecall or re-argue the process in each RRFA. It's a short road from social discouragement to toxicity, unfortunately. ] (]) 18:41, 19 December 2024 (UTC)
#'''Support''' (weakly, on a case-by-case basis). The reason for discouraging duplicate links in running text is that we expect readers to go through the text sequentially, so when they encounter the second instance of the name they will already have seen the first. But the tabulated format of an infobox is designed for non-sequential reading – you can use it for looking up just one piece of information at a time, in any order. A second set of arguments about using or avoiding link is that bluelinks in running text increase visual distraction – but if in a tabulated box you have all entries bluelinked, then the same kind of distraction may be created by having a single one among them ''not'' blue. ] ] 11:02, 23 May 2015 (UTC)
*::Yes I think the watchlist notice should specify what kind of RfA, especially with the introduction of recall. ] <sup>]</sup>] 16:49, 23 December 2024 (UTC)
#'''Support''' readers expect infobox items to be linked and probably think it is an error if it is not. I cant see why it would be seen as overlinking as that really deals with the article body. ] (]) 12:24, 23 May 2015 (UTC)
* '''Option 1'''. Will prevent the unnecessary drama trend we are seeing in the recent. – ] (]) 07:18, 17 December 2024 (UTC)
#'''Support''' Guidelines using the word "generally" are easily overruled by rational justification. The spirit of ] is to avoid clutter. Logical or expected links are not clutter. Easy and consistent navigation is a high value justification. ] (]) 04:40, 24 May 2015 (UTC)
* '''Option 2''' if people think there's a waste of community time, don't spend your time voting or discussing. Or add "reconfirmation" or similar to the watchlist notice. ] (]) 15:08, 17 December 2024 (UTC)
#'''Support''' I thought about this carefully and I think the benefits outweigh the cons. I looked at several other infoboxes that were fully linked and it wasn't any tougher visually if all the politicians are linked multiple times (as opposed to prose where it gets very annoying and where I wish the links were the same color as the surrounding text). It's more like a table where, in scrolling down, continual links can be helpful. I'm not 100% convinced we need every city councilperson's name linked many multiple times in an infobox, but I can't see it hurting anything either. The most important subjects should be linked multiple times, and if there is scrolling distance between the last link it may also be linked again. It absolutely can help readers navigate, especially if they are new to the subject, as this happened to myself recently on one of the presidential articles. I agree with {{ping|Rhododendrites}} that it doesn't go against MoS/Guidelines now so no need to re-write anything. This simply affirms the practice in infoboxes. ] (]) 23:45, 26 May 2015 (UTC)
* '''Option 3''' (which I think is a subset of option 2, so I'm okay with the status quo, but I want to endorse giving 'crats the option to SNOW). While they do come under scrutiny from time to time for the extensive dicsussions in the "maybe" zone following RfAs, this should be taken as an indiciation that they are unlikely to do something like close it as SNOW in the event there is <em>real and substantial</em> concerns being rasied. This is an okay tool to give the 'crats. As far as I can tell, no one has ever accused the them of moving too quickly in this direction (not criticism; love you all, keep up the good work). ] (]) 17:26, 17 December 2024 (UTC)
#'''Support''' per Alsee. We should be careful with putting links in the body text since too many there become distracting. However, navboxes and infoboxes are hotspots where links are expected. ] ] 07:12, 27 May 2015 (UTC)
* '''Option 3 or Option 2'''. Further, if Option 2 passes, I expect it also ends all the bickering about lost community time. A consensus explicitly in favour of "This is allowed" should also be a consensus to discourage relitigation of this RFC. ] (]) 17:35, 17 December 2024 (UTC)
*'''Option 2''': Admins who do not exude entitlement are to be praised. Those who criticize this humility should have a look in the mirror before accusing those who ask for reanointment from the community of "arrogance". I agree that it wouldn't be a bad idea to mention in parentheses that the RFA is a reconfirmation (watchlist) and wouldn't see any problem with crats snow-closing after, say, 96 hours. -- ] <sup>] · ]</sup> 18:48, 17 December 2024 (UTC)
===Oppose (names ''should not'' be linked more than once)===
*:I disagree that BN shouldn't be the normal route. RfA is already as hard and soul-crushing as it is. ] (]) 20:45, 17 December 2024 (UTC)
# '''Oppose''' - ] says {{tq|if helpful for readers, a link may be repeated in ]}}. We have to ask "is it helpful" to repeat this link and generally the answer is no. An infobox is supposed to summarise {{tq|key features of the page's subject}}. It is effectively the same as a single, listified section and we don't link multiple times in a section so why would we link multiple times in the infobox? It's unnecessary. --] (]) 07:55, 21 May 2015 (UTC)
*::Who are you disagreeing with? This RfC is about voluntary RRfA. -- ] <sup>] · ]</sup> 20:59, 17 December 2024 (UTC)
*:::I know. I see a sizable amount of commenters here starting to say that voluntary re-RfAs should be encouraged, and your first sentence can be easily read as implying that admins who use the BN route exude entitlement. I disagree with that (see my reply to Thryduulf below). ] (]) 12:56, 18 December 2024 (UTC)
#] oppose. -- ] 00:07, 22 May 2015 (UTC)
*::One way to improve the reputation of RFA is for there to be more RFAs that are not terrible, such as reconfirmations of admins who are doing/have done a good job who sail through with many positive comments. There is no proposal to make RFA mandatory in circumstances it currently isn't, only to reaffirm that those who voluntarily choose RFA are entitled to do so. ] (]) 21:06, 17 December 2024 (UTC)
#:Does that mean you support rewording the part of ] that says, "... but if helpful for readers, a link may be repeated in infoboxes, tables, image captions, footnotes, hatnotes, and at the first occurrence after the lead." because unless that wording is changed, then I don't see how ] can be used to oppose this RfC. -] (]) 05:20, 22 May 2015 (UTC)
*:::I know it's not a proposal, but there's enough people talking about this so far that it could become a proposal.<br />There's nearly nothing in between that could've lost the trust of the community. I'm sure there are many who do not want to be pressured into ] without good reason. ] (]) 12:57, 18 December 2024 (UTC)
#::Obviously, because its not "helpful for readers" as AussieLegend already said. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 09:33, 24 May 2015 (UTC)
*::::Absolutely nobody is proposing, suggesting or hinting here that reconfirmation RFAs should become mandatory - other than comments from a few people who oppose the idea of people voluntarily choosing to do something policy explicitly allows them to choose to do. The best way to avoid people being pressured into being accused of arrogance for seeking reconfirmation of their status from the community is to sanction those people who accuse people of arrogance in such circumstances as such comments are in flagrant breach of AGF and NPA. ] (]) 14:56, 18 December 2024 (UTC)
#:::I don't see how navigational links inside an infobox, even if repeated aren't helpful for readers. It's not a distraction, as it's not a body of text being linked, and if you went to any other website on the web, they would keep this kind of linking consistent because it's what is ''obviously'' easier for readers. Especially for infoboxes in succession, there is no way it isn't helpful. Just my opinion though. -] (]) 23:35, 26 May 2015 (UTC)
*:::::Yes, I’m saying that they should not become preferred. There should be no social pressure to do RfA instead of BN, only pressure intrinsic to the candidate. ] (]) 15:37, 18 December 2024 (UTC)
#'''Oppose''' per ]/]. It isn't "helpful for readers" to repeat links in a back-to-back or nearly back-to-back way (and not just in infoboxes; it's a general principle). ] application of "helpful for readers" tells us that in very long infoboxes, where the recurrence of the name is widely separated from its initial occurrence, it's okay to relink. Many of the support !votes are effectively making the case that it's somehow always useful for readers if we repeatedly link these names in infoboxes, but that {{em|cannot possibly}} be true or the "{{tq|if helpful for readers, a link may be repeated in ]...}}" wording would not exist! QED. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 09:33, 24 May 2015 (UTC)
*::::::Whether they should become preferred in any situation forms no part of this proposal in any way shape or form - this seeks only to reaffirm that they are permitted. A separate suggestion, completely independent of this one, is to encourage (explicitly not mandate) them in some (but explicitly not all) situations. All discussions on this topic would benefit if people stopped misrepresenting the policies and proposals - especially when the falsehoods have been explicitly called out. ] (]) 15:49, 18 December 2024 (UTC)
#:Twice in the same infobox doesn't mean back-to-back. To take the infobox of ], for example, I can certainly see that there is no need, for the second term as prime minister (84-86), to link to Yitzhak Shamir in both the precceding and the successing. On the other hand, if someone wants to follow the succeding link for the first-listed (most recent) term as Minister of Foreign Affairs, no reason to make the reader have to go all the way up to the prime misinter section to find the same name there, nor to te presedent section to find the second prime minister listed there. (Benjamin Netanyahu). ] ] 13:51, 26 May 2015 (UTC)
*:::::::I am talking and worrying over that separate proposal many here are suggesting. I don’t intend to oppose Option 2, and sorry if I came off that way. ] (]) 16:29, 18 December 2024 (UTC)
#::Sure. You seem to be restating what I said, in detail, just in different wording and with examples. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 00:26, 28 May 2015 (UTC)
*'''Option 2'''. In fact, I'm inclined to ''encourage'' an RRfA over BN, because nothing requires editors to participate in an RRfA, but the resulting discussion is better for reaffirming community consensus for the former admin or otherwise providing helpful feedback. --] (]) 21:45, 17 December 2024 (UTC)
#'''Oppose''' I agree per SMcCandlish. ] (]) 14:05, 26 May 2015 (UTC)
*'''Option 2''' ] has said "{{tq|Former administrators may seek reinstatement of their privileges through RfA...}}" for over ten years and this is not a problem. I liked the opportunity to be consulted in the current RfA and don't consider this a waste of time. ]🐉(]) 22:14, 17 December 2024 (UTC)
*'''Option 2'''. People who think it’s not a good use of their time always have the option to scroll past. ] (]) 01:41, 18 December 2024 (UTC)
===Neutral===
* '''2''' - If an administrator gives up sysop access because they plan to be inactive for a while and want to minimize the attack surface of Misplaced Pages, they should be able to ask for permissions back the quickest way possible. If an administrator resigns because they do not intend to do the job anymore, and later changes their mind, they should request a community discussion. The right course of action depends on the situation. ] <sup>]</sup> 14:00, 18 December 2024 (UTC)
# Policy and guidelines on this already make it clear that multiple links ''can'' be used where appropriate. We do not not need a "should" or "shouldn't" policy over and above what we already have. All the best: ''] ]'', <small>11:42, 23 May 2015 (UTC).</small><br />
*'''Option 1'''. I've watched a lot of RFAs and re-RFAs over the years. There's a darn good reason why the community developed the "go to BN" option: saves time, is straightforward, and if there are issues that point to a re-RFA, they're quickly surfaced. People who refuse to take the community-developed process of going to BN first are basically telling the community that they need the community's full attention on their quest to re-admin. Yes, there are those who may be directed to re-RFA by the bureaucrats, in which case, they have followed the community's carefully crafted process, and their re-RFA should be evaluated from that perspective. ] (]) 02:34, 19 December 2024 (UTC)
:::My reasoning behind this RfC was to try and make the linkage of officeholders within the ] consistent throughout its use in the encyclopedia. This can differ with no guideline ''specific'' to the matter at hand. Unifying the linkage of names whichever way the ] of this RfC falls, would be better than it being determined by consensus on a per article basis. We already do this, one such example being guidelines for specific types of articles, such as the ]. The need is there, if we want to be homogenize the usage, and I think this is one case where that would be sensible. <small>—]</small><sup>(]</sup><sub style="margin-left:-2.0ex;">])</sub> 17:38, 28 May 2015 (UTC)
*'''Option 2'''. If people want to choose to go through an RFA, who are we to stop them? ] (]) 10:25, 19 December 2024 (UTC)
*'''Option 2''' (status quo/no changes) per ]. This is bureaucratic rulemongering at its finest. Every time RFA reform comes up some editors want admins to be required to periodically reconfirm, then when some admins decide to reconfirm voluntarily, suddenly that's seen as a bad thing. The correct thing to do here is nothing. If you don't like voluntary reconfirmation RFAs, you are not required to participate in them. ] (<sup>]</sup>/<sub>]</sub>) 19:34, 19 December 2024 (UTC)
*'''Option 2''' I would probably counsel just going to BN most of the time, however there are exceptions and edge cases. To this point these RfAs have been few in number, so the costs incurred are relatively minor. If the number becomes large then it might be worth revisiting, but I don't see that as likely. Some people will probably impose social costs on those who start them by opposing these RfAs, with the usual result, but that doesn't really change the overall analysis. Perhaps it would be better if our idiosyncratic internal logic didn't produce such outcomes, but that's a separate issue and frankly not really worth fighting over either. There's probably some meta issues here I'm unaware off, it's long since I've had my finger on the community pulse so to speak, but they tend to matter far less than people think they do. ] (]) 02:28, 20 December 2024 (UTC)
* '''Option 1''', per ], ], ], ], and related principles. We all have far better things to do that read through and argue in/about a totally unnecessary RfA invoked as a "Show me some love!" abuse of process and waste of community time and productivity. I could live with option 3, if option 1 doesn't fly (i.e. shut these silly things down as quickly as possible). But option 2 is just out of the question. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 04:28, 22 December 2024 (UTC)
*:Except none of the re-RFAs complained about have been {{tpq|RfA invoked as a "Show me some love!" abuse of process}}, you're arguing against a strawman. ] (]) 11:41, 22 December 2024 (UTC)
*::It's entirely a matter of opinion and perception, or A) this RfC wouldn't exist, and B) various of your fellow admins like TonyBallioni would not have come to the same conclusion I have. Whether the underlying intent (which no one can determine, lacking as we do any magical mind-reading powers) is solely egotistical is ultimately irrelevant. The {{em|actual effect}} (what matters) of doing this whether for attention, or because you've somehow confused yourself into think it needs to be done, is precisely the same: a showy waste of community volunteers' time with no result other than a bunch of attention being drawn to a particular editor and their deeds, without any actual need for the community to engage in a lengthy formal process to re-examine them. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 05:49, 23 December 2024 (UTC)
*:::{{tqb|or because you've somehow confused yourself into think it needs to be done}} I and many others here agree and stand behind the very reasoning that has "confused" such candidates, at least for WTT. ] (]) 15:37, 23 December 2024 (UTC)
*'''Option 2'''. I see no legitimate reason why we should be changing the status quo. Sure, some former admins might find it easier to go through BN, and it might save community time, and most former admins ''already'' choose the easier option. However, if a candidate last ran for adminship several years ago, or if issues were raised during their tenure as admin, then it may be helpful for them to ask for community feedback, anyway. There is no "wasted" community time in such a case. I really don't get the claims that this violates ], because it really doesn't apply when a former admin last ran for adminship 10 or 20 years ago or wants to know if they still have community trust.{{pb}}On the other hand, if an editor thinks a re-RFA is a waste of community time, they can simply choose not to participate in that RFA. Opposing individual candidates' re-RFAs based solely on opposition to re-RFAs in general ''is'' a violation of ]. – ] (]) 14:46, 22 December 2024 (UTC)
*:But this isn't the status quo? We've never done a re-RfA before now. The question is whether this previously unconsidered process, which appeared as an ], is a feature or a bug. ] <sup>]</sup>] 23:01, 22 December 2024 (UTC)
*::There have been lots of re-RFAs, historically. There were more common in the 2000s. ] in 2003 is the earliest I can find, back before the re-sysopping system had been worked out fully. ] back in 2007 was snow-closed after one day, because the nominator and applicant didn't know that they could have gone to the bureaucrats' noticeboard. For more modern examples, ] (2011) is relatively similar to the recent re-RFAs in the sense that the admin resigned uncontroversially but chose to re-RFA before getting the tools back. Immediately following and inspired by HJ Mitchell's, there was the slightly more controversial ]. That ended successful re-RFAS until 2019's ], which crat-chatted. Since then, there have been none that I remember. There have been several re-RFAs from admins who were de-sysopped or at serious risk of de-sysopping, and a few interesting edge cases such as the yet no-consensus ] in 2014 and the ] case in 2015, but those are very different than what we're talking about today. ] (]) 00:01, 23 December 2024 (UTC)
*:::To add on to that, ] was technically a reconfirmation RFA, which in a sense can be treated as a re-RFA. My point is, there is some precedent for re-RFAs, but the current guidelines are ambiguous as to when re-RFAs are or aren't allowed. – ] (]) 16:34, 23 December 2024 (UTC)
*::::Well thank you both, I've learned something new today. It turns out I was working on a false assumption. It has just been so long since a re-RfA that I assumed it was a truly new phenomenon, especially since there were two in short succession. I still can't say I'm thrilled by the process and think it should be used sparingly, but perhaps I was a bit over concerned. ] <sup>]</sup>] 16:47, 23 December 2024 (UTC)
*'''Option 2 or 3''' per Gnoming and CaptainEek. Such RfAs only require at most 30 seconds for one to decide whether or not to spend their time on examination. Unlike other prohibited timesinks, it's not like something undesirable will happen if one does not sink their time. Voluntary reconfirmation RfAs are socially discouraged, so there is usually a very good reason for someone to go back there, such as accountability for past statements in the case of WTT or large disputes during adminship in the case of Hog Farm. I don't think we should outright deny these, and there is no disruption incurred if we don't. ] (]) 15:44, 23 December 2024 (UTC)
*'''Option 2''' but for largely the reasons presented by CaptainEek. ''']''' (<small>aka</small> ] '''·''' ] '''·''' ]) 21:58, 23 December 2024 (UTC)
*'''Option 2 (fine with better labeling)''' These don't seem harmful to me and, if I don't have time, I'll skip one and trust the judgment of my fellow editors. No objection to better labeling them though, as discussed above. ] (]) 22:36, 23 December 2024 (UTC)
*'''Option 1''' because it's just a waste of time to go through and !vote on candidates who just want the mop restored when he or she or they could get it restored BN with no problems. But I can also see option 2 being good for a former mod not in good standing. ] (]) 23:05, 23 December 2024 (UTC)
*:If you think it is a waste of time to !vote on a candidate, just don't vote on that candidate and none of your time has been wasted. ] (]) 23:28, 23 December 2024 (UTC)
*'''Option 2''' per QoH (or me? who knows...) ] • ] • ] 04:24, 27 December 2024 (UTC)
*'''Option 2''' Just because someone may be entitled to get the bit back doesn't mean they necessarily should. Look at ]. I did not resign under a cloud, so I could have gotten the bit back by request. However, the RFA established that I did not have the community support at that point, so it was a good thing that I chose that path. I don't particularly support option 3, but I could deal with it. --] 16:05, 27 December 2024 (UTC)
*'''Option 1''' Asking hundreds of people to vet a candidate who has already passed a RfA and is eligible to get the tools back at BN is a waste of the community's time. -- ] (]) 16:21, 27 December 2024 (UTC)
*'''Option 2''' Abolishing RFA in favour of BN may need to be considered, but I am unconvinced by arguments about RFA being a waste of time. ] ] 19:21, 27 December 2024 (UTC)
*'''Option 2''' I really don't think there's a problem that needs to be fixed here. I am grateful at least a couple administrators have asked for the support of the community recently. ] ''<span style="font-size:small; vertical-align:top;">]</span>''·''<span style="font-size:small; vertical-align:bottom;">]</span>'' 00:12, 29 December 2024 (UTC)
*'''Option 2'''. Keep the status quo of {{tq|any editor is free to re-request the tools through the requests for adminship process}}. Voluntary RfA are rare enough not to be a problem, it's not as though we are overburdened with RfAs. And it’s my time to waste. --] (]) 17:58, 7 January 2025 (UTC)
* '''Option 2 or Option 3'''. These are unlikely to happen anyway, it's not like they're going to become a trend. I'm already wasting my time here instead of other more important activities anyway, so what's a little more time spent giving an easy support?{{pb
}}<span style="border-radius:9em;padding:0 7px;background:#000000">] ]</span> 16:39, 10 January 2025 (UTC)
===Discussion===
===Discussion===
*{{re|Voorts}} If option 2 gets consensus how would this RfC change the wording {{tqq|Regardless of the process by which the admin tools are removed, any editor is free to re-request the tools through the requests for adminship process.}} Or is this an attempt to see if that option no longer has consensus? If so why wasn't alternative wording proposed? As I noted above this feels premature in multiple ways. Best, ] (]) 21:43, 15 December 2024 (UTC)
*'''Comment''' - This is not exactly the same topic that was closed recently at ]. That was specifically about the President of the United States and the problems it creates (especially for children) when the "Preceded by" and "Succeeded by" are not linked. Every other President of the United States was linked for easy access ''EXCEPT'' for Franklin Roosevelt. Truman was the third vice-President so it was not instantly apparent where to click for Truman. And when a youngster is doing a report we want them to have easy access to information, especially for the highest office in the United States. Being able to click from infobox to infobox was very helpful. Of course the result was a snowball to make it consistent with all other US Presidents and because of the importance of the office.
*:That is not actually true. ArbCom can (and has) forbidden some editors from re-requesting the tools through RFA. ] ] 19:21, 27 December 2024 (UTC)
*I've re-opened this per ] on my talk page. If other editors think this is premature, they can !vote accordingly and an uninvolved closer can determine if there's consensus for an early close in deference to the VPI discussion. ] (]/]) 21:53, 15 December 2024 (UTC)
*:The discussion at VPI, which I have replied on, seems to me to be different enough from this discussion that both can run concurrently. That is, however, my opinion as a mere editor. — ] ⚓ ] 22:01, 15 December 2024 (UTC)
*:@], can you please reword the RfC to make it clear that Option 2 is the current consensus version? It does not need to be clarified – it already says precisely what you propose. – ] 22:02, 15 December 2024 (UTC)
*::{{done}} ] (]/]) 22:07, 15 December 2024 (UTC)
*'''Question''': May someone clarify why many view such confirmation RfAs as a waste of community time? No editor is obligated to take up their time and participate. If there's nothing to discuss, then there's no friction or dis-cussing, and the RfA smooth-sails; if a problem is identified, then there was a good reason to go to RfA. I'm sure I'm missing something here. ] (]) 22:35, 15 December 2024 (UTC)
*: The intent of RfA is to provide a comprehensive review of a candidate for adminship, to make sure that they meet the community's standards. Is that happening with vanity re-RfAs? Absolutely not, because these people don't need that level of vetting. I wouldn't consider a week long, publicly advertized back patting to be a productive use of volunteer time. -- ] (]) 23:33, 15 December 2024 (UTC)
*::But no volunteer is obligated to pat such candidates on the back. ] (]) 00:33, 16 December 2024 (UTC)
*::: Sure, but that logic could be used to justify any time sink. We're all volunteers and nobody is forced to do anything here, but that doesn't mean that we should promote (or stay silent with our criticism of, I suppose) things that we feel don't serve a useful purpose. I don't think this is a huge deal myself, but we've got two in a short period of time and I'd prefer to do a bit of push back now before they get more common. -- ] (]) 01:52, 16 December 2024 (UTC)
*::::Unlike other prohibited timesinks, it's not like something undesirable will happen if one does not sink their time. ] (]) 02:31, 16 December 2024 (UTC)
*:::::Except someone who has no need for advanced tools and is not going to use them in any useful fashion, would then skate through with nary a word said about their unsuitability, regardless of the foregone conclusion. The point of RFA is not to rubber-stamp. Unless their is some actual issue or genuine concern they might not get their tools back, they should just re-request them at BN and stop wasting people's time with pointless non-process wonkery. ] (]) 09:05, 16 December 2024 (UTC)
*::::::I’m confused. Adminship requires continued use of the tools. If you think they’s suitable for BN, I don’t see how doing an RfA suddenly makes them unsuitable. If you have concerns, raise them. ] (]) 13:02, 16 December 2024 (UTC)
*I don't think the suggested problem (which I acknowledge not everyone thinks is a problem) is resolved by these options. Admins can still run a re-confirmation RfA after regaining adminsitrative privileges, or even initiate a recall petition. I think as ], we want to encourage former admins who are unsure if they continue to be trusted by the community at a sufficient level to explore lower cost ways of determining this. ] (]) 00:32, 16 December 2024 (UTC)
*:Regarding option 3, ]. The intent of having a reconfirmation request for administrative privileges is counteracted by closing it swiftly. It provides incentive for rapid voting that may not provide the desired considered feedback. ] (]) 17:44, 17 December 2024 (UTC)
* In re the idea that RfAs use up a lot of community time: I first started editing Misplaced Pages in 2014. There were 62 RfAs that year, which was a historic low. Even counting all of the AElect candidates as separate RfAs, including those withdrawn before voting began, we're still up to only 53 in 2024 – counting only traditional RfAs it's only 18, which is the second lowest number ever. By my count we've has 8 resysop requests at BN in 2024; even if all of those went to RfA, I don't see how that would overwhelm the community. That would still leave us on 26 traditional RfAs per year, or (assuming all of them run the full week) one every other week. ] (]) 10:26, 16 December 2024 (UTC)
* What about an option 4 encouraging eligible candidates to go through BN? At the end of the ], add something like "Eligible users are encouraged to use this method rather than running a new request for adminship." The current wording makes re-RfAing sound like a plausible alternative to a BN request, when in actual fact the former rarely happens and always generates criticism. ] (]) 12:08, 16 December 2024 (UTC)
*:Discouraging RFAs is the second last thing we should be doing (after prohibiting them), rather per my comments here and in the VPI discussion we should be ''encouraging'' former administrators to demonstrate that they still have the approval of the community. ] (]) 12:16, 16 December 2024 (UTC)
*:I think this is a good idea if people do decide to go with option 2, if only to stave off any further mixed messages that people are doing something wrong or rude or time-wasting or whatever by doing a second RfA, when it's explicitly mentioned as a valid thing for them to do. ] (]) 15:04, 16 December 2024 (UTC)
*::If RFA is explicitly a valid thing for people to do (which it is, and is being reaffirmed by the growing consensus for option 2) then we don't need to (and shouldn't) discourage people from using that option. The mixed messages can be staved off by people simply not making comments that explicitly contradict policy. ] (]) 15:30, 16 December 2024 (UTC)
*:::Also a solid option, the question is whether people will actually do it. ] (]) 22:55, 16 December 2024 (UTC)
*::::The simplest way would be to just quickly hat/remove all such comments. Pretty soon people will stop making them. ] (]) 23:20, 16 December 2024 (UTC)
* This is not new. We've had sporadic "vanity" RfAs since the early days of the process. I don't believe they're particularly harmful, and think that it unlikely that we will begin to see so many of them that they pose a problem. As such I don't think this policy proposal ]. ''']]''' 21:56, 16 December 2024 (UTC)
* This apparent negative feeling evoked at an RFA for a former sysop ''everyone agrees is fully qualified and trusted'' certainly will put a bad taste in the mouths of other former admins who might consider a reconfirmation RFA ''without first'' visiting BN. This comes in the wake of Worm That Turned's similar rerun. ] (]) 23:29, 16 December 2024 (UTC)
*:Nobody should ever be discouraged from seeking community consensus for significant changes. Adminship is a significant change. ] (]) 23:32, 16 December 2024 (UTC)
*::No argument from me. I was a big Hog Farm backer way back when he was ''merely'' one of Misplaced Pages's best content contributors. ] (]) 12:10, 17 December 2024 (UTC)
*All these mentions of editor time make me have to mention ] (TLDR: our understanding of how editor time works is dreadfully incomplete). ] <sup>]</sup>] 02:44, 17 December 2024 (UTC)
*:I went looking for @]'s comment because I know they had hung up the tools and came back, and I was interested in their perspective. But they've given me a different epiphany. I suddenly realize why people are doing confirmation RfAs: it's because of RECALL, and the one year immunity a successful RfA gives you. Maybe everyone else already figured that one out and is thinking "well duh Eek," but I guess I hadn't :) I'm not exactly sure what to do with that epiphany, besides note the emergent behavior that policy change can create. We managed to generate an entirely new process without writing a single word about it, and that's honestly impressive :P ] <sup>]</sup>] 18:18, 17 December 2024 (UTC)
*::Worm That Turned followed through on a pledge he made in January 2024, before the 2024 review of the request for adminship process began. I don't think a pattern can be extrapolated from a sample size of one (or even two). That being said, it's probably a good thing if admins occasionally take stock of whether or not they continue to hold the trust of the community. As I previously commented, it would be great if these admins would use a lower cost way of sampling the community's opinion. ] (]) 18:31, 17 December 2024 (UTC)
*:::{{ping|CaptainEek}} You are correct that a year's "immunity" results from a successful RRFA, but I see no evidence that this has been the ''reason'' for the RRFAs. Regards, ] (]) 00:14, 22 December 2024 (UTC)
*::::If people decide to go through a community vote to get a one year immunity from a process that only might lead to a community vote which would then have a lower threshold then the one they decide to go through, and also give a year's immunity, then good for them. ] (]) 01:05, 22 December 2024 (UTC)
*::@] I'm mildly bothered by this comment, mildly because I assume it's lighthearted and non-serious. But just in case anyone does feel this way - I was very clear about my reasons for RRFA, I've written a lot about it, anyone is welcome to use my personal recall process without prejudice, and just to be super clear - I waive my "1 year immunity" - if someone wants to start a petition in the next year, do not use my RRfA as a reason not to. I'll update my userpage accordingly. I can't speak for Hog Farm, but his reasoning seems similar to mine, and immunity isn't it. ]<sup>TT</sup>(]) 10:28, 23 December 2024 (UTC)
*:::@] my quickly written comment was perhaps not as clear as it could have been :) I'm sorry, I didn't mean to suggest that y'all had run for dubious reasons. As I said in my !vote, {{tq|Let me be clear: I am not suggesting that is why either Worm or Hogfarm re-upped, I'm just trying to create a general purpose rule here}}. I guess what I really meant was that the reason that we're having this somewhat spirited conversation seems to be the sense that re-RfA could provide a protection from recall. If not for recall and the one year immunity period, I doubt we'd have cared so much as to suddenly run two discussions about this. ] <sup>]</sup>] 16:59, 23 December 2024 (UTC)
*::::I don't agree. No one else has raised a concern about someone seeking a one-year respite from a recall petition. Personally, I think essentially self-initiating the recall process doesn't really fit the profile of someone who wants to avoid the recall process. (I could invent some nefarious hypothetical situation, but since opening an arbitration case is still a possibility, I don't think it would work out as planned.) ] (]) 05:19, 24 December 2024 (UTC)
*::I really don't think this is the reason behind WTT's and HF's reconfirmation RFA's. I don't think their RFA's had much utility and could have been avoided, but I don't doubt for a second that their motivations were anything other than trying to provide transparency and accountability for the community. ] ] 12:04, 23 December 2024 (UTC)
*I don't really care enough about reconf RFAs to think they should be restricted, but what about a lighter ORCP-like process (maybe even in the same place) where fewer editors can indicate, "yeah OK, there aren't really any concerns here, it would probably save a bit of time if you just asked at BN". ] (] • ]) 12:40, 19 December 2024 (UTC)
== Is the "above 8000 words = split" an absolute rule? ==
:Now whether that should hold true for every other political office/elected official (that would include elected judges/mayors/councilpersons/school board members/etc) I do have my doubts. We've established it for US Presidents, but I'd like to read some viewpoints here on whether that should also apply to every political office. Maybe overlinking shouldn't apply to infoboxes since they are a helpful summary of the most important items of an article? Then again, unless it's as important as potus, why do we really need it linked over and over? Food for thought and I'll be reading some posts before deciding whether to expand things or not. ] (]) 07:13, 21 May 2015 (UTC)
I am referring to this chart found on ]:
::I didn't mean to imply that it was the same issue in my opening statement, merely that it was related. I changed my wording there to be more clear. <small>—]</small><sup>(]</sup><sub style="margin-left:-2.0ex;">])</sub> 07:18, 21 May 2015 (UTC)
*Why is this specific to political offices? There are plethora other templates that link to names. For example, where a TV show uses {{tl|infobox television}}, it is common that the same person may be listed in multiple roles (e.g., in '']'', Louie CK is listed as the creator, writer, director, and star) but only linked in the infobox the first time. Whether it is convenient to do this may depend on how the infobox is built (e.g., whether links are inserted automatically and not easily overridden) and how they appear (e.g., whether the references to the same person appear close together), but what is the reason to treat political offices as a special case and could/should this have a broader application. <small>—''']''' ]</small> 14:36, 21 May 2015 (UTC)
|-
! Word count
! scope="col" | What to do
|-
| > 15,000 words || Almost certainly should be divided or trimmed.
|-
| > 9,000 words || Probably should be divided or trimmed, though the scope of a topic can sometimes justify the added reading material.
|-
| > 8,000 words || May need to be divided or trimmed; likelihood goes up with size.
|-
| < 6,000 words || Length alone does not justify division or trimming.
|-
| < 150 words || If an article or list has remained this size for over two months, consider merging it with a related article.<br /> Alternatively, the article could be expanded; see ].
|}
I have seen a few instances where, an editor will raise the issue that an article is too large at, say, 7500 words or 8100 words. We have multiple history pages (and medical/psychology pages) with well over 11,000+ words, even some with over 16000. Where does one draw the line? It seems like Misplaced Pages leaves it to the discretion of the editor after about 8000 words. ] (]) 07:21, 18 December 2024 (UTC)
::There is ] in political offices. For example a user may want to browse through all the ] in order, from the ] to the ]. It could be argued that it would be convenient to have all the successors linked, even if they happened to serve as the previous administration's ] for ease of navigation. The same cannot be said about the benefit of linking other non-ordered things, such as in your example. That's why I specified the proposal in the way that I did. <small>—]</small><sup>(]</sup><sub style="margin-left:-2.0ex;">])</sub> 15:19, 21 May 2015 (UTC)
:Looking at the table, it's obvious that "above 8000 words=Split" is not "an absolute rule". I promise you that if it were, that table would say something that sounded remarkably like "if the article is above 8,000 words, then it absolutely must be split".
{{collapse top|unrelated to this rfc}}
:Additionally, we have ].
:::What about, for example, {{tl|infobox flag}}, which links the words "]" and "]" for every flag when multiple flags are listed, such as ]? Should that be treated any differently? <small>—''']''' ]</small> 22:50, 24 May 2015 (UTC)
:Where one draws the line is: In a place that makes sense for the topic of that specific article, having thoughtfully considered all the facts and circumstances that apply to that unique article. ] (]) 07:41, 18 December 2024 (UTC)
:There was a lengthy discussion at ] about the size guidance, for the record. Splitting pages is a lot of work and not everyone thinks that spreading stuff over multiple pages is better for readers than having in one big page. ] (]) 08:19, 18 December 2024 (UTC)
::In addition to the above, what matters for the technical aspects of article size is not the number of words but the number of bytes. Word count can only ever be an approximation of that as the length of the words used matters ("a" is 1 byte, "comprehensive" is 13), the number and size of included media matters very significantly more. ] (]) 09:20, 18 December 2024 (UTC)
:::I think ] is a bigger technical challenge for long articles. The more templates, and the more complicated templates, the more likely you are to need to split for technical reasons. ] needs a split in part due to PEIS reasons. ] (]) 18:43, 18 December 2024 (UTC)
:What's more, there's nothing even in the excerpt here that would purport an absolute guideline. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 09:44, 18 December 2024 (UTC)
::It isn't an absolute rule, but ''usually'' an article having an extremely long high word count is evidence of a bigger problem with ] -- that it's too dense or detailed for a reader to use it as a first-port-of-call summary. As such, ''usually'', it's a wise move to create daughter articles for the detailed material, and strim it down to its essentials in the main article; this improves the readability of the main article and allows interested readers to follow up into the nitty-gritty. As {{u|Jo-Jo Eumerus}} rightly says above, though, there's not really such thing as an absolute rule in this place. '']'' <sup>]·]</sup> 09:59, 18 December 2024 (UTC)
:::What we now know is that many readers are looking for specific information, with few reading from top to bottom, but the search engines send them to the mother article even when a more specific daughter article exists. So the first port of call needs to be the most highly detailed. The advice in ] is therefore considered well intentioned but obsolete; stripping the mother article and pushing information down to the daughter articles defeats our whole purpose in providing information. ] ] 11:31, 22 December 2024 (UTC)
::::When you say “we know…”, “is considered” and similar, are you pointing to specific previous discussions, RfCs etc on this matter? “In the wild”, as it were, I still see these size limits regularly invoked, even if the conversation rarely ends at them. '']'' <sup>]·]</sup> 09:17, 23 December 2024 (UTC)
: Rather than draw a line, I'd rather just remove that chart. Can't imagine why a suite of concrete word counts and procedures would ever be very helpful. — <samp>] <sup style="font-size:80%;">]</sup></samp> \\ 16:29, 18 December 2024 (UTC)
::It absolutely makes sense to say at what page sizes that editors should start considering other options, as well as where splitting can be absolutely unnecessary. Nothing wrong with the table as long as it's clear those aren't hard or fast rules. ] (]) 16:41, 18 December 2024 (UTC)
:::Agreed, I find it helpful because it helps me remember what is generally too long for mobile users (I understand that mobile is generally a blindspot for us as editors because the vast majority of us don't edit on mobile but most of the readers are actually on mobile) ] (]) 16:49, 18 December 2024 (UTC)
::::I also believe that the chart is helpful. ] (]) 17:29, 18 December 2024 (UTC)
:There don't seem to be any absolute rules laid out there... Even "Almost certainly" is qualified not an absolute rule. ] (]) 16:38, 18 December 2024 (UTC)
*The optimal article size varies quite a lot, actually. Key things we need to consider include:
*:The likely readership. Someone who's looking up ] probably has time to read something long and thoughtful. Someone who's looking up ] might need basic facts, in simple words, very fast.
*:The cognitive load associated with the topic. ] is (very) long but easy to understand; ] is much shorter, but I bet it takes you longer to read, unless you have unusual expertise in mathematics.
:This is not the kind of thing on which we can produce simplistic guidance.—] <small>]/]</small> 17:03, 18 December 2024 (UTC)
:Misplaced Pages leaves it to the discretion of editors far far before 8,000 words. We have thousands of single sentence articles to attest to this. The average article is less than 700 words. ] (]) 17:15, 18 December 2024 (UTC)
::The median article length is around 350 words, and the mean is 750. About one in 75 articles has more than 6,000 words. ] (]) 17:34, 18 December 2024 (UTC)
:::You'll have to take the specifics up with ], although that ballpark range sounds the same. ] (]) 18:45, 18 December 2024 (UTC)
:No. ] (]) 18:52, 18 December 2024 (UTC)
*I've always felt that the kB of readable prose was a better metric for page size (such as is produced by various page size gadgets). Turns out, bigger words take longer to read than shorter words :P Doing it just by wordcount encourages a certain verbosity. For me, my rule of thumb has always aimed to keep big articles under 100kb readable prose. But there's no hard and fast rule, and there shouldn't be. ] <sup>]</sup>] 23:08, 22 December 2024 (UTC)
*:If I'm being honest, what might be the best metric is starting at the top and lightly hammering the {{key|Page Down}} key for a bit. If I groan before reaching the References section, it's too long. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 23:10, 22 December 2024 (UTC)
*::For example, results were heavily discouraging for ] until recently; ] at the article's uncaring girth—thanks Nikki et al.! <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 23:18, 22 December 2024 (UTC)
*:::26,000 words is {{tomats|26000}}. Another way to look at that table is by saying that if it's more than half the length of a book, it's pushing past being "an article" and edging up towards being "a book".
*:::Or you can look at it in terms of how many minutes reading the whole thing would take. There's quite a bit of variation, but for easy math, 300 words per minute means that a 15,000-word-long article would take 50 minutes to read, which almost certainly exceeds the interest and attention span of most readers. ] (]) 00:35, 23 December 2024 (UTC)
*::::I think the most fundamental scalar isn't quite reading time or even visual size, but structural complexity—for an online encyclopedia article, being overlong expresses itself in my increasing inability to navigate an article comfortably to read or locate what I want, or to understand the structure of the scope covered by it at a glance. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 00:38, 23 December 2024 (UTC)
*:::::Come to think of it, one thing that makes an article feel longer than its word count is if its sections, media, and other landmarks have been laid out in a careless or unnatural way. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 00:48, 23 December 2024 (UTC)
*'''No.''' And this was rather a pointless, self-answering question in the first place, not something for a VP thread. The answer to the posed question of 'Is the "above 8000 words=Split" an absolute rule?' is obviously "no", both by observing actual WP community practice, and just by reading the table the OP quoted: {{tq|> 8,000 words — May need to be divided or trimmed; likelihood goes up with size}}. Is anyone here actually confused into believing that A) "must" and "may" are synonymous, or B) that a guideline, to which reasonable exceptions sometimes apply, is somehow a legal-level policy that must be obeyed at all costs? In reality, there is never any hurry to split a large article, and doing it properly often involves a tremendous amount of work, involving both repair of citations (sometimes in great detail), and resummarizing the background context in the side article while also resummarizing the side-matter in ] style within the main article (and doing them distinctly enough that the results are not obnoxiously repetitive if the reader moves between the articles). Doing a good job of this can take several days up to a month or longer of tightly focused work, depending on the detail level of the material, the number citations, etc. It is not trivial, we're all volunteers here, and our readers are not going keel over and die if they reach a detailed article that's a bit longer than they were expecting or would prefer. Ultimately, an article that is ginormous {{em|usually}} should split, but there is no deadline, and it needs to be done properly (plus there are often conceptually different ways to go about it from a content-flow perspective, and that might require some consensus discussion). <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:22, 23 December 2024 (UTC)
*:Ever since WAID reminded me of it, I've thought we should maybe link somewhere as a lemma. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 01:36, 23 December 2024 (UTC)
*::I think I linked it once in ], years ago, and someone objected. I didn't follow up to see whether the objecting editor is one of the handful who think that ''should'' is a more polite and/or IAR-compliant way to say ''must'', but as that's a fairly uncommon POV among editors, it probably wasn't. ] (]) 05:41, 23 December 2024 (UTC)
*:::The linked document pushes very hard on ''should'', "here may exist valid reasons in particular circumstances to ignore a particular item, but the full implications must be understood and carefully weighed" is not a low bar. It sounds much like must except when IAR. ] (]) 09:39, 23 December 2024 (UTC)
*1: no 2: I don’t see anything wrong with the chart if you just use it as a rule of thumb; 3: I don’t know why this needed to be discussed here, rather than a Q&A desk. ] (]) 20:50, 28 December 2024 (UTC)
::::ThisRfC is specific to the ],concerningthelinkageofnameswithinitmorethanonce.Otherinfoboxesareoutside the scopeandnot being addressed here. <small>—]</small><sup>(]</sup><substyle="margin-left:-2.0ex;">])</sub> 17:11, 28May2015 (UTC)
*'''No''', Misplaced Pages ]. It's just a general rule of thumb, and should be adjusted or ignored if the situation/article warrants it. <span class="nowrap">—] (] | ])</span> 04:38, 3 January 2025 (UTC)
{{collapse bottom}}
== Guideline against use of AI images in BLPs and medical articles? ==
*{{ping|AussieLegend}}We often link multiple times in long tables, and the infobox is closer to a table of information than reading actual prose. We know that overlinking in prose is a distraction to the flow of reading. That's why we don't overlink in prose. My question is, if many readers are finding it helpful to use the infoboxes as navigation tools, what does it hurt to link everything? It's usually done in row after row formatting so it really shouldn't cause added eyestrain. Other than it breaks some rule, how does it really hurt those who say we shouldn't do it? Does it really make it harder for people to view the infoboxes if everything is linked? I'm trying to get a grip on why this rule interpretation came into being. Maybe the overlink writers weren't really thinking about infoboxes when it was initially written. I'm not sure. And since if everything is linked in an infobox I don't think it would bother me at all, I'd like to hear some views as to why it causes problems. ] (]) 20:07, 21 May 2015 (UTC)
::The content in an infobox is a range of essentially disjointed information, whereas in a table the content has a common theme. As such, it is closer to ] than ], so the table analogy is incorrect. --] (]) 03:23, 22 May 2015 (UTC)
I have recently seen AI-generated images be added to illustrate both BLPs (e.g. ], now removed) and medical articles (e.g. ]). While we don't have any clear-cut policy or guideline about these yet, they appear to be problematic. Illustrating a living person with an AI-generated image might misinform as to how that person actually looks like, while using AI in medical diagrams can lead to anatomical inaccuracies (such as the lung structure in the second image, where the pleura becomes a bronnchiole twisting over the primary bronchi), or even medical misinformation. While a guideline against AI-generated images in general might be more debatable, do we at least have a consensus for a guideline against these two specific use cases?
*For the record, there's been someone, using various IP addresses, going through political candidates and removing the extra links, even though this discussion is ongoing. I don't have a horse in this race, but someone should maybe speak to them and invite them to the discussion. Either they don't know about it (AGF) or they do, and are ignoring the trends here. Lets hope its the first. --]] 16:37, 22 May 2015 (UTC)
*Lookingthrough"support"and"oppose"reasonsagain,Ihave to saythisproposalcomesoff as biasedforlistingmore"support"reasonsthan"oppose"reasons. ] (] / ]) 12:11, 23May2015 (UTC)
To clarify, I am not including potentially relevant AI-generated images that only ''happen'' to include a living person (such as in ]), but exclusively those used to illustrate a living person in a ] context. ] (] · ]) 12:11, 30 December 2024 (UTC)
:What about any biographies, including dead people. The lead image shouldn't be AI generated for any biography. - ] (]) 12:17, 30 December 2024 (UTC)
::I made an attempt to summarize/generalize both sides of a recent ] I closed regarding a similar issue. I didn't inject any original thought about the proposal, or try and raise reasons that weren't brought up there for the sake of neutrality. I think trying to measure ] numerically has its flaws. There could be 10 reasons against something, while only 1 reason for it, the 1 could be particularly sound. That aside, I apologize if in my attempt at neutrality, I didn't put forth enough for one of the sides. I could have played the ] and found new reasons for a side, but (again) I'd have had to have put my own thought into it, which I was trying to avoid. I have trust in the competency of the community to find their own reasoning or verses in the ]. The reasons were meant more as neutral examples to encourage taking positions and having opinions with a basis, rather than simply ]. <small>—]</small><sup>(]</sup><sub style="margin-left:-2.0ex;">])</sub> 12:48, 23 May 2015 (UTC)
::Same with animals, organisms etc. - ] (]) 12:20, 30 December 2024 (UTC)
:I personally am '''strongly against''' using AI in biographies and medical articles - as you highlighted above, AI is absolutely not reliable in generating accurate imagery and may contribute to medical or general misinformation. I would 100% support a proposal banning AI imagery from these kinds of articles - and a recommendation to not use such imagery other than in specific scenarios. ]] 12:28, 30 December 2024 (UTC)
:I'd prefer a guideline prohibiting the use of AI images full stop. There are too many potential issues with accuracy, honesty, copyright, etc. Has this already been proposed or discussed somewhere? – ] <small>(])</small> 12:38, 30 December 2024 (UTC)
::There hasn't been a full discussion yet, and we have a list of uses at ], but it could be good to deal with clear-cut cases like this (which are already a problem) first, as the wider discussion is less certain to reach the same level of consensus. ] (] · ]) 12:44, 30 December 2024 (UTC)
:Discussions are going on at ] and somewhat at ]. I recommend workshopping an RfC question (or questions) then starting an RfC. ] (]) 13:03, 30 December 2024 (UTC)
::Oh, didn't catch the previous discussions! I'll take a look at them, thanks! ] (] · ]) 14:45, 30 December 2024 (UTC)
:There is one very specific exception I would put to a very sensible blanket prohibition on using AI images to illustrate people, especially BLPs. That is where the person themselves is known to use that image, which I have encountered in ]. ] (]) 15:00, 30 December 2024 (UTC)
::While the Ekpa portrait is just an upscale (and I'm not sure what positive value that has for us over its source; upscaling does not add accuracy, nor is it an artistic interpretation meant to reveal something about the source), this would be hard to translate to the general case. Many AI portraits would have copyright concerns, not just from the individual (who may have announced some appropriate release for it), but due to the fact that AI portraits can lean heavily on uncredited individual sources. --] (]) 16:04, 30 December 2024 (UTC)
:::For the purposes of discussing whether to allow AI images at all, we should always assume that, for the purposes of (potential) policies and guidelines, there exist AI images we can legally use to illustrate every topic. We cannot use those that are not legal (including, but not limited to, copyright violations) so they are irrelevant. An image generator trained exclusively on public domain and cc0 images (and any other licenses that explicitly allow derivative works without requiring attribution) would not be subject to any copyright restrictions (other than possibly by the prompter and/or generator's license terms, which are both easy to determine). Similarly we should not base policy on the current state of the technology, but assume that the quality of its output will improve to the point it is equal to that of a skilled human artist. ] (]) 17:45, 30 December 2024 (UTC)
::::The issue is, either there are public domain/CC0 images of the person (in which case they can be used directly) or there aren't, in which case the AI is making up how a person looks. ] (] · ]) 20:00, 30 December 2024 (UTC)
::::We tend to use art representations either where no photographs are available (in which case, AI will also not have access to photographs) or where what we are showing is an artist's insight on how this person is perceived, which is not something that AI can give us. In any case, we don't have to build policy now around some theoretical AI in the future; we can deal with the current reality, and policy can be adjusted if things change in the future. And even that theoretical AI does make it more difficult to detect copyvio -- ] (]) 20:54, 30 December 2024 (UTC)
:::I wouldn't call it an upscale given whatever was done appears to have removed detail, but we use that image as it was specifically it is the edited image which was sent to VRT. ] (]) 10:15, 31 December 2024 (UTC)
:Is there any clarification on using purely AI-generated images vs. using AI to edit or alter images? AI tools , such as to identify objects and remove them, or generate missing content. The generative expand feature would appear to be unreliable (and it is), but I use it to fill in gaps of cloudless sky produced from stitching together photos for a panorama (I don't use it if there are clouds, or for starry skies, as it produces non-existent stars or unrealistic clouds). ] (]) 18:18, 30 December 2024 (UTC)
::Yes, my proposal is only about AI-generated images, not AI-altered ones. That could in fact be a useful distinction to make if we want to workshop a RfC on the matter. ] (] · ]) 20:04, 30 December 2024 (UTC)
:I'm not sure if we need a clear cut policy or guideline against them... I think we treat them the same way as we would treat an editor's kitchen table sketch of the same figure. ] (]) 18:40, 30 December 2024 (UTC)
:For those wanting to ban AI images full stop, well, you are too late. Most professional image editing software, including the software in one's smartphone as well as desktop, uses AI somewhere. Noise reduction software uses AI to figure out what might be noise and what might be texture. Sharpening software uses AI to figure out what should be smooth and what might have a sharp detail it can invent. For example, a bird photo not sharp enough to capture feather detail will have feather texture imagined onto it. Same for hair. Or grass. Any image that has been cleaned up to remove litter or dust or spots will have the cleaned area AI generated based on its surroundings. The sky might be extended with AI. These examples are a bit different from a 100% imagined image created from a prompt. But probably not in a way that is useful as a rule.
:I think we should treat AI generated images the same as any user-generated image. It might be a great diagram or it might be terrible. Remove it from the article if the latter, not because someone used AI. If the image claims to photographically represent something, we may judge whether the creator has manipulated the image too much to be acceptable. For example, using AI to remove a person in the background of an image taken of the BLP subject might be perfectly fine. People did that with traditional Photoshop/Lightroom techniques for years. Using AI to generate what claims to be a photo of a notable person is on dodgy ground wrt copyright. -- ]°] 19:12, 30 December 2024 (UTC)
::I'm talking about the case of using AI to generate a depiction of a living person, not using AI to alter details in the background. That is why I only talk about AI-generated images, not AI-altered images. ] (] · ]) 20:03, 30 December 2024 (UTC)
:Regarding some sort of brightline ban on the use of any such image in anything article medical related: absolutely not. For example, if someone wanted to use AI tools as opposed to other tools to make an image such as ] (as used in the "medical" article ]) I don't see a problem, so long as it is accurate. Accurate models and illustrations are useful and that someone used AI assistance as opposed to a chisel and a rock is of no concern. — ] <sup>]</sup> 19:26, 30 December 2024 (UTC)
:I believe that the appropriateness of AI images depends on how its used by the user. In BLP and medical articles, it is inappropriate for the images, but it is inappropriate to ban it completely across thw site. By the same logic, if you want full ban of AI, you are banning fire just because people can get burned, without considering cooking. ] (]) 13:33, 31 December 2024 (UTC)
] <sup>]</sup> 00:13, 31 December 2024 (UTC)]]
:I agree that AI-generated images should not be used in most cases. They essentially serve as misinformation. I also don't think that they're really comparable to drawings or sketches because AI-generation uses a level of photorealism that can easily trick the untrained eye into thinking it is real. ] (]) 20:46, 30 December 2024 (UTC)
::AI doesn't need to be photorealistic though. I see two potential issues with AI. The first is images that might deceive the viewer into thinking they are photos, when they are not. The second is potential copyright issues. Outside of the copyright issues I don't see any unique concerns for an AI-generated image (that doesn't appear photorealistic). Any accuracy issues can be handled the same way a user who manually drew an image could be handled. ] (]) 21:46, 30 December 2024 (UTC)
{{multiple image
| image1 = Pope Francis in puffy winter jacket.jpg
| image2 = Illustration of Brigette Lundy Paine by Sandra Mu.png
| footer = ] and ]
| total_width = 300
}}
::AI-generated depictions of BLP subjects are often more "illustrative" than drawings/sketches of BLP subjects made by 'regular' editors like you and me. For example, compare the AI-generated image of Pope Francis and the user-created cartoon of Brigette Lundy-Paine. Neither image belongs on their respective bios, of course, but the AI-generated image is no more "misinformation" than the drawing. ] (]) 00:05, 31 December 2024 (UTC)
:::I would argue the opposite: neither are made up, but the first one, because of its realism, might mislead readers into thinking that it is an actual photograph, while the second one is clearly a drawing. Which makes the first one less illustrative, as it carries potential for misinformation, despite being technically more detailed. ] (] · ]) 00:31, 31 December 2024 (UTC)
::::AI-generated images should always say "AI-generated image of " in the image caption. No misleading readers that way. ] (]) 00:36, 31 December 2024 (UTC)
:::::Yes, and they don't always do it, and we don't have a guideline about this either. The issue is, many people have many different proposals on how to deal with AI content, meaning we always end up with "no consensus" and no guidelines on use at all, even if most people are against it. ] (] · ]) 00:40, 31 December 2024 (UTC)
::::::{{tq|always end up with "no consensus" and no guidelines on use at all, even if most people are against it}} Agreed. Even a simple proposal to have image captions note whether an image is AI-generated will have editors wikilawyer over the definition of 'AI-generated.' I take back my recommendation of starting an RfC; we can already predict how that RfC will end. ] (]) 02:28, 31 December 2024 (UTC)
:Of interest perhaps is ] on the use of drawn cartoon images in BLPs. ] (]) 22:38, 30 December 2024 (UTC)
:We should absolutely not be including any AI images in anything that is meant to convey facts (with the obvious exception of an AI image illustrating the concept of an AI image). I also don't think we should be encouraging AI-altered images -- the line between "regular" photo enhancement and what we'd call "AI alteration" is blurry, but we shouldn't want AI edits for the same reason we wouldn't want fake Photoshop composites.
:That said, I would assume good faith here: some of these images are probably being sourced from Commons, and Commons is dealing with a lot of undisclosed AI images. ] (]) 23:31, 30 December 2024 (UTC)
::]
::Why wouldn't we want "fake Photoshop composites"? A ] can be very useful. I'd be sad if we banned ]. ] (]) 06:40, 31 December 2024 (UTC)
:::Sorry, should have been more clear -- composites that present themselves as the real thing, basically what people would use deepfakes for now. ] (]) 20:20, 31 December 2024 (UTC)
:I don't think any guideline, let alone policy, would be beneficial and indeed on balance is more likely to be harmful. There are always only two questions that matter when determining whether we should use an image, and both are completely independent of whether the image is AI-generated or not:
:#Can we use this image in this article? This depends on matters like copyright, fair use, whether the image depicts content that is legal for an organisation based in the United States to host, etc. Obviously if the answer is "no", then everything else is irrelevant, but as the law and WMF, Commons and en.wp policies stand today there exist some images in both categories we can use, and some images in both categories we cannot use.
:#Does using this image in this article improve the article? This is relative to other options, one of which is always not using any image, but in many cases also involves considering alternative images that we can use. In the case of depictions of specific, non-hypothetical people or objects one criteria we use to judge whether the image improves the article is whether it is an accurate representation of the subject. If it is not an accurate representation then it doesn't improve the article and thus should not be used, regardless of why it is inaccurate. If it is an accurate representation, then its use in the article will not be misrepresentative or misleading, regardless of whether it is or is not AI generated. It may or may not be the best option available, but if it is then it should be used regardless of whether it is or is not AI generated.
:The potential harm I mentioned above is twofold, firstly Misplaced Pages is, by definition, harmed when an images exists we could use that would improve an article but we do not use it in that article. A policy or guideline against the use of AI images would, in some cases, prevent us from using an image that would improve an article. The second aspect is misidentification of an image as AI-generated when it isn't, especially when it leads to an image not being used when it otherwise would have been.
:Finally, all the proponents of a policy or guideline are assuming that the line between images that are and are not AI-generated is sharp and objective. Other commenters here have already shown that in reality the line is blurry and it is only going to get blurrier in the future as more AI (and AI-based) technology is built into software and especially firmware. ] (]) 00:52, 31 December 2024 (UTC)
::I agree with almost the entirety of your post with a caveat on whether something "is an accurate representation". We can tell whether non-photorealistic images are accurate by assessing whether the image accurately conveys ''the idea'' of what it is depicting. Photos do more than convey an idea, they convey the actual look of something. With AI generated images that are photorealistic it is difficult to assess whether they accurately convey the look of something (the shading might be illogical in subtle ways, there could be an extra finger that goes unnoticed, a mole gets erased), but readers might be deceived by the photo-like presentation into thinking they are looking at an actual photographic depiction of the subject which could differ significantly from the actual subject in ways that go unnoticed. ] (]) 04:34, 31 December 2024 (UTC)
::{{tq|A policy or guideline against the use of AI images would, in some cases, prevent us from using an image that would improve an article.}} That's why I'm suggesting a guideline, not a policy. Guidelines are by design more flexible, and ] still does (and should) apply in edge cases.{{pb}}{{tq|The second aspect is misidentification of an image as AI-generated when it isn't, especially when it leads to an image not being used when it otherwise would have been.}} In that case, there is a licensing problem. AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that ''might'' have been AI-generated.{{pb}}{{tq|Finally, all the proponents of a policy or guideline are assuming that the line between images that are and are not AI-generated is sharp and objective. Other commenters here have already shown that in reality the line is blurry and it is only going to get blurrier in the future as more AI (and AI-based) technology is built into software and especially firmware.}} In that case, it's mostly because the ambiguity in wording: AI-edited images are very common, and are sometimes called "AI-generated", but here we should focus on actual prompt outputs, of the style "I asked a model to generate me an image of a BLP". ] (] · ]) 11:13, 31 December 2024 (UTC)
:::Simply not having a completely unnecessary policy or guideline is infinitely better than relying on IAR - especially as this would have to be ignored ''every'' time it is relevant. When the AI image is not the best option (which obviously includes all the times its unsuitable or inaccurate) existing policies, guidelines, practice and frankly common sense mean it won't be used. This means the only time the guideline would be relevant is when an AI image ''is'' the best option and as we obviously should be using the best option in all cases we would need to ignore the guideline against using AI images.
:::{{tpq|AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated.}} The key words here are "supposed to be" and "shouldn't", editors absolutely ''will'' speculate that images are AI-generated and that the Commons labelling is incorrect. We are supposed to assume good faith, but this very discussion shows that when it comes to AI some editors simply do not do that.
:::Regarding your final point, that might be what you are meaning but it is not what all other commenters mean when they want to exclude all AI images. ] (]) 11:43, 31 December 2024 (UTC)
::::For your first point, the guideline is mostly to take care of the "prompt fed in model" BLP illustrations, where it is technically hard to prove that the person doesn't look like that (as we have no available image), but the model likely doesn't have any available image either and most likely just made it up. As my proposal is essentially limited to that (I don't include AI-edited images, only those that are purely generated by a model), I don't think there will be many cases where IAR would be needed.{{pb}}Regarding your two other points, you are entirely correct, and while I am hoping for nuance on the AI issue, it is clear that some editors might not do that. For the record, I strongly disagree with a blanket ban of "AI images" (which includes both blatant "prompt in model" creations and a wide range of more subtle AI retouching tools) or anything like that. ] (] · ]) 11:49, 31 December 2024 (UTC)
:::::{{tpq|the guideline is mostly to take care of the "prompt fed in model" BLP illustrations, where it is technically hard to prove that the person doesn't look like that (as we have no available image)}}. There are only two possible scenarios regarding verifiability:
:::::#The image is an accurate representation and we can verify that (e.g. by reference to non-free photos).
:::::#*Verifiability is no barrier to using the image, whether it is AI generated or not.
:::::#*If it is the best image available, and editors agree using it is better than not having an image, then it should be used whether it is AI generated or not.
:::::#The image is either ''not'' an accurate representation, or we cannot verify whether it is or is not an accurate representation
:::::#*The only reasons we should ever use the image are:
:::::#**It has been the subject of notable commentary and we are presenting it in that context.
:::::#**The subject verifiably uses it as a representation of themselves (e.g. as an avatar or logo)
:::::#:This is already policy, whether the image is AI generated or not is completely irrelevant.
:::::You will note that in no circumstance is it relevant whether the image is AI generated or not. ] (]) 13:27, 31 December 2024 (UTC)
::::::In your first scenario, there is the issue of an accurate AI-generated image misleading people into thinking it is an actual photograph of the person, especially as they are most often photorealistic. Even besides that, a mostly accurate representation can still introduce spurious details, and this can mislead readers as they do not know to what level it is actually accurate. This scenario doesn't really happen with drawings (which are clearly not photographs), and is very much a consequence of AI-generated photorealistic pictures being a thing.{{pb}}In the second scenario, if we cannot verify that it is not an accurate representation, it can be hard to remove the image with policy-based reasons, which is why a guideline will again be helpful. Having a single guideline against fully AI-generated images takes care of all of these scenarios, instead of having to make new specific guidelines for each case that emerges because of them. ] (] · ]) 13:52, 31 December 2024 (UTC)
:::::::If the image is misleading or unverifiable it should not be used, regardless of why it is misleading or unverifiable. This is existing policy and we don't need anything specifically regarding AI to apply it - we just need consensus that the image ''is'' misleading or unverifiable. Whether it is or is not AI generated is completely irrelevant. ] (]) 15:04, 31 December 2024 (UTC)
::::{{tpq|AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated.}}
::::I mean... yes, we should? At the very least Commons should go hunting for mislabeled images -- that's the whole point of license review. The thing is that things are absolutely swamped over there and there are hundreds of thousands of images waiting for review of some kind. ] (]) 20:35, 31 December 2024 (UTC)
:::::Yes, but that's a Commons thing. A guideline on English Misplaced Pages shouldn't decide of what is to be done on Commons. ] (] · ]) 20:37, 31 December 2024 (UTC)
::::::I just mean that given the reality of the backlogs, there are going to be mislabeled images, and there are almost certainly going to be more of them over time. That's just how it is. We don't have control over that, but we do have control over what images go into articles, and if someone has legitimate concerns about an image being AI-generated, then they should be raising those. ] (]) 20:45, 31 December 2024 (UTC)
*'''Support blanket ban on AI-generated images on Misplaced Pages'''. As others have highlighted above, the is not just a slippery slope but an outright downward spiral. We don't use AI-generated text and we shouldn't use AI-generated images: these aren't reliable and they're also ] scraped from who knows what and where. '''Use only reliable material from reliable sources'''. As for the argument of 'software now has AI features', we all know that there's a huge difference between someone using a smoothing feature and someone generating an image from a prompt. ] (]) 03:12, 31 December 2024 (UTC)
*:'''Reply''', the section of ] concerning images is ] which states "Original images created by a Wikimedian are not considered original research, ''so long as they do not illustrate or introduce unpublished ideas or arguments''". Using AI to generate an image only violates ] if you are using it to illustrate unpublished ideas, which can be assessed just by looking at the image itself. COPYVIO, however, cannot be assessed from looking at just the image alone, which AI could be violating. However, some images may be too simple to be copyrightable, for example AI-generated images of chemicals or mathematical structures potentially. ] (]) 04:34, 31 December 2024 (UTC)
*::Prompt generated images are unquestionably violation of ] and ]: Type in your description and you get an image scraping who knows what and from who knows where, often Misplaced Pages. Misplaced Pages isn't an ]. Get real. ] (]) 23:35, 1 January 2025 (UTC)
*:::"Unquestionably"? Let me question that, @]. <code>;-)</code>
*:::If an editor were to use an AI-based image-generating service and the prompt is something like this:
*:::"I want a stacked bar chart that shows the number of games won and lost by ] each year. Use the team colors, which are red #DC052D, blue #0066B2, and black #000000. The data is:
*:::* 2014–15: played 34 games, won 25, tied 4, lost 5
*:::* 2015–16: played 34 games, won 28, tied 4, lost 2
*:::* 2016–17: played 34 games, won 25, tied 7, lost 2
*:::* 2017–18: played 34 games, won 27, tied 3, lost 4
*:::* 2018–19: played 34 games, won 24, tied 6, lost 4
*:::* 2019–20: played 34 games, won 26, tied 4, lost 4
*:::* 2020–21: played 34 games, won 24, tied 6, lost 4
*:::* 2021–22: played 34 games, won 24, tied 5, lost 5
*:::* 2022–23: played 34 games, won 21, tied 8, lost 5
*:::* 2023–24: played 34 games, won 23, tied 3, lost 8"
*:::I would expect it to produce something that is not a violation of either OR in general or OR's SYNTH section specifically. What would you expect, and why do you think it would be okay for me to put that data into a spreadsheet and upload a screenshot of the resulting bar chart, but you don't think it would be okay for me to put that same data into a image generator, get the same thing, and upload that?
*:::We must not mistake the tools for the output. Hand-crafted bad output is bad. AI-generated good output is good. ] (]) 01:58, 2 January 2025 (UTC)
*::::Assuming you'd even get what you requested the model without fiddling with the prompt for a while, these sort of 'but we can use it for graphs and charts' devil's advocate scenarios aren't helpful. We're discussing generating images of people, places, and objects here and in those cases, yes, this would unquestionably be a form of ] & ]. As for the charts and graphs, there are any number of ways to produce these. ] (]) 03:07, 2 January 2025 (UTC)
*:::::{{tpq|We're discussing generating images of people, places, and objects here}} The proposal contains no such limitation. {{tpq| and in those cases, yes, this would unquestionably be a form of WP:OR & WP:SYNTH.}} Do you have a citation for that? Other people have explained better than I can how that it is not necessarily true, and certainly not unquestionable. ] (]) 03:14, 2 January 2025 (UTC)
*::::::As you're well aware, these images are produced by scraping and synthesized material from who knows what and where: it's ultimately pure ] to produce these fake images and they're a straightforward product of synthesis of multiple sources (]) - worse yet, these sources are unknown because training data is by no means transparent. Personally, I'm strongly for a total ban on generative AI on the site exterior to articles on the topic of generative AI. Not only do I find this incredible unethical, I believe it is intensely detrimental to Misplaced Pages, which is an already a flailing and shrinking project. ] (]) 03:23, 2 January 2025 (UTC)
*:::::::So you think the lead image at ] is a SYNTH violation? Its (human) creator explicitly says "This is not done from one specific photo. As I usually do when I draw portraits of people that I can't see in person, I look at a lot of photos of them and then create my own rendition" in the image description, which sounds like the product of synthesis of multiple sources" to me, and "these sources are unknown because" the the images the artist looked at are not disclosed.
*:::::::A lot of my concern about blanket statements is the principle that what's ] is sauce for the gander, too. If it's okay for a human to do something by hand, then it should be okay for a human using a semi-automated tool to do it, too.
*:::::::<small>(Just in case you hadn't heard, the rumors that the editor base is shrinking have been false for over a decade now. Compared to when you created your account in mid-2005, we have about twice as many high-volume editors.)</small> ] (]) 06:47, 2 January 2025 (UTC)
*:::::::Review ] and your attempts at downplaying a prompt-generated image as "semi-automated" shows the root of the problem: if you can't detect the difference between a human sketching from a reference and a machine scraping who-knows-what on the internet, you shouldn't be involved in this discussion. As for editor retention, this remains a serious problem on the site: while the site continues to grow (and becomes core fodder for AI-scraping) and becomes increasingly visible, editorial retention continues to drop. ] (]) 09:33, 2 January 2025 (UTC)
*::::::::Please scroll down below SYNTH to the next section titled "What is not original research" which begins with ], our policies on how images relate to OR. OR (including SYNTH) only applies to images with regards to if they illustrate "unpublished ideas or arguments". It does not matter, for instance, if you synthesize an original ''depiction'' of something, so long as the ''idea'' of that thing is not original. ] (]) 09:55, 2 January 2025 (UTC)
*:::::::::Yes, which explicitly states:
*::::::::::It is not acceptable for an editor to use photo manipulation to distort the facts or position illustrated by an image. Manipulated images should be prominently noted as such. Any manipulated image where the encyclopedic value is materially affected should be posted to Misplaced Pages:Files for discussion. Images of living persons must not present the subject in a false or disparaging light.
*:::::::::Using a machine to generate a fake image of someone is far beyond "manipulation" and it is certainly "false". Clearly we need explicit policies on AI-generated images of people or we wouldn't be having this discussion, but this as it stands clarly also falls under ]: there is zero question that this is a result of "synthesis of published material", even if the AI won't list what it used. Ultimately it's just a synthesis of a bunch of published composite images of who-knows-what (or who-knows-who?) the AI has scraped together to produce a fake image of a person. ] (]) 10:07, 2 January 2025 (UTC)
*:The latter images you describe should be SVG regardless. If there are models that can generate that, that seems totally fine since it can be semantically altered by hand. Any generation with photographic or "painterly" characteristics (e.g. generating something in the style of a painting or any other convention of visual art that communicates aesthetic particulars and not merely abstract visual particulars) seems totally unacceptable. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 07:00, 31 December 2024 (UTC)
*:]
*:@], here's an image I created. It illustrates the concept of 1% in an article. I made this myself, by typing 100 emojis and taking a screenshot. Do you really mean to say that if I'd done this with an image-generating AI tool, using a prompt like "Give me 100 dots in a 10 by 10 grid. Make 99 a dark color and 1, randomly placed, look like a baseball" that it would be hopelessly tainted, because AI is always bad? Or does your strongly worded statement mean something more moderate?
*:I'd worry about photos of people (including dead people). I'd worry about photos of specific or unique objects that have to be accurate or they're worse than worthless (e.g., artwork, landmarks, maps). But I'm not worried about simple graphs and charts like this one, and I'm not worried about ordinary, everyday objects. If you want to use AI to generate a photorealistic image of a cookie, or a spoon, and the output you get ], I'm not actually going to worry about it. ] (]) 06:57, 31 December 2024 (UTC)
*::As you know, Misplaced Pages has the unique factor of being entirely volunteer-ran. Misplaced Pages has fewer and fewer editors and, long-term, we're seeing plummeting birth rates in areas where most Misplaced Pages editors do exist. I wouldn't expect a wave of new ones aimed at keeping the site free of bullshit in the near future.
*::In addition, the Wikimedia Foundation's hair-brained continued effort to turn the site into its political cash machine is no doubt also not helping, harming the site's public perception and leading to fewer new editors.
*::Over the course of decades (I've been here for around 20 years), it seems clear that the site will be negatively impacted by all this, especially in the face of generative AI.
*::As a long-time editor who has frequently stumbled upon intense ] content, fended off armies of outside actors looking to shape the site into their ideological image (and sent me more than a few death threats), and who has identified large amount of politically-motivated nonsense explicitly designed to fool non-experts in areas I know intimately well (such as folklore and historical linguistics topics), I think it need be said that the use of generative AI for content is especially dangerous because of its capabilities of fooling Misplaced Pages readers and Misplaced Pages editors alike.
*::Misplaced Pages is written by people for people. We need to draw a line in the sand to keep from being flooded by increasingly accessible hoax-machines.
*::A blanket ban on generative AI resolves this issue or at least hands us another tool with which to attempt to fight back. We don't need what few editors we have here wasting what little time they can give the project checking over an ocean of AI-generated slop: '''we need more material from reliable sources and better tools to fend off bad actors usable by our shrinking editor base (anyone at the Wikimedia Foundation listening?), not more waves of generative AI garbage'''. ] (]) 07:40, 31 December 2024 (UTC)
*:::A blanket ban doesn't actually resolve most of the issues though, and introduces new ones. Bad usages of AI can already be dealt with by existing policy, and malicious users will ignore a blanket ban anyways. Meanwhile, a blanket ban would harm many legitimate usages for AI. For instance, the majority of professional translators (at least Japanese to English) incorporate AI (or similar tools) into their workflow to speed up translations. Just imagine a professional translator who uses AI to help generate rough drafts of foreign language Misplaced Pages articles, before reviewing and correcting them, and another editor learning of this and mass reverting them for breaking the blanket ban, and ultimately causing them to leave. Many authors (particularly with carpal tunnel) use AI now to control their voice-to-text (you can train the AI on how you want character names spelled, the formatting of dialogue and other text, etc.). A wikipedia editor could train an AI to convert their voice into Misplaced Pages-formatted text. AI is subtly incorporated now into spell-checkers, grammar-checkers, photo editors, etc., in ways many people are not aware of. A blanket AI ban has the potential to cause many issues for a lot of people, without actually being that affective at dealing with malicious users. ] (]) 08:26, 31 December 2024 (UTC)
*::::I think this is the least convincing one I've seen here yet: It contains the ol' 'there are AI features in programs now' while also attempting to invoke accessibility and a little bit of 'we must have machines to translate!'.
*::::As a translator myself, I can only say: ''Oh please''. Generative AI is notoriously terrible at translating and that's not likely to change. And I mean ''ever'' beyond a very, very basic level. Due to the complexities of communication and little matters like nuance, all machine translated material must be thoroughly checked and modified by, yes, ''human'' translators, who often encounter it spitting out complete bullshit scraped from who-knows-where (often Misplaced Pages itself).
*::::I get that this topic attracts a lot of 'but what if generative AI is better than humans?' from the utopian tech crowd but the ''reality'' is that anyone who needs a machine to invent text and visuals for whatever reason simply shouldn't be using it on Misplaced Pages.
*::::Either you, a human being, can contribute to the project or ''you can't''. Slapping a bunch of machine-generated (generative AI) visuals and text (much of it ultimately coming from Misplaced Pages in the first place!) isn't some kind of human substitute, it's just machine-regurgitated slop and is not helping the project.
*::::If people can't be confident that Misplaced Pages is ''made by humans, for humans'' the project is finally on its way out.] (]) 09:55, 31 December 2024 (UTC)
*:::::I don't know how up to date you are on the current state of translation, but:
*::::::''''
*::::::''Over three thousand full-time professional translators from around the world responded to the surveys, which were broken into a survey for CAT tool users and one for those who do not use any CAT tool at all.''
*::::::''88% of respondents use at least one CAT tool for at least some of their translation tasks.''
*::::::''Of those using CAT tools, 83% use a CAT tool for most or all of their translation work.''
*:::::Mind you, traditionally CAT tools didn't use AI, but many do now, which only adds to potential sources of confusion in a blanket ban of AI. ] (]) 17:26, 31 December 2024 (UTC)
*::::::You're barking up the tree with the pro-generative AI propaganda in response to me. I think we're all quite aware that generative AI tool integration is now common and that there's also a big effort to replace human translators — and anything that can be "written" with machines-generated text. I'm also keenly aware that generative AI is ''absolutely horrible'' at translation and ''all of it must be thoroughly checked by humans'', as you would be if you were a translator yourself. ] (]) 22:20, 31 December 2024 (UTC)
*:::::"''all machine translated material must be thoroughly checked and modified by, yes, ''human'' translators''"
*:::::You are just agreeing with me here.
*::::::'''' -American Translation Society
*:::::There are translators (particularly with non-creative works) who are using these tools to shift more towards reviewing. It should be up to them to decide what they think is the most efficient method for them. ] (]) 06:48, 1 January 2025 (UTC)
*::::::And any translator who wants to use generative AI to ''attempt'' to translate can do so off the site. We're not here to check it for them. I strongly support a total ban on any generative AI used on the site exterior to articles on generative AI. ] (]) 11:09, 1 January 2025 (UTC)
*:::::::I wonder what you mean by "on the site". The question here is "Is it okay for an editor to go to a completely different website, generate an image all by themselves, upload it to Commons, and put it in a Misplaced Pages article?" The question here is ''not'' "Shall we put AI-generating buttons on Misplaced Pages's own website?" ] (]) 02:27, 2 January 2025 (UTC)
*:::::::I'm talking about users slapping machine-translated and/or machine-generated nonsense all over the site, only for us to have to go behind and not only check it but correct it. It takes users minutes to do this and it's already happening. It's the same for images. There are very few of us who volunteer here and our numbers are growing fewer. We need to be spending our time improving the site rather than opening the gate as wide as possible for a flood of AI-generated/rendered garbage. The site has enough problems that compound every day rather than having to fend off users armed with hoax machines at every corner. ] (]) 03:20, 2 January 2025 (UTC)
*::::::::Sure, we're all opposed to "nonsense", but my question is: What about when the machine happens to generate something that is ''not'' "nonsense"?
*::::::::I have some worries about AI content. I worry, for example, that they'll corrupt our sources. I worry that ] will get dramatically longer, and also that even more undetected, unconfessed, unretracted papers will get published and believed to be true and trustworthy. I worry that academia will go back to a model in which personal connections are more important, because you really can't trust what's published. I worry that scientific journals will start refusing to publish research unless it comes from someone employed by a trusted institution, that is willing to put its reputation on the line by saying they have directly verified that the work described in the paper was actually performed to their standards, thus scuttling the citizen science movement and excluding people whose institutions are upset with them for other reasons (Oh, you thought you'd take a job elsewhere? Well, we refuse to certify the work you did for the last three years...).
*::::::::But I'm not worried about a Misplaced Pages editor saying "Hey AI, give me a diagram of swingset" or "Make a chart for me out of the data I'm going to give you". In fact, if someone wants to pull the numbers out of ], feed it to an AI, and replace the template's contents with an AI-generated image (until they finally fix the Graphs extension), I'd consider that helpful. ] (]) 07:09, 2 January 2025 (UTC)
*::::::Translators are not using ''generative'' AI for translation, the applicability of LLMs to regular translation is still in its infancy and regardless will not be implementing any ''generative'' faculties to its output since that is the exact opposite of what translation is supposed to do. ] (]) 02:57, 2 January 2025 (UTC)
*:::::::{{tpq|Translators are not using generative AI for translation}} this entirely depends on what you mean by "generative". There are at least three contradictory understandings of the term in this one thread alone. ] (]) 03:06, 2 January 2025 (UTC)
*:::::::Please, you can just go through the entire process with a simple prompt command now. The results are typically shit but you can generate a ton of it quickly, which is perfect for flooding a site like this one — especially without a strong policy against it. I've found myself cleaning up tons of AI-generated crap (and, yes, rendered) stuff here and elsewhere, and now I'm even seeing AI-generated responses to my own comments. It's beyond ridiculous. ] (]) 03:20, 2 January 2025 (UTC)
* '''Ban AI-generated from all articles, AI anything from BLP and medical articles''' is the position that seems it would permit all instances where there are plausible defenses that AI use does not fabricate or destroy facts intended to be communicated in the context of the article. That scrutiny is stricter with BLP and medical articles in general, and the restriction should be stricter to match. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 06:53, 31 December 2024 (UTC)
*:@], please see my comment immediately above. (We had an edit conflict.) Do you really mean "anything" and everything? Even a simple chart? ] (]) 07:00, 31 December 2024 (UTC)
*::I think my previous comment is operative: almost anything we can see AI used programmatically to generate should be SVG, not raster—even if it means we are embedding raster images in SVG to generate examples like the above. I do not know if there are models that can generate SVG, but if there are I happily state I have no problem with that. I think I'm at risk of seeming downright paranoid—but understanding how errors can propagate and go unnoticed in practice, if we're to trust a black box, we need to at least be able to check what the black box has done on a direct structural level. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 07:02, 31 December 2024 (UTC)
*:::A quick web search indicates that there are generative AI programs that create SVG files. ] (]) 07:16, 31 December 2024 (UTC)
*::::Makes perfect sense that there would be. Again, maybe I come off like a paranoid lunatic, but I really need either the ability to check what the thing is doing, or the ability to check and correct exactly what a black box has done. (In my estimation, if you want to know what procedures person has done, theoretically you can ask them to get a fairly satisfactory result, and the pre-AI algorithms used in image manipulation are canonical and more or less transparent. Acknowledging human error etc., with AI there is not even the theoretical promise that one can be given a truthful account of how it decided to do what it did.) <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 07:18, 31 December 2024 (UTC)
*:::::Like everyone said, there should be a ''de facto'' ban on using AI images in Misplaced Pages articles. They are effectively fake images pretending to be real, so they are out of step with the values of Misplaced Pages.--'''''] <sup>]</sup>''''' 08:20, 31 December 2024 (UTC)
*::::::Except, not everybody ''has'' said that, because the majority of those of us who have refrained from hyperbole have pointed out that not all AI images are "fake images pretending to be real" (and those few that are can already be removed under existing policy). You might like to try actually reading the discussion before commenting further. ] (]) 10:24, 31 December 2024 (UTC)
*:::::@], exactly how much "ability to check what the thing is doing" do you need to be able to do, when the image shows 99 dots and 1 baseball, to illustrate the concept of 1%? If the image above said {{tl|pd-algorithm}} instead of {{tl|cc-by-sa-4.0}}, would you remove if from the article, because you just can't be sure that it shows 1%? ] (]) 02:33, 2 January 2025 (UTC)
*::::::The above is a useful example to an extent, but it is a toy example. I really do think i is required in general when we aren't dealing with media we ourselves are generating. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 04:43, 2 January 2025 (UTC)
*:::::::How do we differentiate in policy between a "toy example" (that really would be used in an article) and "real" examples? Is it just that if I upload it, then you know me, and assume I've been responsible? ] (]) 07:13, 2 January 2025 (UTC)
*::::There definitely exist generative AI for SVG files. Here's an example: I used generative AI in Adobe Illustrator to generate the SVG gear in ] (from ]) before drawing by hand the more informative parts of the image. The gear drawing is not great (a real gear would have uniform tooth shape) but maybe the shading is better than I would have done by hand, giving an appearance of dimensionality and surface material while remaining deliberately stylized. Is that the sort of thing everyone here is trying to forbid?
*::::I can definitely see a case for forbidding AI-generated photorealistic images, especially of BLPs, but that's different from human oversight of AI in the generation of schematic images such as this one. —] (]) 01:15, 1 January 2025 (UTC)
*:::::I'd include BDPs, too. I had to get a few AI-generated images of allegedly Haitian presidents deleted a while ago. The "paintings" were 100% fake, right down to the deformed medals on their military uniforms. An AI-generated "generic person" would be okay for some purposes. For a few purposes (e.g., illustrations of ]) it could even be preferable to have a fake "person" than a real one. But for individual/named people, it would be best not to have anything unless it definitely looks like the named person. ] (]) 07:35, 2 January 2025 (UTC)
*I put it to you that our decision on this requires nuance. It's obviously insane to allow AI-generated images of, for example, Donald Trump, and it's obviously insane to ban AI-generated images from, for example, ] or ].—] <small>]/]</small> 11:21, 31 December 2024 (UTC)
*:Of course, that's why I'm only looking at specific cases and refrain from proposing a blanket ban on generative AI. Regarding Donald Trump, we do have one AI-generated image of him that is reasonable to allow (in ]), as the image itself was the subject of relevant commentary. Of course, this is different from using an AI-generated image to illustrate ] himself, which is what my proposal would recommend against. ] (] · ]) 11:32, 31 December 2024 (UTC)
*::That's certainly true, but others are adopting much more extreme positions than you are, and it was the more extreme views that I wished to challenge.—] <small>]/]</small> 11:34, 31 December 2024 (UTC)
*:::Thanks for the (very reasoned) addition, I just wanted to make my original proposal clear. ] (] · ]) 11:43, 31 December 2024 (UTC)
*Going off WAID's example above, perhaps we should be trying to restrict the use of AI where image accuracy/precision is essential, as it would be for BLP and medical info, among other cases, but in cases where we are talking generic or abstract concepts, like the 1% image, it's use is reasonable. I would still say we should strongly prefer am image made by a human with high control of the output, but when accuracy is not as important as just the visualization, it's reasonable to turn to AI to help. ] (]) 15:12, 31 December 2024 (UTC)
* '''Support total ban of AI imagery''' - There are probable copyright problems and veracity problems with anything coming out of a machine. In a word of manipulated reality, Misplaced Pages will be increasingly respected for holding a hard line against synthetic imagery. ] (]) 15:39, 31 December 2024 (UTC)
*:For both issues AI vs not AI is irrelevant. For copyright, if the image is a copyvio we can't use it regardless of whether it is AI or not AI, if it's not a copyvio then that's not a reason to use or not use the image. If the images is not verifiably accurate then we already can (and should) exclude it, regardless of whether it is AI or not AI. For more detail see the extensive discussion above you've either not read or ignored. ] (]) 16:34, 31 December 2024 (UTC)
*'''Yes''', we absolutely should ban the use of AI-generated images in these subjects (and beyond, but that's outside the scope of this discussion). AI should not be used to make up a simulation of a living person. It does not actually depict the person and may introduce errors or flaws that don't actually exist. The picture ''does not depict the real person'' because it is quite simply fake.
*Even worse would be using AI to develop medical images in articles ''in any way''. The possibility for error there is unacceptable. Yes, humans make errors too, but there there is a) someone with the responsibility to fix it and b) someone conscious who actually made the picture, rather than a black box that spat it out after looking at similar training data. '']'' 🎄 ] — ] 🎄 20:08, 31 December 2024 (UTC)
*:It's ''incredibly'' disheartening to see multiple otherwise intelligent editors who have apparently not read and/or not understood what has been said in the discussion but rather responding with what appears to be knee-jerk reactions to anti-AI scaremongering. The sky will not fall in, Misplaced Pages is not going to be taken over by AI, AI is not out to subvert Misplaced Pages, we already can (and do) remove (and more commonly not add in the first placE) false and misleading information/images. ] (]) 20:31, 31 December 2024 (UTC)
*::So what benefit does allowing AI images bring? We shouldn't be forced to decide these on a case-by-case basis.
*::I'm sorry to dishearten you, but I still respectfully disagree with you. And I don't think this is "scaremongering" (although I admit that if it was, I would of course claim it wasn't). '']'' 🎄 ] — ] 🎄 21:02, 31 December 2024 (UTC) '']'' 🎄 ] — ] 🎄 20:56, 31 December 2024 (UTC)
*:::Determining what benefits ''any'' image brings to Misplaced Pages can ''only'' be done on a case-by-case basis. It is literally impossible to know whether any image improves the encyclopaedia without knowing the context of which portion of what article it would illustrate, and what alternative images are and are not available for that same spot.
*:::The benefit of allowing AI images is that when an AI image is the best option for a given article we use it. We gain absolutely nothing by prohibiting using the best image available, indeed doing so would actively harm the project without bringing any benefits. AI images that are misleading, inaccurate or any of the other negative things ''any'' image can be are never the best option and so are never used - we don't need any policies or guidelines to tell us that. ] (]) 21:43, 31 December 2024 (UTC)
*'''Support blanket ban on AI-generated text or images in articles''', except in contexts where the AI-generated content is itself the subject of discussion (in a ] or ]). Generative AI is fundamentally at odds with Misplaced Pages's mission of providing reliable information, because of its propensity to distort reality or make up information out of whole cloth. It has no place in our encyclopedia. <span class="nowrap">—] (] | ])</span> 21:34, 31 December 2024 (UTC)
*'''Support blanket ban on AI-generated images''' except in ABOUTSELF contexts. This is ''especially'' a problem given the preeminence Google gives to Misplaced Pages images in its image search. ] (]) 22:49, 31 December 2024 (UTC)
*'''Ban across the board''', except in articles which are actually about AI-generated imagery or the tools used to create them, or the image itself is the subject of substantial commentary within the article for some reason. Even in those cases, clearly indicating that the image is AI-generated should be required. ] <small><sup>]</sup></small> 00:29, 1 January 2025 (UTC)
*'''Oppose blanket bans''' that would forbid the use of AI assistance in creating diagrams or other deliberately stylized content. Also oppose blanket bans that would forbid AI illustrations in articles about AI illustrations. I am not opposed to banning photorealistic AI-generated images in non-AI-generation contexts or banning AI-generated images from BLPs unless the image itself is specifically relevant to the subject of the BLP. —] (]) 01:27, 1 January 2025 (UTC)
]?]]
*'''Oppose blanket bans''' AI is just a new buzzword so, for example, Apple phones now include "Apple Intelligence" as a standard feature. Does this means that photographs taken using Apple phones will be inadmissable? That would be silly because legacy technologies are already rife with issues of accuracy and verification. For example, there's an image on the main page right now ''(right)''. This purports to be a particular person ("]") but, if you check the , you find that it may have been his brother and even the attribution to the artist is uncertain. AI features may help in exposing such existing weaknesses in our image use and so we should be free to use them in an intelligent way. ]🐉(]) 08:03, 1 January 2025 (UTC)
*:So, you expect an the AI, ''notoriously trained on Misplaced Pages (and whatever else is floating around on the internet)'', to correct Misplaced Pages where humans have failed... using the data it ''scraped from Misplaced Pages (and who knows where else)''? ] (]) 11:12, 1 January 2025 (UTC)
*::I tried using the Deep Research option of Gemini to assess the attribution of the Macquarie portrait. Its stated methodology seemed quite respectable and sensible.
{{cot|The Opie Portrait of Lachlan Macquarie: An Examination of its Attribution: Methodology}}
To thoroughly investigate the attribution of the Opie portrait of Lachlan Macquarie, a comprehensive research process was undertaken. This involved several key steps:
#Gathering information on the Opie portrait: This included details about its history, provenance, and any available information on its cost.
#Reviewing scholarly articles and publications: This step focused on finding academic discussions specifically addressing the attribution of the portrait to John Opie.
#Collecting expert opinions: Statements and opinions from art experts and historians were gathered to understand the range of perspectives on the certainty of the attribution.
#Examining historical documents and records: This involved searching for any records that could shed light on the portrait's origins and authenticity, such as Macquarie's personal journals or contemporary accounts.
#Exploring scientific and technical analyses: Information was sought on any scientific or technical analyses conducted on the portrait, such as pigment analysis or canvas dating, to determine its authenticity.
#Comparing the portrait to other Opie works: This step involved analyzing the style and technique of the Opie portrait in comparison to other known portraits by Opie to identify similarities and differences.
{{cob}}
*::It was quite transparent in listing and citing the sources that it used for its analysis. These included the Misplaced Pages image but if one didn't want that included, it would be easy to exclude it.
*::So, AIs don't have to be inscrutable black boxes. They can have programmatic parameters like the existing bots and scripts that we use routinely on Misplaced Pages. Such power tools seem needed to deal with the large image backlogs that we have on Commons. Perhaps they could help by providing captions and categories where these don't exist.
*::]🐉(]) 09:09, 2 January 2025 (UTC)
*:::They don't ''have to be black boxes'' but they are ''by design'': they exist in a legally dubious area and thus hide what they're scraping to avoid further legal problems. That's no secret. We know for example that Misplaced Pages is a core data set for likely most AIs today. They also notoriously and quite confidently spit out a lie ("hallucinate") and frequently spit out total nonsense. Add to that that they're restricted to whatever is floating around on the internet or whatever other data set they've been fed (usually just more internet), and many specialist topics, like texts on ancient history and even standard reference works, are not accessible on the internet (despite Google's efforts). ] (]) 09:39, 2 January 2025 (UTC)
*:::While its stated methodology seems sensible, there's no evidence that it actually followed that methodology. The bullet points are pretty vague, and are pretty much the default methodologies used to examine actual historical works. ] (] · ]) 17:40, 2 January 2025 (UTC)
*:::: Yes, there's evidence. As I stated above, the analysis is transparent and cites the sources that it used. And these all seem to check out rather than being invented. So, this level of AI goes beyond the first generation of LLM and addresses some of their weaknesses. I suppose that image generation is likewise being developed and improved and so we shouldn't rush to judgement while the technology is undergoing rapid development. ]🐉(]) 17:28, 4 January 2025 (UTC)
* '''Oppose blanket ban''': best of luck to editors here who hope to be able to ban an entirely undefined and largely undetectable procedure. The term 'AI' as commonly used is no more than a buzzword - what ''exactly'' would be banned? And how does it improve the encyclopedia to encourage editors to object to images not simply because they are inaccurate, or inappropriate for the article, but because they subjectively look too good? Will the image creator be quizzed on Commons about the tools they used? Will creators who are transparent about what they have created have their images deleted while those who keep silent don’t? Honestly, this whole discussion is going to seem hopelessly outdated within a year at most. It’s like when early calculators were banned in exams because they were ‘cheating’, forcing students to use slide rules. ] (]) 12:52, 1 January 2025 (UTC)
*:I am genuinely confused as to why this has turned into a discussion about a blanket ban, even though the original proposal exclusively focused on ''AI-generated'' images (the kind that is generated by an AI model from a prompt, which are already tagged on Commons, not regular images with AI enhancement or tools being used) and only in specific contexts. Not sure where the "subjectively look too good" thing even comes from, honestly. ] (] · ]) 12:58, 1 January 2025 (UTC)
*::That just show how ill-defined the whole area is. It seem you restrict the term 'AI-generated' to mean "images generated solely(?) from a text prompt". The question posed above has no such restriction. What a buzzword means is largely in the mind of the reader, of course, but to me and I think to many, 'AI-generated' means generated by AI. ] (]) 13:15, 1 January 2025 (UTC)
*:::I used the text prompt example because that is the most common way to have an AI model generate an image, but I recognize that I should've clarified it better. There is definitely a distinction between an image being ''generated'' by AI (like the Laurence Boccolini example below) and an image being ''altered'' or retouched by AI (which includes many features integrated in smartphones today). I don't think it's a "buzzword" to say that there is a meaningful difference between an image being made up by an AI model and a preexisting image being altered in some way, and I am surprised that many people understand "AI-generated" as including the latter. ] (] · ]) 15:24, 1 January 2025 (UTC)
*'''Oppose as unenforceable.''' I just want you to imagine enforcing this policy against people who have not violated it. All this will do is allow Wikipedians who primarily contribute via text to accuse artists of using AI ] to get their contributions taken down. I understand the impulse to oppose AI on principle, but the labor and aesthetic issues don't actually have anything to do with Misplaced Pages. If there is not actually a problem with the content conveyed by the image—for example, if the illustrator intentionally corrected any hallucinations—then someone objecting over AI is not discussing page content. If the image was not even made with AI, they are hallucinating based on prejudices that are irrelevant to the image. The bottom line is that images should be judged on their content, not how they were made. Besides all the policy-driven stuff, if Misplaced Pages's response to the creation of AI imaging tools is to crack down on all artistic contributions to Misplaced Pages (which seems to be the inevitable direction of these discussions), what does that say? Categorical bans of this kind are ill-advised and anti-illustrator. ] (]) 15:41, 1 January 2025 (UTC)
*:And the same applies to photography, of course. If in my photo of a garden I notice there is a distracting piece of paper on the lawn, nobody would worry if I used the old-style clone-stamp tool to remove it in Photoshop, adding new grass in its place (I'm assuming here that I don't change details of the actual landscape in any way). Now, though, Photoshop uses AI to achieve essentially the same result while making it simpler for the user. A large proportion of all processed photos will have at least some similar but essentially undetectable "generated AI" content, even if only a small area of grass. There is simply no way to enforce the proposed policy, short of banning all high-quality photography – which requires post-processing by design, and in which similar encyclopedically non-problematic edits are commonplace. ] (]) 17:39, 1 January 2025 (UTC)
*:Before anyone objects that my example is not "an image generated from a text prompt", note that there's no mention of such a restriction in the proposal we are discussing. Even if there were, it makes no difference. Photoshop can already generate photo-realistic areas from a text prompt. If such use is non-misleading and essentially undetectable, it's fine; if if changes the image in such a way as to make it misleading, inaccurate or non-encycpopedic in any way it can be challenged on that basis. ] (]) 17:58, 1 January 2025 (UTC)
*::As I said previously, the text prompt is just an example, not a restriction of the proposal. The point is that you talk about editing an existing image (which is what you talk about, as you say {{tq|if if changes the image}}), while I am talking about creating an image ''ex nihilo'', which is what "generating" means. ] (] · ]) 18:05, 1 January 2025 (UTC)
*:::I'm talking about a photograph with AI-generated areas within it. This is commonplace, and is targeted by the proposal. Categorical bans of the type suggested are indeed ill-advised. ] (]) 18:16, 1 January 2025 (UTC)
*:Even if the ban is unenforceable, there are many editors who will choose to use AI images if they are allowed and just as cheerfully skip them if they are not allowed. That would mean the only people posting AI images are those who choose to break the rule and/or don't know about it. That would probably add up to many AI images not used. ] (]) 22:51, 3 January 2025 (UTC)
*'''Support blanket ban''' because "AI" is a fundamentally unethical technology based on the exploitation of labor, the wanton destruction of the planetary environment, and the subversion of every value that an encyclopedia should stand for. ABOUTSELF-type exceptions for "AI" output ''that has already been generated'' might be permissible, in order to document the cursed time in which we live, but those exceptions are going to be rare. How many examples of Shrimp Jesus slop do we need? ] (]) 23:30, 1 January 2025 (UTC)
*'''Support blanket ban''' - Primarily because of the "poisoning the well"/"dead internet" issues created by it. ] (]) 14:30, 2 January 2025 (UTC)
* '''Support a blanket ban''' to assure some control over AI-creep in Misplaced Pages. And per discussion. ] (]) 10:50, 3 January 2025 (UTC)
* '''Support that ] applies to images''': images should be verifiable, neutral, and absent of original research. AI is just the latest quickest way to produce images that are original, unverifiable, and potentially biased. Is anyone in their right mind saying that we allow people to game our rules on ] and ] by using images instead of text? ] (]) 17:04, 3 January 2025 (UTC)
*:As an aside on this: in some cases Commons is being treated as a way of side-stepping ] and other restrictions. Stuff that would get deleted if it were written content on WP gets in to WP as images posted on Commons. The worst examples are those conflict maps that are created from a bunch of Twitter posts (eg the Syrian civil war one). AI-generated imagery is another field where that appears to be happening. ] (]) 10:43, 4 January 2025 (UTC)
*'''Support temporary blanket ban''' with a posted expiration/requred rediscussion date of no more than two years from closing. AI as the term is currently used is very, very new. Right now these images would do more harm than good, but it seems likely that the culture will adjust to them. I support an exception for the when the article is about the image itself and that image is notable, such as the photograph of the black-and-blue/gold-and-white dress in ] and/or examples of AI images in articles in which they are relevant. E.g. "here is what a hallucination is: count the fingers." ] (]) 23:01, 3 January 2025 (UTC)
* First, I think any guidance should avoid referring to specific technology, as that changes rapidly and is used for many different purposes. Second, assuming that the image in question has a suitable copyright status for use on Misplaced Pages, the key question is whether or not the reliability of the image has been established. If the intent of the image is to display 100 dots with 99 having the same appearance and 1 with a different appearance, then ordinary math skills are sufficient and so any Misplaced Pages editor can evaluate the reliability without performing original research. If the intent is to depict a likeness of a specific person, then there needs to be reliable sources indicating that the image is sufficiently accurate. This is the same for actual photographs, re-touched ones, drawings, hedcuts, and so forth. Typically this can be established by a reliable source using that image with a corresponding description or context. ] (]) 17:59, 4 January 2025 (UTC)
*'''Support Blanket Ban on AI generated imagery''' per most of the discussion above. It's a very slippery slope. I ''might'' consider a very narrow exception for an AI generated image of a person that was specifically authorized or commissioned by the subject. -] (]) 02:45, 5 January 2025 (UTC)
* '''Oppose blanket ban''' It is far too early to take an absolutist position, particularly when the potential is enormous. Misplaced Pages is already is image desert and to reject something that is only at the cusp of development is unwise. '''<span style="text-shadow:7px 7px 8px black; font-family:Papyrus">]<sup>]</sup></span>''' 20:11, 5 January 2025 (UTC)
*'''Support blanket ban''' on AI-generated images except in ABOUTSELF contexts. An encyclopedia should not be using fake images. I do not believe that further nuance is necessary. ] (]) 22:44, 5 January 2025 (UTC)
*'''Support blanket ban''' as the general guideline, as accuracy, personal rights, and intellectual rights issues are very weighty, here (as is disclosure to the reader). (I could see perhaps supporting adoption of a sub-guideline for ways to come to a broad consensus in individual use cases (carve-outs, except for BLPs) which address all the weighty issues on an individual use basis -- but that needs to be drafted and agreed to, and there is no good reason to wait to adopt the general ban in the meantime). ] (]) 15:32, 8 January 2025 (UTC)
]
*'''Support indefinite blanket ban except ABOUTSELF and simple abstract examples''' (such as the image of 99 dots above). In addition to all the issues raised above, including copyvio and creator consent issues, in cases of photorealistic images it may never be obvious to all readers exactly which elements of the image are guesswork. The cormorant picture at the head of the section reminded me of ]. Had AI been trained on paintings of horses instead of actual videos and used to "improve" said videos, we would've ended up with serious delusions about the horse's gait. We don't know what questions -- scientific or otherwise -- photography will be used to settle in the coming years, but we do know that consumer-grade photo AI has already been trained to intentionally fake detail to draw sales, such as on photos of the Moon. I think it's unrealistic to require contributors to take photos with expensive cameras or specially-made apps, but Misplaced Pages should act to limit its exposure to this kind of technology as far as is feasible. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 20:57, 9 January 2025 (UTC)
{{clear}}
== Animated GIFs in infoboxes ==
===BLPs===
{{Archive top
|status = Consensus against
|result = There is clear consensus against using AI-generated imagery to depict BLP subjects. Marginal cases (such as major AI enhancement or where an AI-generated image of a living person is itself notable) can be worked out on a case-by-case basis. I will add a sentence reflecting this consensus to the ] and the ]. —] (]) 14:02, 8 January 2025 (UTC)
}}
Are AI-generated images (generated via text prompts, see also: ]) okay to use to depict BLP subjects? The ] example was mentioned in the opening paragraph. The image was created using ], {{tq|a text-to-image model developed by xAI, to generate images...As with other text-to-image models, Aurora generates images from natural language descriptions, called prompts.}} ]]] ] (]) 12:34, 31 December 2024 (UTC)
]]]
The new ] has had an animated ] put in its infobox, where one would normally expect a logo or similar. Is this allowed? I find it rather distracting. (see GIF at https://en.wikipedia.org/File:Shri_Ram_Group.gif) ] ] <sup>]</sup> 13:51, 22 May 2015 (UTC)
]: <ins>Note</ins>: that these images can either be photorealistic in style (such as the Laurence Boccolini example) or non-photorealistic in style (see the ] example, which was generated using ], another text-to-image model).
:Misplaced Pages has no rules against the use of animated GIFs, AFAIK. There are some that have been featured picture of the day, even. That being said, merely because something is allowed, doesn't mean it is a good idea; editorial discretion and article quality are more important than rules, and if the image detracts from the article quality 1) feel free to remove it and 2) if someone objects and puts it back, don't edit war but instead have a discussion and come to a consensus. --]] 16:36, 22 May 2015 (UTC)
] (]) 11:10, 3 January 2025 (UTC) {{clear}}
::Thanks Jayron. I think I have ''never'' come across a animated logo in an Infobox before though. An IP editor has now removed it. I think I'll leave it at that. ] ] <sup>]</sup> 17:04, 22 May 2015 (UTC)
* '''Kill it. Kill it with fire.''' If we don't have a rule against animated GIFs in infoboxes we should make one. --] (]) 06:14, 23 May 2015 (UTC)
*'''No.''' I don't think they are at all, as, despite looking photorealistic, they are essentially just speculation about what the person might look like. A photorealistic image conveys the look of something up to the details, and giving a false impression of what the person looks like (or, at best, just guesswork) is actively counterproductive. (Edit 21:59, 31 December 2024 (UTC): clarified bolded !vote since everyone else did it) ] (] · ]) 12:46, 31 December 2024 (UTC)
**I largely agree with Guy. I think animated Gifs have their place, and think we could use more, especially good ones, but generally oppose them in infoboxes. I'm not quite ready to support a firm rule, as I can imagine excepts. we do not have an article on animated Gifs or animated Google Doodles yet, but in such an article it might be desirable for an example in the info box. I do see that there is an animated Gif in ], and think that is a bad idea, but I don't have the energy to start the discussion there.--]] 17:40, 24 May 2015 (UTC)
*:That AI generated image looks like ] wearing a Laurence Boccolini suit. ] (]) 12:50, 31 December 2024 (UTC)
*Although rare, gifs are useful in some articles. For example, in our ] articles, where certain positions or a sequence of moves must be presented to describe the topic. See ] for an example; it doesn't have an infobox, but if it did, I can't imagine any image being appropriate there except a gif of that particular sequence. The OP's example is obviously a very different case, and that gif should probably be removed. — ]<span style="margin:0 7px;font-variant:small-caps;font-size:0.9em">· ]]</span> 06:50, 23 May 2015 (UTC)
*:There are plenty of non-free images of Laurence Boccolini with which this image can be compared. Assuming at least most of those are accurate representations of them (I've never heard of them before and have no other frame of reference) the image above is similar to but not an accurate representation of them (most obviously but probably least significantly, in none of the available images are they wearing that design of glasses). This means the image should not be used to identify them ''unless'' they use it to identify themselves. It should not be used elsewhere in the article unless it has been the subject of notable commentary. That it is an AI image makes absolutely no difference to any of this. ] (]) 16:45, 31 December 2024 (UTC)
**I can see keeping the animated gif in the chess article, but in an infobox on the chess page? No. --] (]) 17:16, 23 May 2015 (UTC)
*'''No'''. Well, that was easy.{{pb}}<!--converted from 2 lines ~ToBeFree-->They are fake images; they do not actually depict the person. They depict an AI-generated ''simulation'' of a person that may be inaccurate. '']'' 🎄 ] — ] 🎄 20:00, 31 December 2024 (UTC)
*** Why? Why would it be okay to put a valuable "Animated.gif" just above the infobox, as the lead image, but not inside the infobox, in an equally prominent position? ] (]) 15:36, 29 May 2015 (UTC)
*:Even if the subject uses the image to identify themselves, the image is still fake. '']'' (] — ]) 19:17, 2 January 2025 (UTC)
* GIF animations of instructive things like chess moves are simply ], covered by that quasi-guideline. The use of the same technology to animate an oversized icon to be attention getting is arguably already within the purview of ] (basically: don't use icons as decoration), and even if we don't think it's covered, it's a simple matter to ensure that it becomes covered there. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 09:39, 24 May 2015 (UTC)
*'''No''', with the caveat that its mostly on the grounds that we don't have enough information and when it comes to BLP we are required to exercise caution. If at some point in the future AI generated photorealistic simulacrums living people become mainstream with major newspapers and academic publishers it would be fair to revisit any restrictions, but in this I strongly believe that we should follow not lead. ] (]) 20:37, 31 December 2024 (UTC)
*Banning animated ]s from all infoboxes, is a little too broad of a rule for my taste. There are certainly some articles where gifs in the infobox would be warranted, though it may be few and far between. Advising against them in general as guideline would be fine, but a policy outright banning them would be too much. <small>—]</small><sup>(]</sup><sub style="margin-left:-2.0ex;">])</sub> 18:01, 28 May 2015 (UTC)
*'''No'''. The use of AI-generated images to depict people (living or otherwise) is fundamentally misleading, because the images are not actually depicting the person. <span class="nowrap">—] (] | ])</span> 21:30, 31 December 2024 (UTC)
**Having ] address it would work, since it's a guideline. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 18:28, 28 May 2015 (UTC)
*'''No''' except perhaps, maybe, if the subject explicitly is already using that image to represent themselves. But mostly no. -] (]) 21:32, 31 December 2024 (UTC)
*'''Yes''', when that image is an accurate representation and better than any available alternative, used by the subject to represent themselves, or the subject of notable commentary. However, as these are the exact requirements to use ''any'' image to represent a BLP subject this is already policy. ] (]) 21:46, 31 December 2024 (UTC)
*:How well can we determine how accurate a representation it is? Looking at the example above, I'd argue that the real ] has a somewhat rounder/pointier chin, a wider mouth, and possibly different eye wrinkles, although the latter probably depends quite a lot on the facial expression.
*:How accurate a representation a photorealistic AI image is is ultimately a matter of editor opinion. '']'' 🎄 ] — ] 🎄 21:54, 31 December 2024 (UTC)
*::{{tpq|How well can we determine how accurate a representation it is?}} in exactly the same way that we can determine whether a human-crafted image is an accurate representation. How accurate a representation ''any'' image is is ultimately a matter of editor opinion. Whether an image is AI or not is irrelevant. I agree the example image above is not sufficiently accurate, but we wouldn't ban photoshopped images because one example was not deemed accurate enough, because we are rational people who understand that one example is not representative of an entire class of images - at least when the subject is something other than AI. ] (]) 23:54, 31 December 2024 (UTC)
*:::I think except in a few exceptional circumstances of actual complex restorations, human photoshopping is not going to change or distort a person's appearance in the same way an AI image would. Modifications done by a person who is paying attention to what they are doing and merely enhancing an image, by person who is aware, while they are making changes, that they might be distorting the image and is, I only assume, trying to minimise it – those careful modifications shouldn't be equated with something made up by an AI image generator. '']'' 🎄 ] — ] 🎄 00:14, 1 January 2025 (UTC)
*::::I'm guessing your filter bubble doesn't include ] and their notorious ] problems. ] (]) 02:46, 2 January 2025 (UTC)
*:::A photo of a person can be connected to a specific time, place, and subject that existed. It can be compared to other images sharing one or more of those properties. A photo that was PhotoShopped is still either a generally faithful reproduction of a scene that existed, or has significant alterations that can still be attributed to a human or at least to a specific algorithm, e.g. filters. The artistic license of a painting can still be attributed to a human and doesn't run much risk of being misidentified as real, unless it's by Chuck Close et al. An AI-generated image cannot be connected to a particular scene that ever existed and cannot be attributable to a human's artistic license (and there is legal precedent that such images are not copyrightable to the prompter specifically because of this). Individual errors in a human-generated artwork are far more predictable, understandable, identifiable, traceable... than those in AI-generated images. We have innate assumptions when we encounter real images or artwork that are just not transferable. These are meaningful differences to the vast majority of people: according to a , 87% of respondents want AI-generated art to ''at least'' be transparent, and 98% consider authentic images "pivotal in establishing trust". {{pb}}And even if you disagree with all that, can you not see the larger problem of AI images on Misplaced Pages getting propagated into generative AI corpora? ] (]) 04:20, 2 January 2025 (UTC)
*::::I agree that our old assumptions don't hold true. I think the world will need new assumptions. We will probably have those in place in another decade or so.
*::::I think we're ], not here to protect AI engines from ingesting AI-generated artwork. Figuring out what they should ingest is their problem, not mine. ] (]) 07:40, 2 January 2025 (UTC)
*'''Absolutely no fake/AI images of people, photorealistic or otherwise'''. How is this even a question? These images are fake. Readers need to be able to trust Misplaced Pages, not navigate around whatever junk someone has created with a prompt and presented as somehow representative. This includes text. ] (]) 22:24, 31 December 2024 (UTC)
*'''No''' except for edge cases (mostly, if the image itself is notable enough to go into the article). ] (]) 22:31, 31 December 2024 (UTC)
*'''Absolutely not''', except for ABOUTSELF. "They're fine if they're accurate enough" is an obscenely naive stance. ] (]) 23:06, 31 December 2024 (UTC)
* '''No''' with no exceptions. ] (]) 23:54, 31 December 2024 (UTC)
*'''No'''. We don't permit falsifications in BLPs. ] <small><sup>]</sup></small> 00:30, 1 January 2025 (UTC)
*:For the requested clarification by {{u|Some1}}, no AI-generated images (except when the image ''itself'' is specifically discussed in the article, and even then it should not be the lead image and it should be clearly indicated that the image is AI-generated), no drawings, no nothing of that sort. ''Actual photographs'' of the subject, nothing else. Articles are not required to have images at all; no image whatsoever is preferable to something which is ''not'' an image of the person. ] <small><sup>]</sup></small> 05:42, 3 January 2025 (UTC)
*'''No, but with exceptions'''. I could imagine a case where a specific AI-generated image has some direct relevance to the notability of the subject of a BLP. In such cases, it should be included, if it could be properly licensed. But I do oppose AI-generated images as portraits of BLP subjects. —] (]) 01:27, 1 January 2025 (UTC)
*:Since I was pinged on this point: when I wrote "I do oppose AI-generated images as portraits", I meant exactly that, including all AI-generated images, such as those in a sketchy or artistic style, not just the photorealistic ones. I am not opposed to certain uses of AI-generated images in BLPs when they are not the main portrait of the subject, for instance in diagrams (not depicting the subject) to illustrate some concept pioneered by the subject, or in case someone becomes famous for being the subject of an AI-generated image. —] (]) 05:41, 3 January 2025 (UTC)
*'''No''', and no exceptions or do-overs. Better to have no images (or Stone-Age style cave paintings) than ''Frankenstein'' images, no matter how accurate or artistic. Akin to shopped manipulated photographs, they should have no room (or room service) at the WikiInn. ] (]) 01:34, 1 January 2025 (UTC)
*:Some "shopped manipulated photographs" are misleading and inaccurate, others are not. We can and do exclude the former from the parts of the encyclopaedia where they don't add value without specific policies and without excluding them where they are relevant (e.g. ]) or excluding those that are not misleading or inaccurate. AI images are no different. ] (]) 02:57, 1 January 2025 (UTC)
*::Assuming we know. Assuming it's material. The infobox image in – and the only extant photo of – ] was "photoshopped" by a marketing team, maybe half a century before Adobe Photoshop was created. They wanted to show him wearing a necktie. I don't think that this level of manipulation is actually a problem. ] (]) 07:44, 2 January 2025 (UTC)
*'''Yes''', so long as it is an accurate representation. ] ] 03:40, 1 January 2025 (UTC)
*'''No''' not for BLPs. ] (]) 04:15, 1 January 2025 (UTC)
*'''No''' Not at all relevant for pictures of people, as the accuracy is not enough and can misrepresent. Also (and I'm shocked as it seems no one has mentioned this), what about Copyright issues? Who holds the copyright for an AI-generated image? The user who wrote the prompt? The creator(s) of the AI model? The creator(s) of the images in the database that the AI used to create the images? It's sounds to me such a clusterfuck of copyright issues that I don't understand how this is even a discussion. --] (]) 07:10, 1 January 2025 (UTC)
*:Under the US law / copyright office, machine-generated images including those by AI cannot be copyrighted. That also means that AI images aren't treated as derivative works.<br style="margin-bottom:0.5em"/>What is still under legal concern is whether the use of bodies of copyrighted works without any approve or license from the copyright holders to train AI models is under fair use or not. There are multiple court cases where this is the primary challenge, and none have yet to reach a decision yet. Assuming the courts rule that there was no fair use, that would either require the entity that owns the AI to pay fines and ongoing licensing costs, or delete their trained model to start afresh with free licensed/works, but in either case, that would not impact how we'd use any resulting AI image from a copyright standpoint.<span id="Masem:1735741774879:WikipediaFTTCLNVillage_pump_(policy)" class="FTTCmt"> — ] (]) 14:29, 1 January 2025 (UTC)</span>
*'''No''', I'm in agreeance with ] here. Whether we like it or not, the usage of a portrait on an article implies that it's just that, a portrait. It's incredibly disingenuous to users to represent an AI generated photo as truth. ] (]) 09:32, 1 January 2025 (UTC)
*:So you just said a portrait can be used because wikipedia tells you it's a portrait, and thus not a real photo. Can't AI be exactly the same? As long as we tell readers it is an AI representation? Heck, most AI looks closer to the real thing than any portrait. ] (]) 10:07, 2 January 2025 (UTC)
*::To clarify, I didn't mean "portrait" as in "painting," I meant it as "photo of person."
*::However, I really want to stick to what you say at the end there: {{tq|Heck, most AI looks closer to the real thing than any portrait.}}
*::That's exactly the problem: by looking close to the "real thing" it misleads users into believing a non-existent source of truth.{{br|2}}
*::Per the wording of the RfC of "{{tq|depict BLP subjects}}," I don't think there would be any valid case to utilize AI images. I hold a strong No. ] (]) 04:15, 3 January 2025 (UTC)
*'''No.''' We should not use AI-generated images for situations like this, they are basically just guesswork by a machine as Quark said and they can misinform readers as to what a person looks like. Plus, there's a big grey area regarding copyright. For an AI generator to know what somebody looks like, it has to have photos of that person in its dataset, so it's very possible that they can be considered derivative works or copyright violations. Using an AI image (derivative work) to get around the fact that we have no free images is just fair use with extra steps. ] (]) 19:33, 1 January 2025 (UTC) ]?]]
*'''Maybe''' There was a prominent BLP image which we displayed on the ]. ''(right)'' This made me uneasy because it was an artistic impression created from photographs rather than life. And it was "colored digitally". Functionally, this seems to be exactly the same sort of thing as the ] composite. The issue should not be whether there's a particular technology label involved but whether such creative composites and artists' impressions are acceptable as better than nothing. ]🐉(]) 08:30, 1 January 2025 (UTC)
*:Except it is clear to everyone that the illustration to the right is a sketch, a human rendition, while in the photorealistic image above, it is less clear. '']'' (] — ]) 14:18, 1 January 2025 (UTC)
*::Except it says right below it "AI-generated image of Laurence Boccolini." How much more clear can it be when it say point-blank "AI-generated image." ] (]) 10:12, 2 January 2025 (UTC)
*:::Commons descriptions do not appear on our articles. ] (]) 10:28, 2 January 2025 (UTC)
*:::People taking a quick glance at an infobox image that looks pretty like a photograph are not going to scrutinize commons tagging. '']'' (] — ]) 14:15, 2 January 2025 (UTC)
*::Keep in mind that many AIs can produce works that match various styles, not just photographic quality. It is still possible for AI to produce something that looks like a watercolor or sketched drawing.<span id="Masem:1735742005673:WikipediaFTTCLNVillage_pump_(policy)" class="FTTCmt"> — ] (]) 14:33, 1 January 2025 (UTC)</span>
*:::Yes, you're absolutely right. But so far photorealistic images have been the most common to illustrate articles (see ] for some examples. '']'' (] — ]) 14:37, 1 January 2025 (UTC)
*::::Then push to ban photorealistic images, rather than pushing for a blanket ban that would also apply to obvious sketches. —] (]) 20:06, 1 January 2025 (UTC)
*:::::Same thing I wrote above, but for "photoshopping" read "drawing": (Bold added for emphasis)
*:::::{{tqq|...human is not going to change or distort a person's appearance in the same way an AI image would. done by a person who is paying attention to what they are doing by '''person who is aware, while they are making , that they might be distorting the image and is, I only assume, trying to minimise it''' – those careful modifications shouldn't be equated with something made up by an AI image generator.}} '']'' (] — ]) 20:56, 1 January 2025 (UTC)
*::::::@] then why are you advocating for a ban on AI images rather than a ban on distorted images? Remember that with careful modifications by someone who is aware of what they are doing that AI images can be made more accurate. Why are you assuming that a human artist is trying to minimise the distortions but someone working with AI is not? ] (]) 22:12, 1 January 2025 (UTC)
*:::::::I believe that AI-generated images are fundamentally misleading because they are a simulation by a machine rather than a drawing by a human. To quote pythoncoder above: {{tqq|The use of AI-generated images to depict people (living or otherwise) is fundamentally misleading, because the images are not actually depicting the person.}} '']'' (] — ]) 00:16, 2 January 2025 (UTC)
*::::::::Once again your actual problem is not AI, but with misleading images. Which can be, and are, already a violation of policy. ] (]) 01:17, 2 January 2025 (UTC)
*:::::::::I think all AI-generated images, except simple diagrams as WhatamIdoing point out above, are misleading. So yes, my problem is with misleading images, which includes all photorealistic images generated by AI, which is why I support this proposal for a blanket ban in BLPs and medical articles. '']'' (] — ]) 02:30, 2 January 2025 (UTC)
*::::::::::To clarify, I'm willing to make an exception in this proposal for very simple geometric diagrams. '']'' (] — ]) 02:38, 2 January 2025 (UTC)
*::::::::::Despite the fact that not all AI-generated images are misleading, not all misleading images are AI-generated and it is not always possible to tell whether an image is or is not AI-generated? ] (]) 02:58, 2 January 2025 (UTC)
*:::::::::::Enforcement is a separate issue. Whether or not all (or the vast majority) of AI images are misleading is the subject of this dispute.
*:::::::::::I'm not going to mistreat the horse further, as we've each made our points and understand where the other stands. '']'' (] — ]) 15:30, 2 January 2025 (UTC)
*::::::::::Even "simple diagrams" are not clear-cut. The process of AI-generating any image, no matter how simple, is still very complex and can easily follow any number of different paths to meet the prompt constraints. These paths through embedding space are black boxes and the likelihood they converge on the same output is going to vary wildly depending on the degrees of freedom in the prompt, the dimensionality of the embedding space, token corpus size, etc. The only thing the user can really change, other than switching between models, is the prompt, and at some point constructing a prompt that is guaranteed to yield the same result 100% of the time becomes a ] exercise. This is in contrast with non-generative AI diagram-rendering software that follow very fixed, reproducible, ''known'' paths. ] (]) 04:44, 2 January 2025 (UTC)
*:::::::::::Why does the path matter? If the output is correct it is correct no matter what route was taken to get there. If the output is incorrect it is incorrect no matter what route was taken to get there. If it is unknown or unknowable whether the output is correct or not that is true no matter what route was taken to get there. ] (]) 04:48, 2 January 2025 (UTC)
*::::::::::::If I use BioRender or GraphPad to generate a figure, I can be confident that the output does not have errors that would misrepresent the underlying data. I don't have to verify that all 18,000 data points in a scatter plot exist in the correct XYZ positions because I know the method for rendering them is published and empirically validated. Other people can also be certain that the process of getting from my input to the product is accurate and reproducible, and could in theory reconstruct my raw data from it. AI-generated figures have no prescribed method of transforming input beyond what the prompt entails; therefore I additionally have to be confident in how precise my prompt is ''and'' confident that the training corpus for this procedure is so accurate that no error-producing paths exist (not to mention absolutely certain that there is no embedded contamination from prior prompts). Other people have all those concerns, and on top of that likely don't have access to the prompt or the raw data to validate the output, nor do they necessarily know how fastidious I am about my generative AI use. At least with a hand-drawn diagram viewers can directly transfer their trust in the author's knowledge and reliability to their presumptions about the diagram's accuracy. ] (]) 05:40, 2 January 2025 (UTC)
*:::::::::::::If you've got 18,000 data points, we are beyond the realm of "simple geometric diagrams". ] (]) 07:47, 2 January 2025 (UTC)
*::::::::::::::The original "simple geometric diagrams" comment was referring to your 100 dots image. I don't think increasing the dots materially changes the discussion beyond increasing the laboriousness of verifying the accuracy of the image. ] (]) 07:56, 2 January 2025 (UTC)
*:::::::::::::::Yes, but since "the laboriousness of verifying the accuracy of the image" is exactly what she doesn't want to undertake for 18,000 dots, then I think that's very relevant. ] (]) 07:58, 2 January 2025 (UTC)
*:{{outdent|14}} And where is that cutoff supposed to be? 1000 dots? A single straight line? An atomic diagram? What is "simple" to someone unfamiliar with a topic may be more complex.{{pb}}And I don't want to count 100 dots either! ] (]) 17:43, 2 January 2025 (UTC)
*::Maybe you don't. But I know for certain that you can count 10 across, 10 down, and multiply those two numbers to get 100. That's what I did when I made the image, after all. ] (]) 07:44, 3 January 2025 (UTC)
* '''Comment''': when you Google search someone (at least from the Chrome browser), often the link to the Misplaced Pages article includes a thumbnail of the lead photo as a preview. Even if the photo is labelled as an AI image in the article, people looking at the thumbnail from Google would be misled (if the image is chosen for the preview). ] (]) 09:39, 1 January 2025 (UTC)
*:This is why we should not use inaccurate images, regardless of how the image was created. It has absolutely nothing to do with AI. ] (]) 11:39, 1 January 2025 (UTC)
* '''Already opposed a blanket ban''': It's unclear to me why we have a separate BLP subsection, as BLPs are already included in the main section above. Anyway, I ] there. ] (])
*:Some editors might oppose a blanket ban on ''all'' AI-generated images, while at the same time, are against using AI-generated images (created by using text prompts/]) to depict ]. ] (]) 14:32, 1 January 2025 (UTC)
*'''No''' For at least now, let's not let the problems of AI intrude into BLP articles which need to have the highest level of scrutiny to protect the person represented. Other areas on WP may benefit from AI image use, but let's keep it far out of BLP at this point. --] (]) 14:35, 1 January 2025 (UTC)
*I am not a fan of “banning” AI images completely… but I agree that BLPs require special handling. I look at AI imagery as being akin to a computer generated painting. In a BLP, we allow paintings of the subject, but we ''prefer'' photos over paintings (if available). So… we should prefer photos over AI imagery. {{pb}}<!--list syntax fixed ~ToBeFree--> That said, AI imagery is getting good enough that it can be mistaken for a photo… so… If an AI generated image ''is'' the ''only'' option (ie there is no photo available), then the caption should ''clearly'' indicate that we are using an AI generated image. And that image should be replaced as soon as possible with an actual photograph. ] (]) 14:56, 1 January 2025 (UTC)
*:The issue with the latter is that Misplaced Pages images get picked up by Google and other search engines, where the caption isn't there anymore to add the context that a photorealistic image was AI-generated. ] (] · ]) 15:27, 1 January 2025 (UTC)
*::We're here to build an encyclopedia, not to protect commercial search engine companies.
*::I think my view aligns with Blueboar's (except that I find no firm preference for photos over classical portrait paintings): We shouldn't have ''inaccurate'' AI images of people (living or dead). But the day appears to be coming when AI will generate accurate ones, or at least ones that are close enough to accurate that we can't tell the difference unless the uploader voluntarily discloses that information. Once we can no longer tell the difference, what's the point in banning them? Images need to look like the thing being depicted. When we put an photorealistic image in an article, we could be said to be implicitly claiming that the image ''looks like'' whatever's being depicted. We are not ''necessarily'' warranting that the image was created through a specific process, but the image really does need to look like the subject. ] (]) 03:12, 2 January 2025 (UTC)
*:::You are presuming that sufficient accuracy will prevent us from knowing whether someone is uploading an AI photo, but that is not the case. For instance, if someone uploads large amounts of "photos" of famous people, and can't account for how they got them (e.g. can't give a source where they scraped them from, or dates or any Exif metadata at all for when they were taken), then it will still be obvious that they are likely using AI. ] (]) 17:38, 3 January 2025 (UTC)
*:::As another editor pointed out in their comment, there's the {{blue|ethics/moral dilemma of creating fake photorealistic pictures of people and putting them on the internet}}, especially on a site such as Misplaced Pages and especially on their own biography. ] says the bios {{tq|must be written conservatively and with regard for the subject's privacy.}} ] (]) 18:37, 3 January 2025 (UTC)
*:::{{tqq| Once we can no longer tell the difference, what's the point in banning them?}} Sounds like a wolf's in sheep's clothing to me. Just because the surface appeal of fake pictures gets better, doesn't mean we should ]. '']'' (] — ]) 18:47, 3 January 2025 (UTC)
*:If there are no appropriately-licensed images of a person, then by definition any AI-generated image of them will be either a copyright infringement or a complete fantasy. ] (]) 04:48, 2 January 2025 (UTC)
*::Whether it would be a copyright infringement or not is both an unsettled legal question and not relevant: If an image is a copyvio we can't use it and it is irrelevant why it is a copyvio. If an image is a "complete fantasy" then it is exactly as unusable as a complete fantasy generated by non-AI means, so again AI is irrelevant. I've had to explain this multiple times in this discussion, so read that for more detail and note the lack of refutation. ] (]) 04:52, 2 January 2025 (UTC)
*:::But we can assume good faith that a human isn't blatantly copying something. We can't assume that from an LLM like Stability AI which has been shown to from Getty's images. ] (]) 05:50, 2 January 2025 (UTC)
*::::Ooooh, I'm not sure that we can assume that humans aren't blatantly copying something. We can assume that they meant to be helpful, but that's not quite the same thing. ] (]) 07:48, 2 January 2025 (UTC)
*<s>'''Oppose.'''</s> '''Yes.''' I echo ]: {{Tq2|What this conversation is really circling around is banning entire skillsets from contributing to Misplaced Pages merely because some of us are afraid of AI images and some others of us want to engineer a convenient, half-baked, policy-level "consensus" to point to when they delete quality images from Misplaced Pages. Every time someone generates text based on a source, they are doing some acceptable level of interpretation to extract facts or rephrase it around copyright law, and I don't think illustrations should be considered so severely differently as to justify a categorical ban. For instance, the Gisele Pelicot portrait is based on non-free photos of her. Once the illustration exists, it is trivial to compare it to non-free images to determine if it is an appropriate likeness, which it is. That's no different than judging contributed text's compliance with fact and copyright by referring to the source. It shouldn't be treated differently just because most Wikipedians contribute via text.<br/>Additionally, referring to interpretive skillsets that synthesize new information like, random example, statistical analysis. Excluding those from Misplaced Pages is current practice and not controversial. Meanwhile, I think the ability to create images is more fundamental than that. It's not (inheretly) synthesizing new information. A portrait of a person (alongside the other examples in this thread) contains verifiable information. It is current practice to allow them to fill the gaps where non-free photos can't. That should continue. Honestly, it should expand.}} ] (]) 15:41, 1 January 2025 (UTC)
*:Additionally, in direct response to "these images are fake": All illustrations of a subject could be called "fake" because they are not photographs. (Which can also be faked.) The standard for the inclusion of an illustration on Misplaced Pages has never been photorealism, medium, or previous publication in a RS. The standard is how adequately it reflects the facts which it claims to depict. If there is a better image that can be imported to Misplaced Pages via fair use or a license, then an image can be easily replaced. Until such a better image has been sourced, it is absolutely bewildering to me that we would even discuss removing images of people from their articles. What a person looked like is one of the most basic things that people want to know when they look someone up on Misplaced Pages. Including an image of almost any quality (yes, even a cartoon) is practically by definition an improvement to the article and addressing an important need. We should be encouraging artists to continue filling the gaps that non-free images cannot fill, not creating policies that will inevitably expand into more general prejudices against all new illustrations on Misplaced Pages. ] (]) 15:59, 1 January 2025 (UTC)
*::By "Oppose", I'm assuming your answer to the RfC question is "Yes". And this RfC is about using {{blue|AI-generated images (generated via text prompts, see also: ])}} to depict BLP subjects, not regarding human-created drawings/cartoons/sketches, etc. of BLPs. ] (]) 16:09, 1 January 2025 (UTC)
*:::I've changed it to "yes" to reflect the reversed question. I think all of this is related because there is no coherent distinguishing point; AI can be used to create images in a variety of styles. These discussions have shown that a policy of banning AI images ''will'' be used against non-AI images of all kinds, so I think it's important to say these kinds of things now. ] (]) 16:29, 1 January 2025 (UTC)
*::Photorealistic images scraped from who knows where from who knows what sources are without question simply fake photographs and also clear ] and outright ]. There's no two ways about it. Articles do ''not'' require images: An article with some Frankenstein-ed image scraped from who knows what, where and, when that you "created" from a prompt is not an improvement over having no image at all. If we can't provide a quality image (like something you didn't cook up from a prompt) then people can find quality, non-fake images elsewhere. ] (]) 23:39, 1 January 2025 (UTC)
*:::I really encourage you to read the discussion I linked before because it is ]. Images like these do not inherently include either OR or SYNTH, and the arguments that they do cannot be distinguished from any other user-generated image content. But, briefly, I never said articles required images, and this is not about what articles ''require''. It is about ''improvements'' to the articles. Including a relevant picture where none exists is almost always an improvement, especially for subjects like people. Your disdain for the method the person used to make an image is irrelevant to whether the content of the image is actually verifiable, and the only thing we ought to care about is the content. ] (]) 03:21, 2 January 2025 (UTC)
*::::Images like these are absolutely nothing more than synthesis in the purest sense of the world and are clearly a violation of ]: Again, you have no idea what data was used to generate these images and you're going to have a very hard time convincing anyone to describe them as anything other than outright fakes.
*::::A reminder that WP:SYNTH shuts down attempts at manipulation of images ("It is not acceptable for an editor to use photo manipulation to distort the facts or position illustrated by an image. Manipulated images should be prominently noted as such. Any manipulated image where the encyclopedic value is materially affected should be posted to Misplaced Pages:Files for discussion. Images of living persons must not present the subject in a false or disparaging light.") and generating a photorealistic image (from who knows what!) is far beyond that.
*::::Fake images of people do not improve our articles in any way and only erode reader trust. What's next, an argument for the ''fake sources'' LLMs also love to "hallucinate"? ] (]) 03:37, 2 January 2025 (UTC)
*:::::So, if you review the first sentence of SYNTH, you'll see it has no special relevance to this discussion: {{Tq|Do not combine material from multiple sources to state or imply a conclusion not explicitly stated by any of the sources.}}. My primary example has been a picture of a person; what a person looks like is verifiable by comparing the image to non-free images that cannot be used on Misplaced Pages. If the image resembles the person, it is not SYNTH. An illustration of a person created and intended to look like that person is not a manipulation. The training data used to make the AI is irrelevant to whether the image in fact resembles the person. You should also review ] because SYNTH is not a policy; NOR is the policy: {{tq|If a putative SYNTH doesn't constitute original research, then it doesn't constitute SYNTH.}} Additionally, ]. A categorical rule against AI cannot be justified by SYNTH because it does not categorically apply to all use cases of AI. To do so would be illogical on top of ill-advised. ] (]) 08:08, 2 January 2025 (UTC)
*::::::"training data used to make the AI is irrelevant" — spoken like a true AI evangelist! Sorry, 'good enough' photorealism is still just synthetic slop, a fake image presented as real of a ''human being''. A fake image of someone generated from who-knows-what that 'resembles' an article's subject is about as ] as it gets. Yikes. As for the attempts to pass of prompt-generated photorealistic fakes of people as somehow the same as someone's illustration, you're completely wasting your time. ] (]) 09:44, 2 January 2025 (UTC)
*:::::::NOR is a content policy and SYNTH is content guidance within NOR. Because you have admitted that this is not ''about the content'' for you, NOR and SYNTH are irrelevant to your argument, which boils down to ] and, now, inaccurate personal attacks. Continuing this discussion between us would be pointless. ] (]) 09:52, 2 January 2025 (UTC)
*::::::::This is in fact entirely about content (why the hell else would I bother?) but it is true that I also dismissed your pro-AI 'it's just like a human drawing a picture!' as outright nonsense a while back. Good luck convincing anyone else with that line - it didn't work here. ] (]) 09:59, 2 January 2025 (UTC)
*'''Maybe''': there is an implicit assumption with this RFC that an AI generated image would be photorealistic. There hasn't been any discussion of an AI generated sketch. If you asked an AI to generate a sketch (that clearly looked like a sketch, similar to the Gisèle Pelicot example) then I would potentially be ok with it. ] (]) 18:14, 1 January 2025 (UTC)
*:That's an interesting thought to consider. At the same time, I worry about (well-intentioned) editors inundating image-less BLP articles with AI-generated images in the style of cartoons/sketches (if only photorealistic ones are prohibited) etc. At least requiring a human to draw/paint/whatever creates a barrier to entry; these AI-generated images can be created in under a minute using these text-to-image models. Editors are already wary about human-created cartoon portraits (]), now they'll be tasked with dealing with AI-generated ones in BLP articles. ] (]) 20:28, 1 January 2025 (UTC)
*::It sounds like your problem is not with AI but with cartoon/sketch images in BLP articles, so AI is once again completely irrelevant. ] (]) 22:14, 1 January 2025 (UTC)
*::That is a good concern you brought up. There is a possibility of the spamming of low quality AI-generated images which would be laborious to discuss on a case-by-case basis but easy to generate. At the same time though that is a possibility, but not yet an actuality, and ] states that new policies should address current problems rather than hypothetical concerns. ] (]) 22:16, 1 January 2025 (UTC)
*Easy '''no''' for me. I am not against the use of AI images wholesale, but I do think that using AI to represent an existent thing such as a person or a place is too far. Even a tag wouldn't be enough for me. ] </nowiki></span>''']] 19:05, 1 January 2025 (UTC)
*'''No''' obviously, per previous discussions about cartoonish drawn images in BLPs. Same issue here as there, it is essentially original research and misrepresentation of a living person's likeness. ] (]) 22:19, 1 January 2025 (UTC)
*'''No''' to photorealistic, no to cartoonish... this is not a hard choice. The idea that "this has nothing to do with AI" when "AI" magnifies the problem to stupendous proportions is just not tenable. ] (]) 23:36, 1 January 2025 (UTC)
*:While AI might "amplify" the thing you dislike, that does not make AI the problem. The problem is whatever underlying thing is being amplified. ] (]) 01:16, 2 January 2025 (UTC)
*::The thing that amplifies the problem is necessarily a problem. ] (]) 02:57, 2 January 2025 (UTC)
*:::That is arguable, but banning the amplifier does not do anything to solve the problem. In this case, banning the amplifier would cause multiple other problems that nobody supporting this proposal as even attempted to address, let alone mitigate. ] (]) 03:04, 2 January 2025 (UTC)
*'''No''' for all people, per Chaotic Enby. ] (]) 03:23, 2 January 2025 (UTC) Add: no to any AI-generated images, whether photorealistic or not. ] (]) 04:00, 3 January 2025 (UTC)
*'''No''' - We should not be hosting faked images (except as notable fakes). We should also not be hosting copyvios ({{tq|"Whether it would be a copyright infringement or not is both an unsettled legal question and not relevant"}} is just totally wrong - we should be steering clear of copyvios, and if the issue is unsettled then we shouldn't use them until it is).
*If people upload faked images to WP or Commons the response should be as it is now. The fact that fakes are becoming harder to detect simply from looking at them hardly affects this - we simply confirm when the picture was supposed to have been taken and examine the plausibility of it from there. ] (]) 14:39, 2 January 2025 (UTC) ] (]) 14:39, 2 January 2025 (UTC)
*:{{tpq|we should be steering clear of copyvio}} we do - if an image is a copyright violation it gets deleted, regardless of why it is a copyright violation. What we do not do is ban using images that are not copyright violations because they are copyright violations. Currently the WMF lawyers and all the people on Commons who know more about copyright than I do say that at least some AI images are legally acceptable for us to host and use. If you want to argue that, then go ahead, but it is not relevant to ''this'' discussion.
*:{{tpq|if people upload faked images the response should be as it is now}} in other words you are saying that the problem is faked images not AI, and that current policies are entirely adequate to deal with the problem of faked images. So we don't need any specific rules for AI images - especially given that not all AI images are fakes. ] (]) 15:14, 2 January 2025 (UTC)
*::The idea that {{tq|current policies are entirely adequate}} is like saying that a lab shouldn't have specific rules about wearing eye protection when it already has a poster hanging on the wall that says "don't hurt yourself". ] (]) 18:36, 2 January 2025 (UTC)
*:::I rely on one of those up in my workshop at home. I figure if that doesn't keep me safe, nothing will. ] (]) 18:41, 2 January 2025 (UTC)
*::::"{{tq|in other words you are saying that the problem is faked images not AI}}" - AI generated images *are* fakes. This is merely confirming that for the avoidance of doubt.
*::::"{{tq|at least some AI images are legally acceptable for us}}" - Until they decide which ones that isn't much help. ] (]) 19:05, 2 January 2025 (UTC)
*:::::Yes – what FOARP said. AI-generated images are fakes and are misleading. '']'' (] — ]) 19:15, 2 January 2025 (UTC)
*:::Those specific rules exist because generic warnings have proven not to be sufficient. Nobody has presented any evidence that the current policies are not sufficient, indeed quite the contrary. ] (]) 19:05, 2 January 2025 (UTC)
*'''No!''' This would be a massive can of worms; perhaps, however, we wish to cause problems in the new year. ] <small>(]) | :) | he/him | </small> 15:00, 2 January 2025 (UTC)
*:Noting that I think that no AI-generated images are acceptable in BLP articles, regardless of whether they are photorealistic or not. ] <small>(]) | :) | he/him | </small> 15:40, 3 January 2025 (UTC)
*'''No''', unless the AI image has encyclopedic significance beyond "depicts a notable person". AI images, if created by editors for the purpose of inclusion in Misplaced Pages, convey little reliable information about the person they depict, and the ways in which the model works are opaque enough to most people as to raise verifiability concerns. ] (] • ]) 15:25, 2 January 2025 (UTC)
*:To clarify, do you object to uses of an AI image in a BLP when the subject uses that image for self-identification? I presume that AI images that have been the subject of notable discussion are an example of "significance beyond depict a notable person"? ] (]) 15:54, 2 January 2025 (UTC)
*::If the subject uses the image for self-identification, I'd be fine with it - I think that'd be analogous to situations such as "cartoonist represented by a stylized self-portrait", which definitely has some precedent in articles like ]. I agree with your second sentence as well; if there's notable discussion around a particular AI image, I think it would be reasonable to include that image on Misplaced Pages. ] (] • ]) 19:13, 2 January 2025 (UTC)
* '''No''', with obvious exceptions, including if the subject theyrself uses the image as a their representation, or if the image is notable itself. Not including the lack of a free aleternative, if there is no free alternative... where did the AI find data to build an image... non free too. Not including images generated by WP editors (that's kind of ]... - ] (]) 18:02, 2 January 2025 (UTC
*'''Maybe''' I think the question is unfair as it is illustrated with what appears to be a photo of the subject but isn't. People are then getting upset that they've been misled. As others note, there are copyright concerns with AI reproducing copyrighted works that in turn make an image that is potentially legally unusable. But that is more a matter for Commons than for Misplaced Pages. As many have noted, a sketch or painting never claims to be an accurate depiction of a person, and I don't care if that sketch or painting was done by hand or an AI prompt. I strongly ask ] to abort the RFC. You've asked people to give a yes/no vote to what is a more complex issue. A further problem with the example used is the unfortunate prejudice on Misplaced Pages against user-generated content. While the text-generated AI of today is crude and random, there will come a point where many professionally published photos illustrating subjects, including people, are AI generated. Even today, your smartphone can create a groupshot where everyone is smiling and looking at the camera. It was "trained" on the 50 images it quickly took and responded to the build-in "text prompt" of "create a montage of these photos such that everyone is smiling and looking at the camera". This vote is a knee jerk reaction to content that is best addressed by some other measure (such as that it is a misleading image). And a good example of asking people to vote way too early, when the issues haven't been throught out -- ]°] 18:17, 2 January 2025 (UTC)
*'''No''' This would very likely set a dangerous precedent. The only exception I think should be if the image itself is notable. If we move forward with AI images, especially for BLPs, it would only open up a whole slew of regulations and RfCs to keep them in check. Better no image than some digital multiverse version of someone that is "basically" them but not really. Not to mention the ethics/moral dilemma of creating fake photorealistic pictures of people and putting them on the internet. ] (]) 18:31, 2 January 2025 (UTC)
*'''No'''. LLMs don't generate answers, they generate ''things that look like'' answers, but aren't; a lot of the time, that's good enough, but sometimes it very much isn't. It's the same issue for text-to-image models: they don't generate photos of people, they generate ''things that look like'' photos. Using them on BLPs is unacceptable. ] (]) 19:30, 2 January 2025 (UTC)
*'''No'''. I would be pissed if the top picture of me on Google was AI-generated. I just don't think it's moral for living people. The exceptions given above by others are okay, such as if the subject uses the picture themselves or if the picture is notable (with context given). ] (]) 19:56, 2 January 2025 (UTC)
*'''No.''' Uploading alone, although mostly a Commons issue, would already a problem to me and may have personality rights issues. Illustrating an article with a fake photo <ins>(or drawing)</ins> of a living person, even if it is labeled as such, would not be acceptable. For example, it could end up being shown by search engines or when hovering over a Misplaced Pages link, without the disclaimer. ] (]) 23:54, 2 January 2025 (UTC)
* I was going to say no... but we allow paintings as portraits in BLPs. What's so different between an AI generated image, and a painting? Arguments above say the depiction may not be accurate, but the same is true of some paintings, right? (and conversely, not true of other paintings) ] (]) 00:48, 3 January 2025 (UTC)
*::A painting is clearly a painting; as such, the viewer knows that it is not an accurate representation of a particular reality. An AI-generated image made to look exactly like a photo, looks like a photo but is not.
*:] (]) 02:44, 3 January 2025 (UTC)
*::Not all paintings are clearly paintings. Not all AI-generated images are made to look like photographs. Not all AI-generated images made to look like photos do actually look like photos. This proposal makes no distinction. ] (]) 02:55, 3 January 2025 (UTC)
*:::Not to mention, hyper-realism is a style an artist may use in virtually any medium. If Misplaced Pages would accept an analog substitute like a painting, there's no reason Misplaced Pages shouldn't accept an equivalent painting made with digital tools, and there's no reason Misplaced Pages shouldn't accept an equivalent painting made with AI. That is, one where any obvious defects have been edited out and what remains is a straightforward picture of the subject. ] (]) 03:45, 3 January 2025 (UTC)
*::::For the record (and for any media watching), while I personally find it fascinating that a few editors here are spending a substantial amount of time (in the face of an overwhelming 'absolutely not' consensus no less) attempting to convince others that computer-generated (that is, ''faked'') photos of human article subjects are somehow ''a good thing'', I also find it interesting that these editors seem to express absolutely no concern for the intensely negative reaction they're already seeing from their fellow editors and seem totally unconcerned about the inevitable trust drop we'd experience from Misplaced Pages readers when they would encounter fake photos on our BLP articles especially. ] (]) 03:54, 3 January 2025 (UTC)
*:::::Misplaced Pages's reputation would not be affected positively or negatively by expanding the current-albeit-sparse use of illustrations to depict subjects that do not have available pictures. In all my writing about this over the last few days, you are the only one who has said anything negative about me as a person or, really, my arguments themselves. As loath as I am to cite it, ] means assuming that people you disagree with are not ''trying to hurt Misplaced Pages.'' Thryduulf, I, and others have explained in detail why we think our ultimate ideas are explicit benefits to Misplaced Pages and why our opposition to these immediate proposals comes from a desire to prevent harm to Misplaced Pages. I suggest taking a break to reflect on that, matey. ] (]) 04:09, 3 January 2025 (UTC)
*::::::Look, I don't know if you've been living under a rock or what for the past few years but the reality is that '' people hate AI images'' and dumping a ton of AI/fake images on Misplaced Pages, a place people go for ''real information'' and often ''trust'', inevitably leads to a huge trust issue, something Misplaced Pages is increasingly suffering from already. This is ''especially'' a problem when they're intended to represent ''living people'' (!). I'll leave it to you to dig up the bazillion controversies that have arisen and continue to arise since companies worldwide have discovered that they can now replace human artists with 'AI art' produced by "prompt engineers" but you can't possibly expect us to ignore that reality when discussing these matters. ] (]) 04:55, 3 January 2025 (UTC)
*:::::::Those trust issues are born from the publication of hallucinated information. I have only said that it should be OK to use an image on Misplaced Pages when it contains only verifiable information, which is the same standard we apply to text. That standard is and ought to be applied independently of the way the initial version of an image was created. ] (]) 06:10, 3 January 2025 (UTC)
*:To my eye, the distinction between AI images and paintings here is less a question of medium and more of verifiability: the paintings we use (or at least the ones I can remember) are significant paintings that have been acknowledged in sources as being reasonable representations of a given person. By contrast, a purpose-generated AI image would be more akin to me painting a portrait of somebody here and now and trying to stick that on their article. The image could be a faithful representation <small>(unlikely, given my lack of painting skills, but let's not get lost in the metaphor)</small>, but if my painting hasn't been discussed anywhere besides Misplaced Pages, then it's potentially OR or UNDUE to enshrine it in mainspace as an encyclopedic image. ] (] • ]) 05:57, 3 January 2025 (UTC)
*::An image contains a collection of facts, and those facts need to be verifiable just like any other information posted on Misplaced Pages. An image that verifiably resembles a subject as it is depicted in reliable sources is categorically ''not OR''. Discussion in other sources is not universally relevant; we don't restrict ourselves to only previously-published images. If we did that, Misplaced Pages would have very few images. ] (]) 06:18, 3 January 2025 (UTC)
*:::Verifiable how? Only by the editor themselves comparing to a real photo (which was probably used by the LLM to create the image…).
*:::These things are fakes. The analysis stops there. ] (]) 10:48, 4 January 2025 (UTC)
*::::Verifiable by comparing them to a reliable source. Exactly the same as what we do with text. There is no coherent reason to treat user-generated images differently than user-generated text, and the universalist tenor of this discussion has damaging implications for all user-generated images regardless of whether they were created with AI. Honestly, I rarely make arguments like this one, but I think it could show some intuition from another perspective: Imagine it's 2002 and Misplaced Pages is just starting. Most users want to contribute text to the encyclopedia, but there is a cadre of artists who want to contribute pictures. The text editors say the artists cannot contribute ANYTHING to Misplaced Pages because their images that have not been previously published are not verifiable. That is a double-standard that privileges the contributions of text-editors simply because most users are text-editors and they are used to verifying text; that is not a principled reason to treat text and images differently. Moreover, that is simply not what happened—The opposite happend, and images are treated as verifiable based on their contents just like text because that's a common sense reading of the rule. It would have been madness if images had been treated differently. And yet that is essentially the fundamentalist position of people who are extending their opposition to AI with arguments that apply to all images. If they are arguing verifiability seriously at all, they are pretending that the sort of degenerate situation I just described already exists when the opposite consensus has been reached consistently ''for years''. In ], they even tried to say Wikipedians had "turned a blind eye" to these image issues as if negatively characterizing those decisions would invalidate the fact that ''those decisions were consensus.'' The motivated reasoning of these discussions has been as blatant as that.<br/>At the bottom of this dispute, I take issue with trying to alter the rules in a way that creates a new double-standard within verifiability that applies to all images but not text. That's especially upsetting when (despite my and others' best efforts) so many of us are still focusing ''SOLELY'' on their hatred for AI rather than considering the obvious second-order consequences for user-generated images as a whole.<br/>Frankly, in no other context has any Wikipedian ever allowed me to say text they wrote was "fake" or challenge an image based on whether it was "fake." The issue has always been ''verifiability'', not provenance or falsity. Sometimes, IMO, that has lead to disaster and Misplaced Pages saying things I know to be factually untrue despite the contents of reliable sources. But ''that'' is the policy. We compare the contents of Misplaced Pages to reliable sources, and the contents of Misplaced Pages are considered verifiable if they cohere.<br/>I ask again: If Misplaced Pages's response to the creation of AI imaging tools is to crack down on all artistic contributions to Misplaced Pages (which seems to be the inevitable direction of these discussions), what does that say? If our negative response to AI tools is to ''limit what humans can do on Misplaced Pages'', what does that say? Are we taking a stand for human achievements, or is this a very heated discussion of cutting off our nose to save our face? ] (]) 23:31, 4 January 2025 (UTC)
*:::::{{tq|"Verifiable by comparing them to a reliable source"}} - comparing two images and saying that one ''looks like'' the other is not "verifying" anything. The text equivalent is presenting something as a quotation that is actually a user-generated paraphrasing.
*:::::{{tq|"Frankly, in no other context has any Wikipedian ever allowed me to say text they wrote was "fake" or challenge an image based on whether it was "fake.""}} - Try presenting a paraphrasing as a quotation and see what happens.
*:::::{{tq|"Imagine it's 2002 and Misplaced Pages is just starting. Most users want to contribute text to the encyclopedia, but there is a cadre of artists who want to contribute pictures..."}} - This basically happened, and is the origin of ]. Misplaced Pages is not a host for original works. ] (]) 22:01, 6 January 2025 (UTC)
*::::::{{tq|Comparing two images and saying that one looks like the other is not "verifying" anything.}} Comparing text to text in a reliable source is literally the same thing.
*::::::{{tq|The text equivalent is presenting something as a quotation that is actually a user-generated paraphrasing.}} No it isn't. The text equivalent is writing a sentence in an article and putting a ref tag on it. Perhaps there is room for improving the referencing of images in the sense that they should offer example comparisons to make. But an image created by a person is not unverifiable simply because it is user-generated. It is not somehow ''more'' unverifiable simply because it is created in a lifelike style.
*::::::{{tq|Try presenting a paraphrasing as a quotation and see what happens.}} Besides what I just said, ''nobody'' is even presenting these images as equatable to quotations. People in this thread have simply been calling them "fake" of their own initiative; the uploaders have not asserted that these are literal photographs to my knowledge. The uploaders of illustrations obviously did not make that claim either. (And, if the contents of the image is a copyvio, that is a separate issue entirely.)
*::::::{{tq|This basically happened, and is the origin of WP:NOTGALLERY.}} That is not the same thing. User-generated images that illustrate the subject are not prohibited by ]. Misplaced Pages is a host of encyclopedic content, and user-generated images can have encyclopedic content. ] (]) 02:41, 7 January 2025 (UTC)
*:::::::Images are way more complex than text. Trying to compare them in the same way is a very dangerous simplification. '']'' (] — ]) 02:44, 7 January 2025 (UTC)
*::::::::Assume only non-free images exist of a person. An illustrator refers to those non-free images and produces a painting. From that painting, you see a person who looks like the person in the non-free photographs. The image is verified as resembling the person. That is a simplification, but to call it "dangerous" is disingenuous at best. The process for challenging the image is clear. Someone who wants to challenge the veracity of the image would just need to point to details that do not align. For instance, "he does not typically have blue hair" or "he does not have a scar." That is what we already do, and it does not come up much because it would be weird to deliberately draw an image that looks nothing like the person. Additionally, someone who does not like the image for aesthetic reasons rather than encyclopedic ones always has the option of sourcing a photograph some other way like permission, fair use, or taking a new one themself. This is not an intractable problem. ] (]) 02:57, 7 January 2025 (UTC)
*:::::::::So a photorealistic AI-generated image would be considered acceptable until someone identifies a "big enough" difference? How is that anything close to ethical? An portrait that's got an extra mole or slightly wider nose bridge or lacks a scar is still ''not an image of the person'' regardless of whether random Misplaced Pages editors notice. And while I don't think user-generated non-photorealistic images should ever be used on biographies either, at least those can be traced back to a human who is ultimately responsible for the depiction, who can point to the particular non-free images they used as references, and isn't liable to average out details across all time periods of the subject. And that's not even taking into account the copyright issues. ] (]) 22:52, 7 January 2025 (UTC)
*::::::::::{{+1}} to what JoelleJay said. The problem is that AI-generated images are simulations trying to match existing images, sometimes, yes, with an impressive degree of accuracy. But they will always be inferior to a human-drawn painting that's ''trying to depict the person''. We're a human encyclopedia, and we're built by humans doing human things and sometimes with human errors. '']'' (] — ]) 23:18, 7 January 2025 (UTC)
*::::::::::You can't just raise this to an "ethical" issue by saying the word "ethical." You also can't just invoke copyright without articulating an actual copyright issue; we are not discussing copyvio. Everyone agrees that a photo with an actual copyvio in it is subject to that policy.
*::::::::::But to address your actual point: Any image—any ''photo''—beneath the resolution necessary to depict the mole would be missing the mole. Even with photography, we are never talking about science-fiction images that perfectly depict every facet of a person in an objective sense. We are talking about equipment that creates an approximation of reality. The same is true of illustrations and AI imagery.
*::::::::::Finally, a human being ''is'' responsible for the contents of the image because a human is selecting it and is responsible for correcting any errors. The result is an image that someone is choosing to use because they believe it is an appropriate likeness. We should acknowledge that human decision and evaluate it naturally—''Is it an appropriate likeness?'' ] (]) 10:20, 8 January 2025 (UTC)
*:::::::::::(Second comment because I'm on my phone.) I realize I should also respond to this in terms of additive information. What people look like is not static in the way your comment implies. Is it inappropriate to use a photo because they had a zit on the day it was taken? Not necessarily. Is an image inappropriate because it is taken at a bad angle that makes them look fat? Judging by the prolific ComicCon photographs (where people seem to make a game of choosing the worst-looking options; seriously, it's really bad), not necessarily. Scars and bruises exist and then often heal over time. The standard for whether an image with "extra" details is acceptable would still be based on whether it comports acceptably with other images; we literally do what you have capriciously described as "unethical" and supplement it with our compassionate desire to not deliberately embarrass BLPs. (The ComicCon images aside, I guess.) So, no, I would not be a fan of using images that add prominent scars where the subject is not generally known to have one, but that is just an unverifiable fact that does not belong in a Misplaced Pages image. Simple as. ] (]) 10:32, 8 January 2025 (UTC)
*:::::We don't evaluate the reliability of a source solely by comparing it to other sources. For example, there is an ongoing discussion at the baseball WikiProject talk page about the reliability of a certain web site. It lists no authors nor any information on its editorial control policy, so we're not able to evaluate its reliability. The reliability of all content being used as a source, including images, needs to be considered in terms of its provenance. ] (]) 23:11, 7 January 2025 (UTC)
* Can you note in your !vote whether AI-generated images (generated via text prompts/text-to-image models) that are ''not'' photo-realistic / hyper-realistic in style are okay to use to depict BLP subjects? For example, see the image to the right, which was ] then ] from his article: ] by ]]] {{pb}} Pinging people who !voted No above: ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ] --- ] (]) 03:55, 3 January 2025 (UTC) {{clear}}
*:Still no, I thought I was clear on that but we should not be using AI-generated images in articles for anything besides representing the concept of AI-generated images, or if an AI-generated image is notable or irreplaceable in its own right -- e.g, a musician uses AI to make an album cover.
*:(this isn't even a good example, it looks more like ])
*:] (]) 04:07, 3 January 2025 (UTC)
*:Was I unclear? ''No'' to all of them. ] (]) 04:13, 3 January 2025 (UTC)
*:Still '''no''', because carving out that type of exception will just lead to arguments down the line about whether a given image is too realistic. <span class="nowrap">—] (] | ])</span> 04:24, 3 January 2025 (UTC)
*:I still think '''no'''. My opposition isn't just to the fact that AI images are misinformation, but also that they essentially serve as a loophole for getting around Enwiki's image use policy. To know what somebody looks like, an AI generator needs to have images of that person in its dataset, and it draws on those images to generate a derivative work. If we have no free images of somebody and we use AI to make one, that's just using a fair use copyrighted image but removed by one step. The image use policy prohibits us from using fair use images for BLPs so I don't think we should entertain this loophole. If we ''do'' end up allowing AI images in BLPs, that just disqualifies the rationale of not allowing fair use in the first place. ] (]) 04:40, 3 January 2025 (UTC)
*:'''No''' those are not okay, as this will just cause arguments from people saying a picture is ''obviously'' AI-generated, and that it is therefore appropriate. As I mentionned above, there are some exceptions to this, which Gnomingstuff perfectly describes. Fake sketches/cartoons are not appropriate and provide little encyclopedic value. ] (]) 05:27, 3 January 2025 (UTC)
*:'''No''' to this as well, with the same carveout for individual images that have received notable discussion. Non-photorealistic AI images are going to be no more verifiable than photorealistic ones, and on top of that will often be lower-quality as images. ] (] • ]) 05:44, 3 January 2025 (UTC)
*:Thanks for the ping, yes I can, the answer is no. ] (]) 07:31, 3 January 2025 (UTC)
*:'''No''', and that image should be deleted before anyone places it into a mainspace article. Changing the RfC intro long after its inception seems a second bite at an apple that's not aged well. ] (]) 09:28, 3 January 2025 (UTC)
*::The RfC question has not been changed; another editor was the RfC question did not make a distinction between photorealistic/non-photorealistic AI-generated images, so I had to add and ping the editors who'd voted !No to clarify things. It has only been 3 days; there's still 27 more days to go. ] (]) 11:18, 3 January 2025 (UTC)
*:::Also answering '''No''' to this one per all the arguments above. "It has only been 3 days" is not a good reason to change the RfC question, especially since many people have already !voted and the "30 days" is mostly indicative rather than an actual deadline for a RfC. ] (] · ]) 14:52, 3 January 2025 (UTC)
*::::The RfC question hasn't been changed; see my response to Zaathras below. ] (]) 15:42, 3 January 2025 (UTC)
*:No, that's even a worse possible approach.<span id="Masem:1735910695864:WikipediaFTTCLNVillage_pump_(policy)" class="FTTCmt"> — ] (]) 13:24, 3 January 2025 (UTC)</span>
*:'''No'''. We're the human encyclopedia. We should have images drawn or taken by real humans who are trying to depict the ''subject'', not by machines trying to simulate an image. Besides, the given example is horribly drawn. '']'' (] — ]) 15:03, 3 January 2025 (UTC)
*:I like these even less than the photorealistic ones... This falls into the same basket for me: if we wouldn't let a random editor who drew this at home using conventional tools add it to the article why would we let a random editor who drew this at home using AI tools at it to the article? (and just to be clear the AI generated image of Germán Larrea Mota-Velasco is not recognizable as such) ] (]) 16:06, 3 January 2025 (UTC)
*:I said *NO*. ] (]) 10:37, 4 January 2025 (UTC)
*:'''No''' Having such images as said above means the AI had to use copyrighted pictures to create it and we shouldn't use it. --] (]) 01:12, 5 January 2025 (UTC)
*:Still '''no'''. If for no other reason than that it's a bad precedent. As others have said, if we make one exception, it will just lead to arguments in the future about whether something is "realistic" or not. I also don't see why we would need cartoon/illustrated-looking AI pictures of people in BLPs. ] (]) 20:43, 6 January 2025 (UTC)
*'''Absolutely not'''. These images are based on whatever the AI could find on the internet, with little to no regard for copyright. Misplaced Pages is better than this. ] (]) 10:16, 3 January 2025 (UTC)
*'''Comment''' The RfC question should not have been fiddled with, esp. for such a minor argument that the complai9nmant could have simply included in their own vote. I have no need to re-confirm my own entry. ] (]) 14:33, 3 January 2025 (UTC)
*:The RfC question hasn't been modified; I've only added a clarifying that these images can either be photorealistic in style or non-photorealistic in style. I pinged all the !No voters to make them aware. I could remove the Note if people prefer that I do (but the original RfC question is the ''exact same'' as it is now, so I don't think the addition of the Note makes a whole ton of difference). ] (]) 15:29, 3 January 2025 (UTC)
*'''No''' At this point it feels redundant, but I'll just add to the horde of responses in the negative. I don't think we can fully appreciate the issues that this would cause. The potential problems and headaches far outweigh whatever little benefit might come from AI images for BLPs. ]] 21:34, 3 January 2025 (UTC)
*'''Support temporary blanket ban''' with a posted expiration/requred rediscussion date of no more than two years from closing. AI as the term is currently used is very, very new. Right now these images would do more harm than good, but it seems likely that the culture will adjust to them. ] (]) 23:01, 3 January 2025 (UTC)
*'''No'''. Misplaced Pages is made ''by'' and ''for'' humans. I don't want to become . Adding an AI-generated image to a page whose topic isn't about generative AI makes me feel insulted. ] (]) 00:03, 4 January 2025 (UTC)
*'''No'''. Generative AI may have its place, and it may even have a place on Misplaced Pages in some form, but that place isn't in BLPs. There's no reason to use images of someone that do not exist over a real picture, or even something like a sketch, drawing, or painting. Even in the absence of pictures or human-drawn/painted images, I don't support using AI-generated images; they're not really pictures of the person, after all, so I can't support using them on articles of people. Using nothing would genuinely be a better choice than generated images. ] <span style="font-weight:bold">|</span> ] 01:07, 4 January 2025 (UTC)
*'''No''' due to reasons of copyright (AI harvests copyrighted material) and verifiability. ] <small>(])</small> 18:12, 4 January 2025 (UTC)
*'''No.''' Even if you are willing to ignore the inherently fraught nature of using AI-generated ''anything'' in relation to BLP subjects, there is simply little to no benefit that could possibly come from trying something like this. There's no guarantee the images will actually look like the person in question, and therefore there's no actual context or information that the image is providing the reader. What a baffling proposal. ] (]) 19:53, 4 January 2025 (UTC)
*:{{tpq|There's no guarantee the images will actually look like the person in question}} there is no guarantee ''any'' image will look like the person in question. When an image is not a good likeness, regardless of why, we don't use it. When am image is a good likeness we consider using it. Whether an image is AI-generated or not it is completely independent of whether it is a good likeness. There are also reason other then identification why images are used on BLP-articles. ] (]) 20:39, 4 January 2025 (UTC)
*Foreseeably there may come a time when people's official portraits are AI-enhanced. That time might not be very far in the future. Do we want an exception for official portraits?—] <small>]/]</small> 01:17, 5 January 2025 (UTC)
*:This subsection is about purely AI-generated works, not about AI-enhanced ones. ] (] · ]) 01:23, 5 January 2025 (UTC)
*'''No.''' Per Cremastra, "We should have images drawn or taken by real humans who are trying to depict the ''subject''," - ] (]) 02:12, 5 January 2025 (UTC)
*'''Yes''', depending on specific case. One can use drawings by artists, even such as ]. The latter is an intentional distortion, one could say an intentional misinformation. Still, such images are legitimate on many pages. Or consider numerous images of ]. How realiable are they? I am not saying we must deliberatly use AI images on all pages, but they may be fine in some cases. Now, speaking on "medical articles"... One might actually use the AI generated images of certain biological objects like proteins or organelles. Of course a qualified editorial judgement is always needed to decide if they would improve a specific page (frequently they would not), but making a blanket ban would be unacceptable, in my opinion. For example, the images of protein models generatated by ] would be fine. The AI-generated images of biological membranes I saw? I would say no. It depends. ] (]) 02:50, 5 January 2025 (UTC) {{pb
}}This is complicated of course. For example, there are tools that make an image of a person that (mis)represents him as someone much better and clever than he really is in life. That should be forbidden as an advertisement. This is a whole new world, but I do not think that a blanket rejection would be appropriate. ] (]) 03:19, 5 January 2025 (UTC)
* '''No''', I think there's legal and ethical issues here, especially with the current state of AI. ] ] 03:38, 5 January 2025 (UTC)
*'''No''': Obviously, we shouldn't be using AI images to represent anyone. ] (]) 05:31, 5 January 2025 (UTC)
*'''No''' Too risky for BLP's. Besides if people want AI generated content over editor made content, we should make it clear they are in the wrong place, and readers should be given no doubt as to our integrity, sincerity and effort to give them our best, not a program's. ] (]) 14:51, 5 January 2025 (UTC)
*'''No''', as AI's grasp on the Internet takes hold stronger and stronger, it's important Misplaced Pages, as the online encyclopedia it sets out to be, remains factual and real. Using AI images on Wiki would likely do more harm than good, further thinning the boundaries between what's real and what's not. – ''']''' <sub>(]) (])</sub> 16:52, 5 January 2025 (UTC)
*'''No''', not at the moment. I think it will hard to avoid portraits that been enhanced by AI, as it already been on-going for a number of years and there is no way to avoid it, but I don't want arbitary generated AI portraits of any type. '''<span style="text-shadow:7px 7px 8px black; font-family:Papyrus">]<sup>]</sup></span>''' 20:19, 5 January 2025 (UTC)
*'''No for natural images (e.g. photos of people)'''. Generative AI by itself is not a reliable source for facts. In principle, generating images of people and directly sticking them in articles is no different than generating text and directly sticking it in articles. In practice, however, generating images is worse: Text can at least be discussed, edited, and improved afterwards. In contrast, we have significantly less policy and fewer rigorous methods of discussing how AI-generated images of natural objects should be improved (e.g. "make his face slightly more oblong, it's not close enough yet"). Discussion will devolve into hunches and gut feelings about the fidelity of images, all of which essentially fall under WP:OR. ] (]) 20:37, 5 January 2025 (UTC)
*'''No''' I'm appalled that even a small minority of editors would support such an idea. We have enough credibility issues already; using AI-generated images to represent real people is not something that a real encyclopedia should even consider. ] (]) 22:26, 5 January 2025 (UTC)
*'''No''' I understand the comparison to using illustrations in BLP articles, but I've always viewed that as less preferable to no picture in all honestly. Images of a person are typically presented in context, such as a performer on stage, or a politician's official portrait, and I feel like there would be too many edge cases to consider in terms of making it clear that the photo is AI generated and isn't representative of anything that the person specifically did, but is rather an approximation. ] (]) 06:50, 6 January 2025 (UTC)
*'''No''' - Too often the images resemble caricatures. Real caricatures may be included in articles if the caricature (e.g., political cartoon) had ] and is attributed to the artist. Otherwise, representations of living persons should be real representations taken with photographic equipment. ] (]) 02:31, 7 January 2025 (UTC)
*:So you will be arguing for the removal of the lead images at ], ], etc. then? ] (]) 06:10, 7 January 2025 (UTC)
*::At this point you're making bad-faith "BY YOUR LOGIC" arguments. You're better than that. Don't do it. ] (]) 19:18, 7 January 2025 (UTC)
*'''Strong no''' per bloodofox. —] (]'''-''']) 03:32, 7 January 2025 (UTC)
:'''No''' for AI-generated BLP images ] (]) 21:40, 7 January 2025 (UTC)
== IPv6 IPs ==
*'''No''' - Not only is this effectively guesswork that usually includes unnatural artefacts, but worse, it is also based on unattributed work of photographers who didn't release their work into public domain. I don't care if it is an open legal loophole somewhere, IMO even doing away with the fair use restriction on BLPs would be morally less wrong. I suspect people on whose work LLMs in question were trained would also take less offense to that option. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 23:25, 7 January 2025 (UTC)
*'''No''' – ] says that {{tq|Non-free content should not be used when a freely licensed file that serves the same purpose can reasonably be expected to be uploaded, as is the case for almost all portraits of living people.}} While AI images may not be considered copyrightable, it still be a copyright violation if the output resembles other, copyrighted images, pushing the image towards NFC. At the very least, I feel the use of non-free content to generate AI images violates the spirit of the NFC policy. (I'm assuming copyrighted images of a person are used to generate an AI portrait of them; if free images of that person were used, we should just use those images, and if ''no'' images of the person were used, how on Earth would we trust the output?) ] (]) 02:43, 8 January 2025 (UTC)
*'''No''', AI images should not be permitted on Misplaced Pages at all. ] (]) 11:27, 8 January 2025 (UTC)
{{Archive bottom}}
===Expiration date?===
Anybody can edit Misplaced Pages. But we need to remember an Ip user when we want to mention him/her in any discussion. these huge Ip s are not easy to remember. So we must encourage them to register. '''And the check user tool should be good enough to deal with these huge alpha-numeric IPs.'''
"AI," as the term is currently used, is very new. It feels like large language models and the type of image generators under discussion just got here in 2024. (Yes, I know it was a little earlier.) The culture hasn't completed its initial response to them yet. Right now, these images do more harm than good, but that may change. Either we'll come up with a better way of spotting hallucinations or the machines will hallucinate less. Their copyright status also seems unstable. I suggest that any ban decided upon here have some expiration date or required rediscussion date. Two years feels about right to me, but the important thing would be that the ban has a number on it. ] (]) 23:01, 3 January 2025 (UTC)
*No need for any end-date. If there comes a point where consensus on this changes, then we can change any ban then. ] (]) 05:27, 5 January 2025 (UTC)
*An end date is a positive suggestion. Consensus systems like Misplaced Pages's are vulnerable to half-baked precedential decisions being treated as inviolate. With respect, this conversation does not inspire confidence that this policy proposal's consequences are well-understood at this time. If Misplaced Pages goes in this direction, it should be labeled as primarily reactionary and open to review at a later date. ] (]) 10:22, 5 January 2025 (UTC)
*Agree with FOARP, '''no need for an end date'''. If something significantly changes (e.g. reliable sources/news outlets such as the ''New York Times'', BBC, AP, etc. start using text-to-image models to generate images of living people for their own articles) then this topic can be revisited later. Editors will have to go through the usual process of starting a new discussion/proposal when that time comes. ] (]) 11:39, 5 January 2025 (UTC)
*:Seeing as this discussion has not touched at all on what other organizations may or may not do, it would not be accurate to describe any consensus derived from this conversation in terms of what other organizations may or may not be doing. That is, there has been no consensus that we ought to be looking to the New York Times as an example. Doing so would be inadvisable for several reasons. For one, they have sued an AI company over semi-related issues and they have teams explicitly working on what the future of AI in news ought to look like, so they have some investment in what the future of AI looks like and they are explicitly trying to shape its norms. For another, if they did start to use AI in a way that may be controversial, they would have no positive reason to disclose that and many disincentives. They are not a neutral signal on this issue. Misplaced Pages should decide for itself, preferably doing so while not disrupting the ability of people to continue creating user-generated images. ] (]) 03:07, 6 January 2025 (UTC)
* ] on an indefinite basis, if something changes. An arbitrary sunset date doesn't seem much use. ] (]) 03:15, 6 January 2025 (UTC)
* No need per others. Additionally, if practices change, it doesn't mean editors will decide to follow new practices. As for the technology, it seems the situation has been fairly stable for the past two years: we can detect some fakes and hallucinations immediately, many more in the past, but certainly not all retouched elements and all generated photos available right now, even if there was a readily accessible tool or app that enabled ordinary people to reliably do so.
:Through the history, art forgeries have been fairly reliably detected, but rarely quickly. Relatedly, I don't see why the situation with AI images would change in the next 24 months or any similar time period. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 22:17, 9 January 2025 (UTC)
There is a contentious ] currently resulting from a ] of a ] in which the closer found that the consensus was Delete. The closer then tagged the redirect with ], in particular {{tl|db-xfd}}. It was then deleted by an admin who had taken part in the deletion discussion. The guideline on non-administrative closes says that a non-administrative close of Delete is not permitted, because the closer cannot press the Delete button. The first question at ] seems to be whether DRV '''''must''''' vacate the close and allow a new close by an ] administrator, or whether DRV can endorse the close and leave the close standing. My opinion is that a DRV endorsement of a non-admin close is as good a close as a regular admin close, but that is only my opinion.
The second question that is raised by the DRV discussion is about the existing practice that non-admins sometimes make Delete closes at ]. Should this practice be stopped, because the guideline says that non-admins may not make Delete closes, or should the guideline be revised, or should the guideline be left as is, but with such closes being sometimes allowed? My own opinion is that if it is necessary sometimes to allow a practice that is contrary to the guideline, the guideline should be revised, so as to reduce the load at ], but that is only my opinion.
Should ] be able to endorse the irregular non-admin close, or is it necessary for DRV to vacate the close? Also, should the non-admin closer be thanked, or cautioned?
] (]) 06:51, 31 December 2024 (UTC)
:On the first question, I think that whatever decision DRV makes at ] will be 'legal'. They are not required to vacate the close, no matter how much one editor might like to have a second bite at that apple.
:On your second question, I prefer the existing rules. It is not necessary to allow NACs (]) of 'delete'. Good admins will not blindly trust anyone else's decision, so a NAC to delete does not necessarily save any time, and if the admin disagrees, then it could cause drama. NACs to delete should be gently but firmly discouraged. ] (]) 07:30, 31 December 2024 (UTC)
::I agree with WAID. ] (]) 10:29, 31 December 2024 (UTC)
*That's procedurally irregular, but it was the correct close of the discussion and we've got to the right outcome.—] <small>]/]</small> 11:32, 31 December 2024 (UTC)
* As I said at the Deletion Review, I support non-admins closing RfDs as Delete. If TfDs have been made an exception, RfDs can be too. Closing a heavily discussed nomination at RfD is more about the reading, analysis and thought process at arriving at the outcome, and less about the technicality of the subsequent page actions. It will help making non-admins mentally prepared to advance to admin roles.<span style="font-family:Segoe Script">]</span><span style="font-size:115%">]</span> 17:28, 1 January 2025 (UTC)
:It seems dumb to think that a close can go through DRV and 'pass' only for it to be vacated because the closer didn't have the right credentials. If the close is found to be good, does it matter who closed it? If bad Delete closes by non-admins were regular occurrences, then maybe, but I don't imagine this is the case. ] </nowiki></span>''']] 19:12, 1 January 2025 (UTC)
*The only problem is that if it becomes a regular occurrence, it creates more work overall. An admin can delete and carry out the delete. A non-admin can say it needs to be deleted, but still needs an admin to carry out the delete. That's why this should be discouraged - if it becomes commonplace it will generate a lot more work, but a one-off can clearly be endorsed at DRV. ] ''<span style="font-size:small; vertical-align:top;">]</span>''·''<span style="font-size:small; vertical-align:bottom;">]</span>'' 19:26, 1 January 2025 (UTC)
*:I think it's time for the long-standing "it creates more work" argument to be retired. In the first scenario, person 1 does A and B. In the second scenario, person 1 does A and person 2 does B. That does not create more work overall, it's the same amount of work overall, and it ''reduces'' work for person 1. Splitting work between two people doesn't create more work. ] (]) 14:55, 4 January 2025 (UTC)
*::If person 2 here did B without doing any additional work whatsoever, then person 2 shouldn't be able to do B. We expect admins to ''look'' at what they're deleting. Plus, you're creating additional work for persons 3-20, who are watching ] and don't appreciate demands to go sanity-check low-urgency, possibly-complex closes at unfamiliar deletion venues mixed into the copyright infringement, spam, and attack pages they're trying to prioritize. —] 15:15, 4 January 2025 (UTC)
===Discussion of How Much Attention Admins Pay to What They Are Deleting===
*:::No, we don't expect admins to look at what they're deleting. Anyone familiar with the admin deletion stats (as you are) knows that every day, admins delete many pages without ever looking at them. Person 2 can do B without A. It's OK for person 2 to rely on person 1 to do A correctly. It's not true that in order for person 2 to do B then person 2 must also have done A, and it's not how we operate with other deletions. Non-admins are perfectly capable of closing RfCs and many other discussions; there is nothing about a deletion discussion that suddenly makes non-admins unable to summarize consensus. There is no reason an admin can't rely on a non-admins summary of consensus, just as admins rely on non-admins CSD tagging. ] (]) 15:21, 4 January 2025 (UTC)
*:::: We absolutely <em>do</em> expect admins to look at what they're deleting. At most a NAC delete close can save an admin the trouble of writing the close themself, but if an admin is blindly deleting without verifying that the CSD tag is actually valid for CSD then sooner or later they're going to wind up at ]. ]] 15:49, 4 January 2025 (UTC)
*::::{{u|Levivich}}, I agree with your conclusion, but not with your analogy. As {{u|Anomie}} pointed out, we do not blindly delete pages tagged as CSD. ] specifically instructs us to verify that the page meets a speedy deletion criterion, rather than just appeared as such to one user. This is a very different situation to an AfD that garnered consensus among multiple editors over the course of at least seven days, where the admin's job is just to verify that the NAC read consensus correctly. ] ] 16:01, 4 January 2025 (UTC)
*:::::We can say it all we want but we can't argue with ]. The admin who has deleted over 1 million pages did not read 1 million pages. Nor did the admin who deleted 800,000 pages read 800,000 pages. An admin who has deleted 600,000 pages--no doubt without reading even half of them--just got elected to arbcom. Nobody is taking those admins to ANI or thinks they're doing anything wrong (including me).
*:::::So no, admins don't read the pages they delete, and no, we don't expect them to, as proven by the massive number of deletions, and no, admins who delete without reading aren't taken to ANI, they're promoted. This includes CSDs.
*:::::More broadly, there is no reason not to allow admins to rely on non-admin XfD closures when making deletion decisions. We already do this for multiple types of XfDs, we can and should do it for AfDs. ] (]) 16:05, 4 January 2025 (UTC)
*::::::{{u|Explicit}} didn't have to read over one million pages, because most of those deletions were the result of an XfD, not a CSD. He had to review almost a million XfD discussions to make sure consensus was to delete, which is exactly what he does when closing. And the majority of CSD deletions are of clumsy, unsourced self-promotion pages that take less than ten seconds to assess and confirm as such. I know for a fact that {{u|Liz}} -- number #3 on that list -- carefully reviews every speedy-tagged page before deleting it, and routinely rejects such requests when they do not meet CSD. {{pb}} {{u|Levivich}}, you are making some serious accusations here, with zero evidence to support them. I don't think this will help your case here. ] ] 16:24, 4 January 2025 (UTC)
*:::::::I have no case here and I'm making no accusations. If you want to believe that a person has read over a million XfDs, you go ahead and believe that. I don't, because even over 15 years, that would be 182 XfDs a day every day with no days off, and I don't believe anyone does, or is capable of doing, that much XfD reading. ] (]) 17:03, 4 January 2025 (UTC)
*:::::::: {{u|Levivich}} You're completely wrong, because you're missing a number of very obvious issues with those statistics.
*::::::::: Not even a majority of Explicit's deletions are XfDs - most are speedies
*::::::::: Many are G13 deletions, which don't need any analysis, they're simply done on timeframe. You can do those in seconds. Similarly U1, R2 and F8
*::::::::: Most articles have a talk page, which also needs to be deleted (G8), so deleting most articles means two deletions.
*::::::::: RfDs don't take very long to close at all; most are unanimous
*::::::::: Of Explicit's last 500 deletions, only 58 have been XfDs (and their associated talk pages where they existed, making 97 deletions).
*::::::::: The vast majority of the rest have been G13, G8, U1, R2 and F8.
*:::::::: Just in the interests of accuracy, you know. ] 17:18, 4 January 2025 (UTC)
*:::::::::Owen: {{tqq|Explicit didn't have to read over one million pages, because most of those deletions were the result of an XfD, not a CSD}}
*:::::::::BK: {{tqq|Not even a majority of Explicit's deletions are XfDs - most are speedies}}
*:::::::::I don't know which one of you is wrong but it doesn't matter. Explicit did not read 1 million pages over the last 15 years prior to deleting them, whether they were XfDs or CSDs. Nobody is reading 182 Misplaced Pages pages 7 days a week for 15 years. Nobody has read a million Misplaced Pages pages. No human can thoroughly review 182 things a day. It's mathematics, guys. If a person spends 5 minutes on each review -- which isn't a thorough review of anything -- that's 15 hours per day to do 182 reviews. Nobody is spending that much time, 7 days a week, for 15 years. Even if the person spends just 1 minute, that's over 3 hours a day... every day for 15 years. The math proves that Explicit is spending maybe 1 minute per deletion.
*:::::::::Now: an admin spending 1 minute per deletion is not providing any real kind of level of oversight that can't be provided by a non-admin closing the XfD and the admin then spending 1 minute reviewing the close and deleting the page.
*:::::::::The math and the stats don't lie. The suggestion that admins carefully review every page before deleting them is plainly not true. The suggestion that if admins didn't do that, they'd be taken to ANI, is also plainly not true. We have admins spending a minute or less per deletion and not being taken to ANI. These are facts. ] (]) 19:31, 4 January 2025 (UTC)
*:::::::::: Your "math" is based on a lot of faulty assumptions and oversimplifications, which you seem to be persisting in despite others trying to correct you. ]] 20:42, 4 January 2025 (UTC)
*:::::::::: Those are ''not'' facts, because your data is faulty. Your reply simply tells me that you didn't read what I wrote. Someone with the editing pattern of Explicit ''isn't'' reviewing 182 things a day. Nowhere near that. Quite apart from the talk page issue (which, if every page had a talk page, would immediately halve the number of reviews) in some of the speedy categories I mention there's nothing ''to'' review; it's simply pressing a button. Indeed, deleting the articles in the stale G13 queue, orphaned G8 queue, or the F5 or F8 category, can result in dozens - even hundreds - of deletions in one button press. As an example, on the 3rd January alone, Explicit deleted 113 F8 images, plus 83 talk pages of those images. That's 196 deletions, all done in a few seconds, as there's nothing to review. In comparison, the number of XfDs he closed that day was 25. ] 21:21, 4 January 2025 (UTC)
*:::::::::::Cryptic: {{tqq|We expect admins to ''look'' at what they're deleting.}}
*:::::::::::BK: {{tqq|That's 196 deletions, all done in a few seconds, as there's nothing to review.}}
*:::::::::::I disagreed with Cryptic's point, and thank you BK for providing an example of exactly what I'm talking about. We do not expect admins to review (or "''look'' at") what they're deleting, sometimes there's not even anything to look at. Admins delete things without reviewing what they're deleting all the time, and they're not hauled off to ANI for it. BK, you're arguing with me, but you're not actually disagreeing with what I'm saying. You're not arguing, as others have said above, that all admins review everything they delete before they delete it, or that this is the community expectation. ] (]) 22:24, 4 January 2025 (UTC)
*:::::::::::: I'm simply pointing out that the claim you have made {{tq|The math proves that Explicit is spending maybe 1 minute per deletion. Now: an admin spending 1 minute per deletion is not providing any real kind of level of oversight that can't be provided by a non-admin closing the XfD and the admin then spending 1 minute reviewing the close and deleting the page.}} is not correct; Explicit is not spending 1 minute per XfD, he is spending 1 minute per ''deletion'', and because in many cases the admin pressing the button is simply completing an automated process (in the case of G13, that the article has not been edited for six months; in the case of F8, that the identical file exists at Commons), and deleting many files in one button-press, that skews the data. Now, if you are saying that an admin is ''closing AfDs or deleting G7 or G11 speedies at a high rate'' (not just "deleting things"), and their speed suggests they aren't reviewing them carefully - ''then'' you have a point. ] 23:33, 4 January 2025 (UTC)
*:::::::::::::Not actually reviewing deletions to make sure they were correct was one of the two major factors that resulted in Arbcom desysopping ] (the other was a refusal to engage with good-faith queries about his actions and refusing to engage at all with IP editors). As others have said, how long it takes to ensure that what you are deleting should be deleted varies considerably. For G13s it's as simple as checking that bot has correctly determined that a given timestamp was more than 6 months ago - either the entire batch will be correct or the entire batch will be incorrect. Most of the deletions I do are the result of RfDs, after determining that the consensus is to delete (which is usually very simple) I delete the page. The software then tells me that page has a talk page, at least 9 times out of 10 (maybe more) it takes less than a second to verify there isn't any any reason they are G8 exempt. There is no excuse for not doing the reviewing properly though because there ''are'' exceptions. ] (]) 00:22, 5 January 2025 (UTC)
*:::::::::::::I didn't say Explicit is spending 1 minute per XfD, I said "per deletion." And your point about "many files in one button-press" is literally the same as my point, which is that admins ''don't'' carefully review every single thing they delete, they sometimes delete many files in one button press (196 deletions in a few seconds is an example). So, you agree with me that "we expect admins to look at what they're deleting" is not correct, it's actually disproven by the data. ] (]) 00:37, 5 January 2025 (UTC)
*::::::::::::::Admins ''are'' expected to review everything they delete. It's just that in some cases many pages can be reviewed together very quickly. It is also possible to spend time carefully reviewing many pages in detail, assembling a list of which should be deleted and then deleting them the pages on that together with a single click. ] (]) 01:08, 5 January 2025 (UTC)
*::::::::::::::It was in the context of XfDs, however ("{{tq|If you want to believe that a person has read over a million XfDs, you go ahead and believe that}}"). ] 08:03, 5 January 2025 (UTC)
*:::::::::::::::That was in response to someone saying they were mostly XfDs. The same point holds if they were mostly CSDs. That's why I said it doesn't matter whether they were mostly XfDs or CSDs. Regardless of whether it's XfD or CSD, when someone makes 500k or 1 million deletions, we know they didn't look at each and every individual thing (page, file, whatever) that was deleted, nor do we expect them to. (Which I said in response to people saying we expect admins to look at every single thing they delete.) ] (]) 13:18, 5 January 2025 (UTC)
*:::::By pressing the delete button you are asserting that at least one of the following is true:
*:::::*The page met the specified speedy deletion criterion (e.g. if the deletion log says G12 you are asserting the page, including all of its old revisions, was copyvio).
*:::::*The page was eligible for PROD, this was the first time that it was prodded and nobody has objected to the prod.
*:::::*The deletion of the page was discussed a the relevant XfD (or, exceptionally, in an RfC) and that the consensus of that discussion was to delete the page.
*:::::If an admin is not prepared to put their name to the truthfulness of that assertion then they should not be deleting the page. ] (]) 16:12, 4 January 2025 (UTC)
*{{tq|My own opinion is that if it is necessary sometimes to allow a practice that is contrary to the guideline, the guideline should be revised, so as to reduce the load at DRV, but that is only my opinion|quotes=y}} - actually, {{u|Robert McClenon}}, your opinion is solidly anchored in policy. ] tells us: {{tq|the written rules themselves do not set accepted practice. Rather, they document already-existing community consensus regarding what should be accepted and what should be rejected.}} If CfD is working fine as it is, let's update policy to reflect the practice. ] ] 16:09, 2 January 2025 (UTC)
*Regarding the ], the guideline on non-admin "delete" closures is at ] and explicitly includes exceptions for TfD and CfD, so there isn't currently a conflict between existing practice and deletion guidelines. ] ] 08:00, 9 January 2025 (UTC)
Is there a guideline that says that unregistered editors (IP addresses) should not edit in Misplaced Pages space (project space)? We had am ] discussion in which an unregistered editor asked a registered editor to nominate an essay for deletion. The registered editor did as requested, which I think is known as proxying. As I understand, unregistered editors cannot create new pages in either article space or project space, and an AFD or MFD discussion is its own page. The MFD was then closed as a ], because no rationale was given. The question has to do with a comment made by one of the MFD regular editors that IP editors should not edit in project space. Another editor questioned whether there was a guideline to that effect. I cannot recall having seen a guideline that restricts or discourages unregistered editors from editing in project space. Is there such a guideline? ] (]) 00:39, 1 January 2025 (UTC)
:No. IP editors regularly participate in project space. ] (]/]) 00:43, 1 January 2025 (UTC)
Now if i mention them anywhere in talk page discussion just think how difficult it would be remember them. Sometimes user report IP socks when they see similar range. But in these cases the users won't be able to recognize IP-shifting socks as it may not be possible for human brain to recognize the IP-range. Misplaced Pages can't stop them from editing. But if they don't listen to request of opening account, we can come to some solution where they can be shortened through some software.
:No, and anyone who claims there is can be safely disregarded as full of shit. (Not that it's the first time that people confidently claim false authority.) ] (]) 08:11, 1 January 2025 (UTC)
:Adding to the chorus, no. Unregistered users are explicitly instructed to do this in ] (same for AfD, etc.) – ] <small>(])</small> 08:22, 1 January 2025 (UTC)
::Thank you. Three ] were then in order. One to the unregistered editor, for not giving a reason for the deletion request. Two to the registered editor who was proxying, for making an MFD nomination without stating a reason. Three to the editor who said that IPs should stay out of project space. I think that the third editor would have had a case to argue that policy should be changed and the English Misplaced Pages should follow the Portuguese example of not permitting IP editing, but that is only my opinion and is an unrelated issue. ] (]) 16:30, 1 January 2025 (UTC)
:::{{smalldiv|1=That's six trouts!{{jokes}} ] (]) 17:06, 1 January 2025 (UTC)}}
:::::<small>Second breakfast.</small> ] (]) 00:42, 2 January 2025 (UTC)
:::Ptwiki permits IP editors everywhere except the mainspace. See the . ] (]) 07:51, 3 January 2025 (UTC)
== Should ] include mention of AI-generated comments? ==
--<span style="border:1.5px solid lime;padding:1.5px;">] (])</span> 16:55, 23 May 2015 (UTC)
:The length of IPv6 addresses is certainly a real problem. What I don't see here, however, is any proposal to make it easier. Do you have a proposal here ]? ] (]) 20:58, 25 May 2015 (UTC)
Using AI to write your comments in a discussion makes it difficult for others to assume that you are discussing in good faith, rather than trying to use AI to argue someone into exhaustion (see example of someone using AI in their replies ). More fundamentally, ] can't apply to the AI itself as AI lacks intentionality, and it is difficult for editors to assess how much of an AI-generated comment reflects the training of the AI vs. the actual thoughts of the editor.
::I suggest adding language to the welcome template for IPs that points out that IPv6 addresses are difficult to remember, as an additional incentive to create an account. (IPv4 addresses are worse in one respect. They are usually dynamic, because ISPs have to manage the pool, and this is a different factor that makes it difficult to communicate with them.) About the only reasonable thing that comes to my mind is adding language to the welcome template. ] (]) 21:04, 25 May 2015 (UTC)
Should ] be addended to include that using AI to generate your replies in a discussion runs counter to demonstrating good faith? ] (]) 00:23, 2 January 2025 (UTC)
:::{{ping|Robert McClenon}} Why would anyone want to remember their own IP address? Or are you suggesting that a significant number would register to make remembering their identity easier on others? I mean, the word incentive usually implies a benefit to one's own interest. ―] ] 11:46, 29 May 2015 (UTC)
* '''Yes''', I think this is a good idea. ] (]) 00:39, 2 January 2025 (UTC)
::::The complaint appears to be about the difficulty of ''other'' editors remembering the long IP address, e.g., in order to use their talk page. I agree that remembering your own IP address is a silly issue, especially because the IP can and should always just register an account. ] (]) 14:52, 29 May 2015 (UTC)
:'''No'''. As with all the other concurrent discussions (how many times do we actually need to discuss the exact same FUD and scaremongering?) the problem is not AI, but rather inappropriate use of AI. What we need to do is to (better) explain what we actually want to see in discussions, not vaguely defined bans of swathes of technology that, used properly, can aid communication. ] (]) 01:23, 2 January 2025 (UTC)
:Another annoying thing is the long prefilled undo edit summaries where the username or IP address is used three times in ] with source <code><nowiki>Undid revision $1 by ] (])</nowiki></code>. For IPv6 we get the form <code><nowiki>Undid revision 664551967 by ] (])</nowiki></code>. It renders as "Undid revision 664551967 by ] (])", but the code is 194 characters. Edit summaries can be at most 255 characters so there is only 61 left for the editor to explain the revert, unless part of the prefilled summary is manually removed first. IPv4 only uses 119 characters, leaving 136 for the editor. If you undo an edit then the undone edit is usually right before in the page history so there is easy access to the links, and I very rarely click the links in the undo summary. Is it possible to insert a test in ] and produce a shorter text for IPv6 (and possibly long usernames), or would the test code just become part of the edit summary with the current software? I'm and admin so I suppose I could just try but I don't like experimenting with live code. ] (]) 12:47, 29 May 2015 (UTC)
::Note that this topic is discussing using AI to ''generate'' replies, as opposed to using it as an aid (e.g. asking it to edit for grammar, or conciseness). As the above concurrent discussion demonstrates, users are already using AI to generate their replies in AfD, so it isn't scaremongering but an actual issue.
::] also does not ban anything ("Showing good faith is not required"), but offers general advice on demonstrating good faith. So it seems like the most relevant place to include mention of the community's concerns regarding AI-generated comments, without outright banning anything. ] (]) 01:32, 2 January 2025 (UTC)
::{{u|PrimeHunter}} has pointed out another problem. '''What if an "IPv6 IP" reverts edits made by another "IPv6 IP"?. Just think what the edit History will be like.''' They have the right to edit WP, but we need to come to a solution which will help us remembering them so that we can report them in case of IP sockpuppetry cases.<span style="border:1.5px solid lime;padding:1.5px;">] (])</span> 13:32, 29 May 2015 (UTC)
:::And as pointed out, multiple times in those discussions, different people understand different things from the phrase "AI-generated". The community's concern is not AI-generated comments, but comments that do not clearly and constructively contribute to a discussion - ''some'' such comments are AI-generated, some are not. This proposal would, just as all the other related ones, cause actual harm when editors falsely accuse others of using AI (and this ''will'' happen). ] (]) 02:34, 2 January 2025 (UTC)
:::But why do you need to ''remember'' these numbers? Surely you're not typing these numbers out manually, and I'm pretty sure that if your computer is modern enough to edit Misplaced Pages, then it is capable of copying and pasting a mere 39 characters. ] (]) 15:43, 29 May 2015 (UTC)
::::Nobody signed up to argue with bots here. If you're pasting someone else's comment into a prompt and asking the chatbot to argue against that comment and just posting it in here, that's a real problema and absolutely should not be acceptable. ] (]) 03:31, 2 January 2025 (UTC)
::::Sometimes Users report IP socks. They are able to find the similarity due to small IPs. Now it will be difficult.<span style="border:1.5px solid lime;padding:1.5px;">] (])</span> 09:15, 30 May 2015 (UTC)
:::::Thank you for the assumption of bad faith and demonstrating one of my points about the harm caused. Nobody is forcing you to engage with bad-faith comments, but whether something is or is not bad faith needs to be determined by its content not by its method of generation. Simply using an AI demonstrates neither good faith nor bad faith. ] (]) 04:36, 2 January 2025 (UTC)
:::::Generally, the first 4 segments are the equivalent of a full IPv4 address. So in theory, 1111:2222:3333:4444:AAAA:AAAA:AAAA:AAAA and 1111:2222:3333:4444:AAAA:AAAA:BBBB:AAAA are most likely the same person on the same connection to an ISP. 1111:2222:3333:5555:AAAA:AAAA:AAAA:AAAA should be the same ISP, but is likely a different user. Actual ISP practice isn't well established, and so you could in theory have multiple unrelated people on one /64, or have one person receive IPs from multiple /64s, but it hasn't come up much that I've seen. ]] 13:50, 30 May 2015 (UTC)
:::::I don't see why we have any particular to reason to suspect a respected and trustworthy editor of using AI. '']'' (] — ]) 14:31, 2 January 2025 (UTC)
::::I'm one of those people who clarified the difference between AI-generated vs. edited, and such a difference could be made explicit with a note. Editors are already accusing others of using AI. Could you clarify how you think addressing AI in ] would cause actual harm? ] (]) 04:29, 2 January 2025 (UTC)
:::::By encouraging editors to accuse others of using AI, by encouraging editors to dismiss or ignore comments because they suspect that they are AI-generated rather than engaging with them. @] has already encouraged others to ignore my arguments in this discussion because they suspect I might be using an LLM and/or be a bot (for the record I'm neither). ] (]) 04:33, 2 January 2025 (UTC)
::::::I think {{u|bloodofox}}'s ] was about "you" in the rhetorical sense, not "you" as in Thryduulf. ] (]) 11:06, 2 January 2025 (UTC)
:::::Given your relentlessly pro-AI comments here, it seems that you'd be A-OK with just chatting with a group of chatbots here — or leaving the discussion to them. However, most of us clearly are not. In fact, I would immediately tell someone to get lost were it confirmed that indeed that is what is happening. I'm a human being and find the notion of wasting my time with chatbots on Misplaced Pages to be incredibly insulting and offensive. ] (]) 04:38, 2 January 2025 (UTC)
::::::My comments are neither pro-AI nor anti-AI, indeed it seems that you have not understood pretty much anything I'm saying. ] (]) 04:43, 2 January 2025 (UTC)
:::::::Funny, you've done nothing here but argue for more generative AI on the site and now you seem to be arguing to let chatbots run rampant on it while mocking anyone who doesn't want to interface with chatbots on Misplaced Pages. Hey, why not just sell the site to Meta, am I right? ] (]) 04:53, 2 January 2025 (UTC)
::::::::I haven't been arguing for more generative AI on the site. I've been arguing against banning it on the grounds that such a ban would be unclear, unenforceable, wouldn't solve any problems (largely because whether something is AI or not is completely irrelevant to the matter at hand) but would instead cause harm. Some of the issues identified are actual problems, but AI is not the cause of them and banning AI won't fix them.
::::::::I'm not mocking anybody, nor am I advocating to {{tpq|let chatbots run rampant}}. I'm utterly confused why you think I might advocate for selling Misplaced Pages to Meta (or anyone else for that matter)? Are you actually reading anything I'm writing? You clearly are not understanding it. ] (]) 05:01, 2 January 2025 (UTC)
:::::::::So we're now in 'everyone else is the problem, not me!' territory now? Perhaps try communicating in a different way because your responses here are looking very much like the typical AI apologetics one can encounter on just about any contemporary LinkedIn thread from your typical FAANG employee. ] (]) 05:13, 2 January 2025 (UTC)
::::::::::No, this is not a {{tpq|everyone else is the problem, not me}} issue because most other people appear to be able to understand my arguments and respond to them appropriately. Not everybody agrees with them, but that's not an issue.
::::::::::I'm not familiar with Linkedin threads (I don't use that platform) nor what a "FAANG employee" is (I've literally never heard the term before now) so I have no idea whether your characterisation is a compliment or a personal attack, but given your comments towards me and others you disagree with elsewhere I suspect it's closer to the latter.
::::::::::AI is a tool. Just like any other tool it can be used in good faith or in bad faith, it can be used well and it can be used badly, it can be used in appropriate situations and it can be used in inappropriate situations, the results of using the tool can be good and the results of using the tool can be bad. Banning the tool inevitably bans the good results as well as the bad results but doesn't address the reasons why the results were good or bad and so does not resolve the actual issue that led to the bad outcomes. ] (]) 12:09, 2 January 2025 (UTC)
:::::::::::In the context of generating comments to other users though, AI is much easier to use for bad faith than for good faith. LLMs don't understand Misplaced Pages's policies and norms, and so are hard to utilize to generate posts that productively address them. By contrast, bad actors can easily use LLMs to make low quality posts to waste people's time or wear them down.
:::::::::::In the context of generating images, or text for articles, it's easy to see how the vast majority of users using AI for those purposes is acting in good faith as these are generally constructive tasks, and most people making bad faith changes to articles are either obvious vandals who won't bother to use AI because they'll be reverted soon anyways, or trying to be subtle (povpushers) in which case they tend to want to carefully write their own text into the article.
:::::::::::It's true that AI "is just a tool", but when that tool is much easier to use for bad faith purposes (in the context of discussions) then it raises suspicions about why people are using it. ] (]) 22:44, 2 January 2025 (UTC)
:'''Not really''' – I agree with Thryduulf's arguments on this one. Using AI to help tweak or summarize or "enhance" replies is of course not bad faith – the person is trying hard. Maybe English is their second language. Even for replies 100% AI-generated the user may be an ESL speaker struggling to remember the right words (I always forget 90% of my French vocabulary when writing anything in French, for example). In this case, I don't think we should make a ''blanket'' assumption that using AI to generate comments is not showing good faith. '']'' (] — ]) 02:35, 2 January 2025 (UTC)
== "Fair use" from third party as opposed to official sources ==
*'''Yes''' because generating walls of text is not good faith. People "touching up" their comments is also bad (for starters, if you lack the English competency to write your statements in the first place, you probably lack the competency to tell if your meaning has been preserved or not). Exactly ''what'' AGF should say needs work, but something needs to be said, and <s>AGF</s>DGF is a good place to do it. ] (]) 02:56, 2 January 2025 (UTC)
*:Not all walls of text are generated by AI, not all AI generated comments are walls of text. Not everybody who uses AI to touch up their comments lacks the competencies you describe, not everybody who does lack those competencies uses AI. It is not always possible to tell which comments have been generated by AI and which have not. This proposal is not particularly relevant to the problems you describe. ] (]) 03:01, 2 January 2025 (UTC)
:::Someone has to ask: Are you generating all of these pro-AI arguments using ChatGPT? It'd explain a lot. If so, I'll happily ignore any and all of your contributions, and I'd advise anyone else to do the same. We're not here to be flooded with LLM-derived responses. ] (]) 03:27, 2 January 2025 (UTC)
::::That you can't tell whether my comments are AI-generated or not is one of the fundamental problems with these proposals. For the record they aren't, nor are they pro-AI - they're simply anti throwing out babies with bathwater. ] (]) 04:25, 2 January 2025 (UTC)
:::::I'd say it also illustrates the serious danger: We can no longer be sure that we're even talking to other people here, which is probably the most notable shift in the history of Misplaced Pages. ] (]) 04:34, 2 January 2025 (UTC)
::::::How is that a "serious danger"? If a comment makes a good point, why does it matter whether ti was AI generated or not? If it doesn't make a good point, why does it matter if it was AI generated or not? How will these proposals resolve that "danger"? How will they be enforceable? ] (]) 04:39, 2 January 2025 (UTC)
:::::::Misplaced Pages is made for people, by people, and I like most people will be incredibly offended to find that we're just playing some kind of LLM pong with a chatbot of your choice. You can't be serious. ] (]) 04:40, 2 January 2025 (UTC)
::::::::You are entitled to that philosophy, but that doesn't actually answer any of my questions. ] (]) 04:45, 2 January 2025 (UTC)
:::::::"why does it matter if it was AI generated or not?"
:::::::Because it takes little effort to post a lengthy, low quality AI-generated post, and a lot of effort for human editors to write up replies debunking them.
:::::::"How will they be enforceable? "
:::::::] isn't meant to be enforced. It's meant to explain to people how they can demonstrate good faith. Posting replies to people (who took the time to write them) that are obviously AI-generated harms the ability of those people to assume good faith. ] (]) 05:16, 2 January 2025 (UTC)
:The linked "example of someone using AI in their replies" appears – to me – to be a non-AI-generated comment. I think I preferred the allegedly AI-generated comments from that user (]). The AI was at least superficially polite. ] (]) 04:27, 2 January 2025 (UTC)
::Obviously the person screaming in all caps that they use AI because they don't want to waste their time arguing is not using AI for that comment. Their first post calls for the article to be deleted for not "" and "merely" reiterating what other sources have written.
::Yes, after a human had wasted their time explaining all the things wrong with its first post, then the bot was able to write a second post which ''looks'' ok. Except it only superficially ''looks'' ok, it doesn't actually accurately describe the articles. ] (]) 04:59, 2 January 2025 (UTC)
Given that a truly free image to illustrate the ] retail outlets can't be found after a reasonable amount of searching, is there any preference in the "fair use" policy to using a non-free images from a third party (e.g. ) as opposed to one taken from the company in question's site () and presumably owned by them?
:::Multiple humans have demonstrated in these discussions that humans are equally capable of writing posts which superficially ''look'' OK but don't actually accurately relate to anything they are responding to. ] (]) 05:03, 2 January 2025 (UTC)
::::But I can assume that everyone here is acting in good faith. I can't assume good faith in the globally-locked sock puppet spamming AfD discussions with low effort posts, whose bot is just saying whatever it can to argue for the deletion of political pages the editor doesn't like. ] (]) 05:09, 2 January 2025 (UTC)
:::::True, but I think that has more to do with the "globally-locked sock puppet spamming AfD discussions" part than with the "some of it might be " part. ] (]) 07:54, 2 January 2025 (UTC)
::::::All of which was discovered because of my suspicions from their inhuman, and meaningless replies. "Reiteration isn't the problem; redundancy is," maybe sounds pithy in a vacuum, but this was written in reply to me stating that we aren't supposed to be doing OR but reiterating what the sources say.
::::::"Your criticism feels overly prescriptive, as though you're evaluating this as an academic essay" also ''sounds good'', until you realize that the bot is actually criticizing its own original post.
::::::The fact that my suspicions about their good faith were ultimately validated only makes it even harder for me to assume good faith in users who sound like ChatGPT. ] (]) 08:33, 2 January 2025 (UTC)
:::::::I wonder if we need some other language here. I can understand feeling like this is a bad interaction. There's no sense that the person cares; there's no feeling like this is a true interaction. A contract lawyer would say that there's no ], and there can't be, because there's no mind in the AI, and the human copying from the AI doesn't seem to be interested in engaging their brain.
:::::::But... do you actually think they're doing this for the purpose of ''intentionally'' harming Misplaced Pages? Or could this be explained by other motivations? ] – or to anxiety, insecurity (will they hate me if I get my grammar wrong?), incompetence, negligence, or any number of other "understandable" (but still something ]- and even block-worthy) reasons. ] (]) 08:49, 2 January 2025 (UTC)
::::::::The ] has a header at the top asking people not to template them because it is "impersonal and disrespectful", instead requesting "please take a moment to write a comment below '''in your own words'''"
::::::::Does this look like acting in good faith to you? Requesting other people write personalized responses to them while they respond with an LLM? Because it looks to me like they are trying to waste other people's time. ] (]) 09:35, 2 January 2025 (UTC)
:::::::::] means that you assume people aren't deliberately screwing up on purpose. Humans are self-contradictory creatures. I generally do assume that someone who is being hypocritical hasn't noticed their contradictions yet. ] (]) 07:54, 3 January 2025 (UTC)
::::::::::"Being hypocritical" in the abstract isn't the problem, it's the fact that asking people to put effort into their comments, while putting in minimal effort into your own comments appears bad faith, especially when said person says they don't want to waste time writing comments to stupid people. The fact you are arguing AGF for this person is both astounding and disappointing. ] (]) 16:08, 3 January 2025 (UTC)
:::::::::::It feels like there is a lack of reciprocity in the interaction, even leaving aside the concern that the account is a block-evading sock.
:::::::::::But I wonder if you have read AGF recently. The first sentence is "'''Assuming good faith''' ('''AGF''') means assuming that people are not deliberately ''trying'' to hurt Misplaced Pages, even when their actions are harmful."
:::::::::::So we've got some of this (e.g., harmful actions). But do you really believe this person woke up in the morning and decided "My main goal for today is to deliberately hurt Misplaced Pages. I might not be successful, but I sure am going to try hard to reach my goal"? ] (]) 23:17, 4 January 2025 (UTC)
::::::::::::Trying to hurt Misplaced Pages doesn't mean they have to literally think "I am trying to hurt Misplaced Pages", it can mean a range of things, such as "I am trying to troll Wikipedians". A person who thinks a cabal of editors is guarding an article page, and that they need to harass them off the site, may think they are improving Misplaced Pages, but at the least I wouldn't say that they are acting in good faith. ] (]) 23:27, 4 January 2025 (UTC)
:::::::::::::Sure, I'd count that as a case of "trying to hurt Misplaced Pages-the-community". ] (]) 06:10, 5 January 2025 (UTC)
* The issues with AI in discussions is not related to good faith, which is narrowly defined to intent. ] (]) 04:45, 2 January 2025 (UTC)
My gut instinct would be that the latter is preferable, but I've no idea if that has a basis in legal fact and/or WP policy...? Can any one clarify this?
*:In my mind, they are related inasmuch as it is much more difficult for me to ascertain good faith if the words are eminently not written by the person I am speaking to in large part, but instead generated based on an unknown prompt in what is likely a small fraction of the expected time. To be frank, in many situations it is difficult to avoid the conclusion that the disparity in effort is being leveraged in something less than good faith. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 05:02, 2 January 2025 (UTC)
*::Assume good faith, don't ascertain! Llm use can be deeply unhelpful for discussions and the potential for mis-use is large, but the most recent discussion I've been involved with where I observed an llm post was responded to by an llm post, I believe both the users were doing this in good faith. ] (]) 05:07, 2 January 2025 (UTC)
] (]) 17:21, 24 May 2015 (UTC)
*:::All I mean to say is it should be licit that unhelpful LLM use should be something that can be mentioned like any other unhelpful rhetorical pattern. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 05:09, 2 January 2025 (UTC)
:I think neither are acceptable, but perhaps I am misunderstanding the question. The business still exists, so why can't someone walk over an take a photo?
*::::Sure, but ] doesn't mention any unhelpful rhetorical patterns. ] (]) 05:32, 2 January 2025 (UTC)
*::::The fact that everyone (myself included) defending "LLM use" says "use" rather than "generated", is a pretty clear sign that no one really wants to communicate with someone using "LLM generated" comments. We can argue about bans (not being proposed here), how to know if someone is using LLM, the nuances of "LLM use", etc., but at the very least we should be able to agree that there are concerns with LLM generated replies, and if we can agree that there are concerns then we should be able to agree that somewhere in policy we should be able to find a place to express those concerns. ] (]) 05:38, 2 January 2025 (UTC)
:Are you talking about photos from other eras?
*:::::...or they could be saying "use" because "using LLMs" is shorter and more colloquial than "generating text with LLMs"? ] (]) 06:19, 2 January 2025 (UTC)
*::::::Seems unlikely when people justify their use for editing (which I also support), and not for generating replies on their behalf. ] (]) 06:23, 2 January 2025 (UTC)
:By the way, this is a subject for this page, which is to discuss changes in policy, not the application of policy. The help desk or ] is a better place.--]] 17:29, 24 May 2015 (UTC)
*:::::::This is just semantics.
*:::::::For instance, I am OK with someone using a LLM to post a productive comment on a talk page. I am also OK with someone generating a reply with a LLM that is a productive comment to post to a talk page. I am not OK with someone generating text with an LLM to include in an article, and also not OK with someone using a LLM to contribute to an article.
:: While Menzies still exists as a newspaper distribution and aviation business, the retail side- which was widespread and very well-known (particularly in Scotland)- was sold off in the late 1990s, and I've been unable to find free photographs of the shops in their original state.
*:::::::The only difference between these four sentences is that two of them are more annoying to type than the other two. ] (]) 08:08, 2 January 2025 (UTC)
*::::::::Most people already assume good faith in those making productive contributions. In situations where good faith is more difficult to assume, would you trust someone who uses an LLM to generate all of their comments as much as someone who doesn't? ] (]) 09:11, 2 January 2025 (UTC)
:: As per your comment, though, I've ]. ] (]) 19:51, 24 May 2015 (UTC)
*:::::::::Given that LLM-use is completely irrelevant to the faith in which a user contributes, yes. Of course what amount that actually is may be anywhere between completely and none. ] (]) 11:59, 2 January 2025 (UTC)
*::::::::::LLM-use is relevant as it allows bad faith users to disrupt the encyclopedia with minimal effort. Such a user , as well as started and , all using AI. I had previously been involved in a debate with another sock puppet of theirs, but at that time they didn't use AI. Now it seems they are switching to using an LLM just to troll with minimal effort. ] (]) 21:44, 2 January 2025 (UTC)
=="Comprised of" and the problem of pet peeves in editing==
*:::::::::::LLMs are a tool that can be used by good and bad faith users alike. Using an LLM tells you nothing about whether a user is contributing in good or bad faith. If somebody is trolling they can be, and should be, blocked for trolling regardless of the specifics of how they are trolling. ] (]) 21:56, 2 January 2025 (UTC)
{{user|Giraffedata}} is by now well known for his crusade against the phrase "]" (the phrase has its own article). Some people think it is good that he "takes an interest in grammar", others think it is silly or offensive that he thinks he needs to enforce his own arbitrary preference onto other peoples' completley crammatically correct language usage. I admit I am among the latter. The problem is that his practice creates conflicts, as can be seen from his talkpage where editors regularly complain about his changes to their language, frequently saying that they use the phrase deliberately and pointing out that it is not in fact considered incorrect by English style authorities, or by linguists who specialize in English. Giraffedata, generally responds with contempt asserting that he has a right to change any word in the encyclopedia as he sees fit. This is of course true in principle, but it seems to conflict with our general approach to arbitrary style issues such as ], ] and ] which generally suggests that editors should not arbitrarily change between styles in articles to which they are not major contributors. Giraffedata responds, correctly, that neither these nor the MOS explicitly cover questions such as grammar and word usage.
*::::::::::::A can of spray paint, a kitchen knife, etc., are tools that can be used for good or bad, but if you bring them some place where they have few good uses and many bad uses then people will be suspicious about why you brought them. You can't just assume that a tool in any context is equally harmless. Using AI to generate replies to other editors is more suspicious than using it to generate a picture exemplifying a fashion style, or a description of a physics concept. ] (]) 23:09, 2 January 2025 (UTC)
The problem of course with this attitude is that if Giraffedata can use semiautomatic tools to change between styles, and refuse to for example make a list of exceptions, or to even concede the right of other editors to use these expressions in article space, then any other editor can do the same. I could for example with the same reasoning create a bot to insert the wording "comprised of" instead of "composed of" across articles, or simply manually revert Giraffedata's changes. Or I could choose some other arbitrary style choice or word to systematically change. Currently there is nothing in policy or practice that could deter me or someone else from doing so, or any policy that could be applied if I were to do it, that would not also apply in kind to Giraffedata's practices.
*:::::::::I wouldn't trust anything factual the person would have to say, but I wouldn't assume they were malicious, which is the entire point of ]. ] (]) 16:47, 2 January 2025 (UTC)
*::::::::::] is not a death pact though. At times you should be suspicious. Do you think that if a user, ''who you already have suspicions of'', is also using an LLM to generate their comments, that that doesn't have any effect on those suspicions? ] (]) 21:44, 2 January 2025 (UTC)
So I think it is time that as a community we discuss the principles in this and whether they should motivate us to change policy, MOS or make some other decision to avoid this kind of issue getting disruptive. I realize that this discussion is both about policy and about dispute and about user conduct - but I hope we can focus on the principle of it, and work towards finding a solution that will make most editors happy.
*:::::::::::So… If you suspect that someone is not arguing in good faith… just stop engaging them. If they are creating walls of text but not making policy based arguments, they can be ignored. Resist the urge to respond to every comment… it isn’t necessary to “have the last word”. ] (]) 21:57, 2 January 2025 (UTC)
*::::::::::::As the person ] demonstrates, you can't "just stop engaging them". When they then somebody has to engage them in some way. It's not about trying to "have the last word", this is a collaborative project, it generally requires engaging with others to some degree. When someone like the person I linked to above (now banned sock), spams low quality comments across dozens of AfDs, then they are going to waste people's time, and telling others to just not engage with them is dismissive of that. ] (]) 22:57, 2 January 2025 (UTC)
I think that different possible solutions could be to 1. create a policy that covers this, such as a parallel to WP:RETAIN that states that whenever two grammatical forms can be considered equally correct, the choices of the main contributor should be respected. 2. Require that people doing large scale changes of a single term or construction should maintain a list of articles that are exceptions and will not be "corrected". My suggested solutions can be seen in the essay ] ] · ] 19:27, 24 May 2015 (UTC)
*:::::::::::::That they've been banned for disruption indicates we can do everything we need to do to deal with bad faith users of LLMs without assuming that everyone using an LLM is doing so in bad faith. ] (]) 00:33, 3 January 2025 (UTC)
:: For the record, I think the editor you mention as an example is doing good work and contributing positively to the encyclopedia. I am with you in the spirit of your new Misplaced Pages essay, but the devil is in the detail of discussing when differences of usage matter and when they do not. As a reference on that topic, I recommend that all the editors following this discussion here or watching Maunus's essay under construction read Steven Pinker's book '']'' at their earliest opportunity. -- ] (], ]) 21:18, 25 May 2015 (UTC)
*::::::::::::::I don't believe we should assume everyone using an LLM is doing so in bad faith, so I'm glad you think my comment indicates what I believe. ] (]) 01:09, 3 January 2025 (UTC)
::I think there is a sufficient fraction of our readership that is going to find "comprised of" jarring that we probably ought to avoid it, even if there are ambits where it's considered unremarkable. It strikes me as rare that it would really be important to phrase things that way. This is sort of in the spirit of ] — don't strain to use forms that will appear inferior to a lot of readers, even if you don't think they're inferior, provided there are good substitutes.
:::What about the fraction of our readership that feels exactly the opposite? Who wins, and why? ] (]) 23:06, 31 May 2015 (UTC)
::Similarly, the which-v-that thing is mostly noticeable only to American readers, but if it makes no difference to UK readers, then why not use "that" even in BrEng articles? --] (]) 19:49, 24 May 2015 (UTC)
:::Whether or not it is important to phrase it like that is kind of besides the point - because there are significant fractions that feel either way. The point is that dozens of editors approach Giraffedata on his page to tell him to please not correct that which is not in their eyes wrong. Why should their views be overruled by Giraffedata and the other "significant fractions" views?] · ] 20:45, 24 May 2015 (UTC)
::::I think you meant to say "beside the point". --] (] · ] · ]) 08:54, 25 May 2015 (UTC)
::Meh. Unless it is part of a direct quotation, I agree with Trovatore that there's little benefit to insisting on using a form that many will find problematic. ] ≠ ] 19:59, 24 May 2015 (UTC)
:::OK then. I and plenty of other people find "consists of" to be problematic, so there's little benefit to Giraffedata's insistence on its use. ] (]) 23:07, 31 May 2015 (UTC)
:::There is a lot of words and usages that "many" find problematic, but which are nonetheless an entirely accepted and acceptable part of ordinary English usage. Should we allow other editors to create crusades to remove split infinitives? Prepositions at the ends of sentences? Misplaced Pages is a collaborative encyclopedia involving people with many different views, and that alone means there is value to allow pluralism whenever possible. What are your thoughts on the larger principle, that of avoiding conflict over irrelevant style issues?] · ] 20:40, 24 May 2015 (UTC)
* Has there been an RfC on this? Counting those who complain the loudest (on either side) on a user talk page isn't a reliable way of gauging community consensus. --] (]) 23:55, 24 May 2015 (UTC)
:I don't think there has been no, but counting those who complain the highest in an RfC also isnt a good way to gauge consensus necessarily. RfCU's have a tendency to degenerate very quickly. I had hoped that this could be a venue to address the issue without making it about the person, but obviously I shouldnt have named the thread the way I did then (I will proceed to rename it). That is why I am trying to see here whether anyone else sees the problem - which is not specifically Giraffedata's edits but the principle of avoiding conflict on arbitrary style issues. ] · ] 00:00, 25 May 2015 (UTC)
*"Comprised of" is a perfectly acceptable phrase used on a regular basis by the English-speaking world (see ] for some examples). I find it ] for one user to dedicate himself solely to removing it, despite objections of others. ] ]|] 00:01, 25 May 2015 (UTC)
*In areas of significant dispute, I think widespread changes should require explicit community support. RfCs may be flawed, but they are the best we have at this point; and most of the flaws are within us, not the process itself. I think (1) Giraffedata should run an RfC, bear the consensus burden, and refrain in the meantime, and (2) Giraffedata should agree beforehand that they will leave all changes of this type to others if the RfC fails, something of a voluntary topic ban. (Side note: Maunus said "RfCU's have a tendency to degenerate very quickly", and I don't know whether that was a typo. ] has been dead for some time, and that's not the kind of RfC I'm referring to.) ―] ] 05:36, 25 May 2015 (UTC)
::I think that is exactly a good solution. In the absence of a general consensus to deprecate the usage, he should refrain untill the consensus is generated. I forgot that RfC/U is gone, it would be an RfC about "comproised of" then.] · ] 19:31, 25 May 2015 (UTC)
*Numerous mainstream style guides deprecate the use of "comprised of"; hopefully, no one here wants to argue that point. I will remove or replace the phrase in any article of which I am doing a significant re-write because better word choices are available. That said, it is a relatively minor style point, like campaigning for the mandatory use of the serial comma or such. Frankly, I find it rather weird that anyone would aggressively work for the phrase's universal removal -- who has the time to spend on such a trivial matter across four million Misplaced Pages articles? There is an element of obsessive-compulsive insanity about it. I suppose the question that should be asked is ''Are these edits really disruptive, or just irritating to a handful of editors who think "comprised of" represents good writing?'' If these edits really are disruptive, how about some examples of such disruption? ] (]) 06:36, 25 May 2015 (UTC)
*:I don't think your question is answerable in any objective way; it's a matter of perspective. If shows nothing but increase in the use of "comprised of" in books, that's enough to require an RfC to establish community consensus. Any evidence from style guides could be presented and considered in the RfC. To clarify, I'm not suggesting that the RfC would decide whether "comprised of" should be abandoned completely, but whether there is community support for widespread changes of a crusade nature such as is being considered here. ―] ] 06:45, 25 May 2015 (UTC)
::::Just the fact that he can make hundreds of edits every day of the week, shows that the phrase is considered a totally natural part of many thousand editor's usage. it simply is waaaaay too commonly occurring to be considered incorrect. And of course it is found in literature by writers from Herman Melville to Pynchon. 4,3 million hits on google books, 1,1 million on google scholar.] · ] 20:42, 25 May 2015 (UTC)
:::::Myriad English-language quirks, colloquialisms and errors are "natural" parts of thousands of editors' everyday language usage, but that doesn't make them all appropriate in an encyclopedic register. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 23:56, 25 May 2015 (UTC)
:::Actually, the relevant Ngram viewer would seem to be one , which shows "comprised of" (falling rapidly) well ahead of "composed of" (rising slowly), which leads me to ask what's the third alternative that's taking grammatical market share away from "composed of"? But I think the issue is: does this change protect the integrity of Misplaced Pages more than it discourages participation? If "comprised of" is grammatical then it is hard to argue that obliterating it protects the integrity of Misplaced Pages. So then the follow-up question becomes do hypercorrections discourage participation? ] (]) 08:09, 25 May 2015 (UTC)
*I'm 100% in agreement with Trovatore. Giraffedata's edits are in the spirit of ], which takes precedence over ]. The former is about seeking common ground (e.g., the mutually acceptable "]" instead of "eyeglasses" or "spectacles", each of which is widely used only in certain English varieties). The latter is to be relied upon when there's no consensus that either/any option has tangible benefits when compared with the other. Despite a common misconception, ] is ''not'' an instruction to refrain from modifying any style that isn't flat-out incorrect, irrespective of the rationale.<br />Opinions differ as to whether "comprised of" is proper English. Does anyone assert that Giraffedata's alternative wording ''isn't'' (or that it's inferior in some other respect)? If not, what harm is he causing?<br />It seems as though much of the opposition is based on the principle of the matter, not a belief that Giraffedata is damaging the encyclopedia. Some view his edits – which they perceive as the replacement of one perfectly acceptable style with another – as utterly pointless. That's a valid opinion, but why is it grounds to counter his efforts? If the result is something equally good (albeit not better, in your view), what's the problem? That Giraffedata is wasting his time instead of doing something that you consider worthwhile?<br />In my opinion, the real waste of time is the crusade to counter Giraffedata's crusade. ''All'' of us have better things to do than revert harmless-at-worst edits and participate in discussions such as this one.<br />Of course, if someone asserts – in good faith – that some of Giraffedata's replacement wording ''is'' inferior to "comprised of" (for one or more reasons unrelated to which phrase appeared in the article first), that's a different story. I want to stress that I'm ''not'' referring to such a scenario above. —] 08:03, 25 May 2015 (UTC)
*:I have a few pet peeves myself, but I have refrained from hunting down and "fixing violations" because I felt that would be seen as disruptive. These pet peeves are no different from what is being discussed here. Like this, they are in gray areas where there is no clear consensus in style guides or among the Misplaced Pages community, but some will of course disagree with them since nothing has total agreement at Misplaced Pages. They are a matter of personal opinion, and, like Giraffedata, I would be implementing mine on a widespread scale. If your view wins out here I'll consider that a community green light for such activity. It would not be ]y behavior, as I would be doing it to make what I consider improvements to the encyclopedia, not simply to make a point; my desire to make these changes predates this discussion. Are you ok with this? ―] ] 08:50, 25 May 2015 (UTC)
*::If, among those with an opinion on the matter, a significant percentage regards the styling that you wish to remove as less valid than its potential replacement and substantially everyone else regards the two styles as equally valid, I'm beyond okay with that. —] 10:47, 25 May 2015 (UTC)
*:::Where are you getting your information about how the community feels about "comprised of"? ―] ] 11:18, 25 May 2015 (UTC)
*::::Please reread my 08:03 message, wherein I convey my observational impression and inquire as to whether anyone's position is inconsistent therewith. You're welcome to answer my questions, of course. —] 12:18, 25 May 2015 (UTC)
*:::::I have no particular perception in that area, and I wouldn't use it as a basis for argument if I did because it would be very error-prone. ―] ] 12:57, 25 May 2015 (UTC)
*::::::I'm not requesting an assessment of positions held by the community at large. I'm asking whether any individual's opposition to Giraffedata's edits stems from a sincere belief that the resultant prose is inferior to that which it replaced (i.e., that Giraffedata's changes aren't merely unnecessary, but actually reduce the articles' quality). —] 13:20, 25 May 2015 (UTC)
*:::::::Sorry for my misunderstanding. When writing new prose, I think I would generally choose "comprised of" over "composed of", I guess because "comprise" has a narrower range of definitions than "compose" and is therefore more precise. This is based on nothing but instinct, but I would have to say that, ''in my opinion'', "composed of" does slightly reduce articles' quality. Does the difference matter to five percent of readers? Probably not, and that's why I'm not roaming Misplaced Pages making this change wherever I see it. I simply ask that others offer me and those like me the same consideration. Does that answer your question? ―] ] 13:55, 25 May 2015 (UTC)
::::::::::::I think Giraffedata's replacements are sometimes, not infrequently but not always, clearly inferior. I think "composed of" and "comprised of" are not fully synonymous in all contexts, and sometimes give different nuances to the meaning. To me composed of means that something has been composed into a certain order, with the components in specific relation to eachother, whereas comprised of means that some category simply subsumes a set of elements.] · ] 19:31, 25 May 2015 (UTC)
:::::::::::::That could be a valid point in some contexts (especially patent law, as I observed elsewhere). But we know that Giraffedata doesn't robotically replace all cases of "comprised of" with "composed of", and in any given case it's unlikely that he (or anyone else) would object to some other alternative. The fact his choices are not 100% perfect every time according to everyone isn't indicative of a policy problem, a user behavior problem, a generalized style/grammar problem, or any other real problem. There are simply sometimes personal, contextual disagreements, that can be resolved in the usual way. I don't see any evidence provided that Giraffedata insists on retaining his preferred wording. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 00:03, 26 May 2015 (UTC)
*:::::::: The issue, though, is that you don't need an "of" with "comprised". "Comprise" is grammatically the equivalent of "include". You would not say that something is "included of" or "including of" something else; you would say that it "includes" something else, or is "including" something else. See ] for the use of these terms in patent law, which is very serious about using the right terms. Cheers! ] ] 16:25, 25 May 2015 (UTC)
*::::::::: But "include" and "comprise" are not equivalent. It is valid to use "comprised of" but not valid to use "included of". ] (]) 16:46, 25 May 2015 (UTC)
*:::::::::: Perhaps it is a matter of context, but a patent claim can either read "consisting of" or "comprising"; if "comprised of" were used, the claim would be invalid. ] ] 16:52, 25 May 2015 (UTC)
*::::::::::: I don't know that; but even if true, that a specific field has specific usage rules is not really relevant here. "The committee was comprised of three members." "Three members comprised the committee." Both are valid. ] (]) 16:57, 25 May 2015 (UTC)
*:::::::::]: ''The issue, though, is that you don't need an "of" with "comprised". "Comprise" is grammatically the equivalent of "include". You would not say that something is "included of" or "including of" something else; you would say that it "includes" something else, or is "including" something else.'' Let's suppose for a moment that there is an issue (though I'm not at all sure that there is one). Then this isn't it. Not only is it not the issue, but (like many people) you've conflated the verb COMPRISE (which of course has forms ''comprised'') with what's being (unnecessarily?) discussed in this section: the adjective COMPRISED. (See the article "]" for the distinction.) That you wouldn't say that something is "included of" or "including of" something else (as I too would not) is by the way. ¶ "Comprised of" is a mildly interesting formula. If it's anomalous, it's not uniquely so: consider the pair POSSESS and ''possessed of''. (Props to ] for ] to our attention.) -- ] (]) 00:25, 26 May 2015 (UTC)
*:::::::::: That goes straight to my later point, that we should not be using words with potentially confusing meanings when more common words are available that don't have this problem. ] ] 00:51, 26 May 2015 (UTC)
*:::::::::::: The problem with this word is that "The committee comprised three members" and "Three members were comprised by the committee" are {{em|also}} valid. See any dictionary if you don't believe me. Even ] has this in considerable detail. The word is an ] and thus its use is generally always going to be confusing to someone, even pretty intelligent people, no matter what. A strong case can thus be made that it should generally not be used here except where it {{em|must}} be, and probably the one and only case that is true is, as bd2412 and I have both already pointed out, in patent law, where it is a strictly defined ]. The fact that there are some editors who do not understand this problem and thus think there is no problem with "comprised of" does not somehow make their opinion that the phrase shouldn't be changed equally valid. ] does not require unanimity, and it very, very often comes down to which argument makes more sense, not which is argued with more fervor or preferred by more arguers. There simply is no contest when it comes to which side of that debate has more facts on its side and what conclusion they point to. The auto-antonym problem is genuinely intractable and incontrovertible. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 00:44, 26 May 2015 (UTC)
*:::::::::::::Please explain how comprise is an auto-antonym, how it can mean either ''x'' or ''not x''. ―] ] 00:27, 26 May 2015 (UTC)
*:::::::::::::Never mind. I read ] and consider that a misuse of the term, but I'm not going to quibble over unimportant semantics. ―] ] 00:48, 26 May 2015 (UTC)
*::::::::::::::I hadn't read that talk page thread, and can't vouch for it. If you just search this VP for "auto-autonomy", you'll find my reasoning on the matter. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 01:38, 26 May 2015 (UTC)
*My knee-jerk reaction is to object to editors going around enforcing their views on prescriptive grammar. This is mainly because prescriptivists are often misinformed. I also appreciate that using a form acceptable to both sides may result in a loss of richness in language (as Geoffrey Pullum and/or Arnold Zwicky put it: acceptance means that "crazies win"). However, on examining several of the edits by {{user|Giraffedata}} I generally found them to improve the style and/or reduce potential ambiguity, so I agreed with them. I also found the explanation on the user's subpage well-informed and valid (which does not mean that I agree with everything). Similarly with "that"/"which", where I ''usually'' find the use of "that" equally appropriate where "which" is used to introduce a "restrictive" relative clause. I have so far resisted the urge to revert what may look like prescriptivist "corrections", since I believe that the restrictive "that" is (at least consciously) accepted by more people, though it should also be noted that many who say they insist on "that" intuitively prefer "which" in some circumstances in their own writing. Another consideration is that some people object to use of "that" when the antecedent is human. So, on balance, I think the decision shoud be based on what is stylistically better and on commonality. For this sort of issue, I am not in favour of invoking strict application of anything like ] and ], which, I think, have the potential to create more disruption. I would be in favour of advice that recommended avoidance of ambiguity (for instance where "comprise" and "include" may be viewed as denoting substantially different logical relationships, the use or non-use of a comma may be regarded as insufficient differentiation between supplementary and integrated use of relative clauses, or the avoidance of a split infinitive may introduce ambiguity). --] (]) 16:02, 25 May 2015 (UTC)
*'''Oppose'''. There are several points to respond to in this proposal and thread:
{{collapse top}}
*#Ultimately, I agree with programmatic efforts to remove a potentially confusing construction that uses an ] like "comprise", and replace it with something clearer. If the same editor were changing all "comprised of" sentences to "comprising" ones, to invert which of the two self-contradictory meanings of "comprise" were being used, that would be an actual problem and potentially disruptive. Replacing either of them with clearer language is not. <small></small>
*#I agree ] supersedes ]. And it's a mistake to extrapolate from a handful of very narrowly defined rules like ]/WP:RETAIN, ] and ], which happen to be similar in only one way, that there's a general principle that whoever edited earlier has more editorial rights at a page than later editors. This is flatly contradicted by policy at ], and by the ]. WP would have nearly no content, and it would all be terrible, if it were true. The only reason those three rules swim against WP:BOLD is that too much editorial strife results otherwise, in those very limited circumstances. They're cases where ] is overriding a general rule, for serious reasons. <small></small> I shouldn't have to note this about ENGVAR/CITEVAR/ERA, but I clearly do, because people at disparate venues as ] debates and the very one we're in now, quite frequently try to extrapolate from them a generalized principle that names, spellings, styles, wording selections, sentence structures, etc. must not be changed because the original creator of the article or adder of the material didn't want it that way. It's total bollocks.
*#I have to observe that a great deal of what is done with ] by numerous editors, programmatically across many/all articles, is what someone pejoratively labelled "hypercorrection". The sky has not fallen, and we are not banning AWB. It's very purpose is semi-automating minor, ]y edits, so most of them will, pretty much by definition, look trivial to a lot of other editors, and be the kind of editing they don't feel they want to do or examine. One editor's "pet peeve" is another editor's "cleanup". One editor's "crusade" is another editor's "routine". One editor's "obsession with trivia" is another's "improving readability". Just because you don't share someone else's focus and feelings doesn't mean what they do is worthless. Also, the ] were a series of genocidal military campaigns by Christians to take the Holy Land from Muslims. Nothing on Misplaced Pages is sanely comparable to that, and every time someone refers to another editor as a "crusader" or "on a crusade", they're triggering a corollary of ], just substituting the Crusaders for the Nazis, but depending on pro-Christian bias in the English-speaking world to get away with it undetected by people's BS filters. It's also a ] violation.
*#There's a serious logic problem inherent in simultaneously holding that these things are trivial and don't matter, but that some people focusing on them discourages the participation of others. Only someone who is inordinately concerned with a tiny style/grammar nitpick like this would quit Misplaced Pages over it, or flee from editing a particular article, or some other ] response. Ergo, no one who feels "discouraged" over something like this can, without hypocrisy, criticize another editor for being supposedly too concerned about the alleged nitpick in question. What would really be happening is they're at least equally concerned about it, just opposed over what the "right" version is. And, in the more generalized case, it's pretty laughable when someone from a wikiproject, who rarely edits anything but articles on a narrow topic of limited interest to most readers and editors, tries to criticize ]/]-focused editors for being "too focused" on style and title editing. Cf. ].
*#Another latent issue in discussions of this sort is that the textual size of an edit really has nothing to do with its importance, and neither does the conceptual category into which someone wants to place it. A view that amounts to "little tweaks like swapping one word or glyph for another are just trivia", or more broadly "style and grammar matters are a waste of time" are common but idiosyncratic and emotional responses to a feeling one could probably summarize as "I don't personally care much about style, usage, grammar and punctuation, and I'm personally irritated by people who are". This attitude accounts for much of the virulently anti-] sentiment espoused by a small number of editors. At it's core, it's simply a sublimated form of ] and ]. Read any flamey WP:MOS or ]-related discussion, and you'll see immediately how quickly the veil drops and the hate comes out in plain view, including on this page right now (just text search for "obsessive" and you'll find numerous nasty examples, with plenty more a post or two away from these). A touch of this view also underlies comments like "I find it disruptive for one user to dedicate himself solely to" . Well, most of the rest of us find it disruptive for one user to try dictate what other editors may spend their volunteer time working on.
*#Whether something is technically "grammatical" (according to what sources, contradicted by what other sources?) has little to do with whether it's good writing. "My naked lamps migrate over chicken-massaged postal seeds" is perfectly grammatical but meaningless. The "comprise" problem is that the word is an ]. All of this grandstanding about it on both sides is a waste of time, because the real solution here is obviously to {{xt|avoid (and replace) auto-antonyms in any usage in which the meaning could be unclear}}. We should probably just put that into MOS. It really has nothing at all to do with whether the "proper" use (says who?) is "a collection comprising 50 pieces" (also conveyed by "a collection comprised of 50 pieces") or "50 pieces comprising a collection" (also conveyed by "50 pieces comprised by/in a collection"). Both contradictory meanings of "comprise" have long been well-attested, and while one is older and less common today, possibly headed for obsolescence (or, if you feel the other way, one is somewhat neologistic and only attested in more recent sources), neither are "wrong", despite them being opposite. <small></small>
*#Mandruss makes a good point: 'I have a few pet peeves myself, but I have refrained from hunting down and "fixing violations" because I felt that would be seen as disruptive.' We all do resist this urge. I've observed many times before that it's essentially impossible for any one person to agree with every rule in MOS, because the whole thing is necessarily a compromise between radically divergent style rules from every geographical and vocational part of the English-speaking world. The thing to look at here is that Giraffedata's edits are not simply a "peeve", a willy-nilly preference, but have a reasonable, reader-facing rationale. There's a big difference between that and, say, going around and changing every instance of "forwards" to "forward" just because you hate that minor redundancy and your English dialect doesn't favor it.
*#I also agree with all of Boson's commonsense observations, immediately above mine.
*#The proponent's '{{tq|Currently there is nothing in policy or practice that could deter me or someone else from doing so...}}' stuff, which almost has a ]y ''I'm gonna do this to punish you all, if you don't stop me by agreeing to the rules I want against my own bad idea'' air to it, also raises ] concerns. We should not and do not draft up elaborate, problematic policies to pre-emptively address problems that are not extant, because it just inspires troublesome editors to do precisely what we're newly proscribing when there wasn't anyone doing it before. Thus it's also an exercise in ].
{{collapse bottom}}
:<span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 16:58, 25 May 2015 (UTC) <small>Updated: 01:51, 26 May 2015 (UTC)</small></p>
:* For words like this that have multiple senses that can be confusing because of their nuance, can't we just replace them with clearer language? Perhaps "the collection includes 50 pieces" or "there are 50 pieces in the collection". While this is not at the level of certain hard sciences articles that use jargon that is incomprehensible to the average reader, vocabulary selections can be a barrier to clear understanding, and one that is easily avoided. ] ] 17:07, 25 May 2015 (UTC)
::* Yes, that's the very idea that's at issue here. Some editors are convinced that such constructions are in no way problematic, and want to take Giraffedata to task for changing them to clearer language. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 17:14, 25 May 2015 (UTC)
:::* I would not consider changing "comprised of" to "comprising" to be using clearer language; why not change those uses to more common words like "consisting of" or "including"? ] ] 18:12, 25 May 2015 (UTC)
:::: Giraffedata does not change it to comprising, in fact he also removes "comprising" and all other occurences of the verb comprise. The argument that he is simply taking thers to task to make them use clearer language is of course predicated on the notion that comprising is unclear or confusing - an assertion foer which there is no evidence whatsoever. It is not the case that auto-antonyms are necessarily confusing, and I have yet to see a usage of "comprised of" that was actually ambiguous. It is ambiguous only in the mind of someone who thinks it is language's job to be fully governed by binary logic and is unable to understand that meaning of words vary in context. If Giraffedata was actually making attempts to understand the reason why people choose to use the word or see how it fits into contexts, and only changing those that were possibly confusing then I am sure this issue would have never arisen. but that is not his approach, his approach is a one-size (his) fits all argument. Which can be reasonably and non-civility-breachingly be called a crusade.] · ] 19:25, 25 May 2015 (UTC)
::::: Here is . ] ] 19:31, 25 May 2015 (UTC)
::::::Hmm, I have seen him change "comprising" to "composed of" as well.] · ] 20:39, 25 May 2015 (UTC)
:::::::(EC) bd2412, Giraffedata most commonly uses "composed of" or "consists of", but explains the various replacements ]. It's also instructive to actually look at the related threads on Giraffedata's talk page. You find that the characterization of him as '{{tq|generally respond with contempt asserting that he has a right to change any word in the encyclopedia as he sees fit}}' is quite disingenuous, and borders on ]. Giraffedata even has a well-reasoned and well-researched user essay about the "comprised of" matter at ], but most complainants have not even looked at it, despite his edit summaries linking to it, and despite the fact that the whole point of it is addressing their concerns with reason and sources. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 20:01, 25 May 2015 (UTC)
::::::::I can count at least three editors on the talkpage saying that they have read his essay and disagrees, and requests for him not to continue to change it in the specific articles they have used the wording int. And in each case he responds in an offended tone, and draws the same ludicruous "ownership" argument that you defend below - which amounts to saying that the person who actually wrote an article has less of a right to determine wording in it than some one who hasn't because allowing any of their preferences to stand would be condoning article ownership. He makes no attempt to reach a consensus on the question, just stubbornly asserts his right to make the change. Yes, I get stubborn and angry as well when faced with that kind of an attitude - but that is EXACTLY the reason we need some kind of policy or guideline on this issue. ] · ] 20:31, 25 May 2015 (UTC)
:::::::::I have to respectfully disagree. I find his "tone" (to the extent that word makes sense in a text environment) to be measured, calm, and reasonable. Neither me nor Giraffedata have made any such argument '{{tq|that the person who actually wrote an article has less of a right to determine wording in it than some one who hasn't}}'; rather, the clear fact is that no editor has more or fewer editing rights in this regard, but the proposal we're discussing here would install one, that conflicts with already long-established policy. The rewording of it just above is also self-contradictory on its face, since making any such wording edit automatically constitutes helping to write the article, so it's a self-fulfilling "condition".<p>Some further background may help others understand why this dispute is a one-sided tempest in a teapot, a demand to fight being made against someone trying to avoid a fight (i.e. you engaging in what looks like the very "bullying" you complain of). Giraffedata said '{{tq|You don't have to agree with me either}}', and explicitly suggests that you revert him in articles where you insist on disagreeing with him, '{{tq|unless you're interested in finding a compromise or you think you can convince me this is the least awkward wording}}'. You'd earlier said to him '{{tq|What else do you want me to do, edit war?}}', to which he responded '{{tq|You won't be able to edit war on this, though, because I won't participate. Note that the Misplaced Pages definition of edit war requires making the same edit multiple times per day, and you have never seen me do that.}}' I just really don't see a problem here. You're being at least as "stubborn" as he is. I think anyone would be "stubborn" in the face of baldfaced claims that they have {{em|no right}} to edit an article here. When I turned your requirements back on you in a tongue-in-cheek way, you reacted with immediate umbrage, remember? <small>], shortly before you opened this VP thread.]</small> <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 23:52, 25 May 2015 (UTC)
::::::::::No, policy is very clear that slow editwarring is also editwarring. And all of te arguments you produce apply in equal measure to giraffedata- his edits are ALSO selfish, You seem to be graduating the latter of disgusting rhetorical strategies, now also attributing quotes to me that I never said. ] · ] 23:59, 25 May 2015 (UTC)
:::::::::::] does not say what you seem to think it says. I just read it top to bottom, in case it changed. Another relevant policy, ] makes it clear that ''consensus can change'', so the notion that once a change is reverted it can never be made again is not applicable. But let's return to your accusations and the facts: Where's the proof that Giraffedata has in fact ] the ] by slowly re-reverting and re-re-re-reverting the exact same edit? I see no evidence of this, but it is required. Direct policy quote: '{{tq|An edit war only arises if the situation develops into a series of back-and-forth reverts.}}' I'm sure you're aware, as we all are, that it's common editing procedure to try an alternative change if one change is reverted but an editor still feels the present text is flawed. This appears to be Giraffedata's editing pattern. It simply is not the case that he always changes "comprised of" to (or back to) a specific alternative like "composed of". You even said so yourself earlier. And if anyone doubts that I'm quoting accurately, they can simply go read the original thread, since I posted exactly where it is. <small>, it was from the sentence immediately preceding the quoted part, which anyone can verify.]</small> I have to observe that there's a clear pattern emerging here: I and others address your points in detail, while you respond with emotive hyperbole and ] distractions that seem to serve a ] purpose, but which evade answering most or any actual points raised against your position, and which especially fail to provide any evidence that is asked for. I have to say I don't think this strategy will be successful. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 00:43, 26 May 2015 (UTC)
::::::::::::Well, we did have at least one active admin who believed that every single change to another's contribution was "technically a revert", but I think he got over it when the absurdity of his position was explained (his "rule" meant that every single edit after the page creation was a reversion, no matter what the edit did). ] (]) 16:05, 29 May 2015 (UTC)
*Most people here are failing to address the substance of the proposal, sticking to their own opinions about "comprised of" specifically. The question is: what is the poper etiquette and procedure for enforcing one's pet peeves on other peoples writing? If there were a consensus that "comprised of" should not be used in wikipedia then of course that would settle the specific question here, but not the wider principle of how to handle style related conflicts where there is no "right answer". ] · ] 19:16, 25 May 2015 (UTC)
::In general, I think that if constructions such as "comprised of" are deemed grammatical, then it's unhelpful for someone to do nothing on Misplaced Pages but remove them. I would wonder about the motives of someone who edits in such a fashion anyway. Are they here to construct an encyclopedia or just to eradicate a grammar foible that they don't like? That said, if changing wording makes the sentence clearer for people to read, then fair enough. However, I would echo BD2412's point that, if you are going to make wording clearer, use a more common word entirely, or a construction that is unambiguous.
::Perhaps, if an editor wants to make a grammar edit where the grammar was previously correct, he/she should only do so while making other substantive edits to the article. ] (]) 19:28, 25 May 2015 (UTC)
*To get us back on track: Mandruss has let us know that if i turns out that there is a general consensus in this discussion to the effect that as long as someone can argue that their preference is preferable to some other choice, and there is no general consensus to say otherwise, then an editor is justified in programatically enforcing their preference, then Mandruss will personally take up such a practice. I will myself do the same of course. So what rules of etiquette would you like Mandruss and <s>me</s> '''I''' to follow as we purge the encyclopedia systematically of usages that bug us and that we consider to be likely to be bugging likeminded readers?] · ] 19:34, 25 May 2015 (UTC)
::I for one get my knickers in a twist when someone dare end a sentence with a preposition. ] ]|] 19:43, 25 May 2015 (UTC)
*The "substance of the proposal" is that Maunus wants to turn ] on its ear. His request for '{{tq|a parallel to WP:RETAIN that states that whenever two grammatical forms can be considered equally correct, the choices of the main contributor should be respected}}' is grotesque and un-wiki. Such an idea is not parallel at all to WP:RETAIN, but an argument for "whoever can dump the most words into a page, whether they are encyclopedic or not, controls it forever". Such a rule would be an unmitigated disaster, and nothing on Misplaced Pages works anything like that. See also ], where Maunus makes patent ] claims over an article: '{{tq|No you do not . If you were to actually do something useful and write an article, then you would have a right to make style choices for it.}}' Maunus then vows a ]y, ]ing revertwar campaign: '{{tq|I for one am not going to back down, and the next time you revert "comprised of" in an article where I have reverted you once I will not be this gracious about it.}}' (Note: Nothing was gracious about Maunus's post.). Most of what Maunus says in that thread is very confused about various policies and guidelines, as is what he's saying on this page, too. So, let's be really clear about this: No, Maunus, you do not own and control an article or any page here by virtue of jealously guarding it and ensuring that your own edits dominate its wording. The fact that you object to someone editing "other people's wording", by which you really mean {{em|your}} wording, means you do not understand ]. PS: A key detail in the proposal is ""two grammatical forms can be considered equally correct", which is rarely the actual case with any two forms, is certainly not the case with "comprised of" (which is widely denigrated in numerous reliable sources) and even in cases where is it approximately true that there's "equal" acceptance, it's usually a difference between UK and US English, i.e. it's already governed by ]. It simply comes up so infrequently that editors like Maunus will vow they're "not going to back down" and "will not be ... gracious about it", that we ] some new etiquette rule about people using AWB to make minor wording tweaks to articles in series and over time. That's what AWB is designed to do. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 20:01, 25 May 2015 (UTC)
::OOh what a civil way to insult and personally attack someone. Very impressive, you must have practiced that a long time. Giraffedata is the one who is in constant battleground mode and is slow editwarring without having any backing by consensus. If there were a consensus that comprised should never be used then I would follow it, but I am not obligated by policy to sit down and peacefully let him bully anyone who disagrees with him. If he wants to change this usage in articles on my watchlist he will have to get a consensus for it on the talkpage in each separate case untill there is a general projectwide consensus that supports him. And in doing so I will be entirely within policy as it currently exists. So either you make a set of guidelines for how to approach this issue, or I will be fully justified in reverting giraffedata on any article where he makes this change - untill a local consensus is established. That is the substance. So if you would like me not to do this I suggest you get your head out of your sanctimonious bum and address the actual issue. ] · ] 20:07, 25 May 2015 (UTC)
:::Thanks for making my case for me. Please actually read ] for starters. An "I will hunt you to the ends of the earth if you dare edit one of my pages" attitude is not going to serve you well here. Let's turn your reasoning back on you: Show me a site-wide consensus that the alternatives to "comprised of" that Giraffedata uses (there are lots of them, depending on the contexts in which the phrase is found) and which many other editors prefer, should never be used. None of us are obligated by policy to let you bully us into accepting wording that many find awkward, confusing, ignorant, or jarring. If you ever want to use that phrase again, you must get consensus for it on the talk page in each separate case until there is a general project-wide consensus that supports you. Does that sound fair and reasonable to you? BTW, I've actually read most of the relevant threads on Giraffedata's talk page, and he's quite calm, reasonable, civil, and patient, in stark contrast to the ranty fist-shaking posted there by you and several others with an axe to grind. The fact that it's in favor of some pet peeve instead of against one doesn't make it any less a case of axe-grinding and of advancing the very kind of pet peeve you just produced an essay about avoiding. PS: Being civil does not require being flattering or refraining from criticism. Here's an example of being actually incivil, you referring to another editor's work as '{{tq|your crusade}}'. (See my previous post for why this is essentially the same as saying "your Kristalnacht"). It's also hypocritical to disrespectfully confront another editor, and make long-term editwarring threats, and then call them '{{tq|confrontational and disrespectful}}'. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 20:48, 25 May 2015 (UTC)
::::::So this is where your argument collapses, and you are forced to admit that this kind of behavior is not ok and is disruptive and problematic. Yuo could only see that problem, when it was in the context of an edit with which you didnt agree and by an editor you didnt like. but you saw it. If you can see that it would be a problem if I were agressively inserting comprised of into articles to which I have not otherwise contributed without getting consensus, then of course you can realize that that is esxactly what Giraffedata is doing (and what I am not...yet). And no, using the word the word crusade as a metaphor for a similar agressive coampaign to make the rest of the world conform to one's belief is not a personal attack. Imputing other editors viewpoints they have not expressed or speculating about their real motivations in a snide and sarcastic manner is. So pardon me while I go vomit over your hypocrisy.] · ] 20:55, 25 May 2015 (UTC)
:::::::That response is an incoherent ], full of ], and unresponsive to any point I made. Hmm, "imputing other editors viewpoints they have not expressed or speculating about their real motivations..." A good example of that would be "could only see that problem, when it was in the context of an edit with which you didnt agree and by an editor you didnt like. but you saw it." Anyway, you utterly missed the point. I too think it would be unfair to require of you all those things before you could make such an series of edits! That was the whole message of that ''Gedankenexperiment''. Please exit the "me vs. them" mode. I believe, and Giraffedata has also said, you are free to make such edits yourself, even to simply revert him. No one is trying to impose pre-emptive consensus-seeking requirements on you before you can make minor wording tweaks to articles, much less invent some new policy to enforce it. ] is already genuine policy here. It's unreasonable of you to expect that policy to not apply to someone else just because you happen to disagree with them on some point of grammar, and to propose your new anti-BOLD policy. I'll quote Giraffedata directly why he doesn't think you {{em|should}} go on a spree of reverting him: '{{tq|that pretty selfish, since {{em|I}} think {{em|your}} choice is one of the most awkward, but I let it stand for months.}}' That strikes me as remarkably {{em|non}}-confrontational on his part. What we really have here is two editors each with a conflicting preference and each occasionally editing in their preference at a particular article to see if it sticks, and each using a similar rationale. This happens a zillion times a day on Misplaced Pages, and it's actually highly unusual for one party to such a disagreement to wait {{em|months}} before approaching the change again. It's the exact opposite of edit-warring. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 23:31, 25 May 2015 (UTC)later and reinser the same change.
:::::::::Sloweditwarring is also editwarring. And yes, Giraffedata does editwar, he will come back to the same article two months and revert again. And he does not keep a list of articles where his edits are contested. And when requested to make an exception he states that making the edit is his right and that people dissagreeing with him are wrong and selfish to insist in correcting his corrections back. And no, my polic is not anti-bold it is specifically about what to do when a bold style edit s reverted. And the answer is GET CONSENSUS> which is basic fucking policy already. So it is you who is trying to create an exempt category of edits, where the burden of discussion and argumentation is reversed. And yes I am being almost equally stubborn as giraffedata (not yet to the degree of embarking on a crusade) but for some reason you are fine with only faulting me for being stubborn and selfish not him, in spite of the fact that I am the one trying to make a proposal to avoid people being stubborn and selfish in general. ] · ] 00:10, 26 May 2015 (UTC)
::::::::::But only because it suits your editing goals. You've not identified a real problem, you've conjured up a hypothetical abuse problem, and are scapegoating an individual editor whose grammar you don't like. Re: '{{tq|Giraffedata does editwar}}' – For the fifth time: Prove it. Where are the diffs? Attempts at ] won't convince anyone. I don't only fault you for being stubborn. I clearly observed that being supposedly stubborn in response to threats to your editing rights is entirely reasonably, and that's it's hypocritical to call someone else doing that "stubborn" when you do it yourself. I scare-quoted "stubborn" because it's your word, not mine. We can analyze other word choices of yours like this. Take "crusade". Aside from my feeling that it's a variant of '']'' using Saracen-slaughter instead of Jew-slaughter, I think you making a big stink at VP about this rather illusory problem, that is not demonstrably ] anything at all, over a personality dispute with another editor, looks like a "crusade" to anyone who doesn't mind that pejorative label, and a particularly ] type of campaign at that. It's fallacious to point at one editor and say what amounts to ''We have to do something about this terrible problem that might happen if someone other than him abuses editing tools in ways I can't prove he's really doing.'' It's even worse to then defend at length all your animosity about this particular editor and his edits, while trying to convince us you are really focusing on a general problem, not this editor, and that people are misinterpreting the point of the proposal. It's disingenuous, or confused, I'm not sure which. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 01:35, 26 May 2015 (UTC)
*To me this sounds like a behavioral issue... not a content issue. The fact is, going on a Wiki-crusade of ''any'' sort is disruptive - no matter what the cause or how just and right it may be. Make a correction (of any sort) in one article, and you are seen as improving wikipedia ... go on a crusade, and make the same correction in thousands of articles, and you are quickly seen as being a disruptive asshole. ] (]) 20:32, 25 May 2015 (UTC)
:Not a content issue true, but a behavioral issue which is not covered by any of our behavior policies and which some editors condone because they happen to agree with the person causing the disruption. A solution to the immediate problem would be to establish a consensus that "comprised of" needs to be removed aggressively and people should have barnstaers for doing so. This would however quickly cause other people to do the same, introducing changes that may not be as agreeable to the majority, and then we have the problem again. So the solution is to have a behavior guideline on how to proceed when you want to make style changes across many articles.] · ] 20:36, 25 May 2015 (UTC)
*: I don't know about that. I have made hundreds of thousands of disambiguation fixes with AWB, and have done mass-repairs of misspellings of "received" and "hierarchy", and have only very rarely been criticized for doing so, even when I have made runs of many thousands of edits at a time. A style change that is likely to make the wording of an article more accessible to a broader audience is not much different, in my view. ] ] 21:50, 25 May 2015 (UTC)
:::Well there is a difference whether or not you can see it. Namely that Giraffedata's talkpage is full of equal amounts of praise and criticism. The difference may have to do with the fact that all users of English agree that recieve and haeirarchy are errors, but there is not such agreement on comprised of and a bunch of other style changes that some consider improving prose and accessibility and other's dont.] · ] 22:13, 25 May 2015 (UTC)
::::"Not much different" already concedes there's a difference. The talk page comments are not really equal, and Misplaced Pages doesn't work on the basis of voting and headcounts (except to an extent at ]). We all already surely know that people are an order of magnitude more likely to invest the time and energy to register a disagreement than an agreement; this is a well-known fact of human behavior generally. More interestingly, the praise received is often from editors who never even thought about the question before and were not participating in any related discussions, while the criticisms never seem to be from uninvolved editors. I don't see anyone at his talk page posting that they agree with one of his edits, but oppose his ability to use AWB to make it. No one is even saying that they are undecided on this usage point, but sure that he alone should somehow be retrained from being able to edit articles to reflect what he thinks is better wording. There's also a huge civility gulf; most of the commenters against this editing pattern arrive on his talk page with an aggressive "how dare you" attitude, a belittling view that he's ] and/or stupid, and that his contributions are of no value and "obsessive". It's deeply insulting, and evidentiary of problems that exist between those commenters' keyboards and chairs.</p>More importantly, the fact that many do consider the changes to be an improvement is reason enough to make them. ] is policy; the only way that WP improves is by people boldly making such changes. The burden is on resisters against wording tweaks to demonstrate that they should be reverted. A change in readability is not comparable to something like insertion of a new fact that may not be properly sourced. Changes to articles that trigger core policy concerns like ], ], or ] can basically be reverted with impunity until the policy concerns are satisfied, but there is no comparable policy concern raised by whether "comprised of" or "composed of" (or whatever) is better wording. The Misplaced Pages default is that such changes can be made "]". As Giraffedata himself frequently points out, other editors are free to revert such a change at an article. The only place in this dispute where I see anyone suggesting that one editor has no or less right to edit an article is Maunus's comments. I'll quote it again in case anyone missed it: '{{tq|If you were to actually do something useful and write an article, then you would have a right to make style choices for it.}}' I.e., if you did not write most of an article, you have no right to make style edits in it, and if you are not writing an article, the work you're doing on Misplaced Pages is not useful. It's simultaneously among the most confused and most insulting things I've ever seen here. (BTW, I'm having this reaction without previous involvement; I don't recall ever having interacted with Giraffedata in any way before today, and my interactions with Maunus have been brief, uncommon, and barely memorable.) <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 23:09, 25 May 2015 (UTC)
:::::Talk about not understanding basic policy: "The burden is on resisters against wording tweaks to demonstrate that they should be reverted." And here you are just inventing policy on the spot: "A change in readability is not comparable to something like insertion of a new fact that may not be properly sourced." Again thanks for the gratuitous condescension and veiled insults - I am getting used to that from the selfavowed upholders of civility by now. Please. And yes I admit wholeheartedly that I consider Giraffedata to be an utterly useless editor who is in no way improving the encyclopedia, but merely wasting other peoples time - but the purpose of this entire discussion is exactly not to enforce that view on others, but to find a way to deal with the problems that this approach would cause if it were generally adopted by others.] · ] 23:22, 25 May 2015 (UTC)
::::::]: '{{tq|Note that an editor who repeatedly restores his or her preferred version is edit warring, whether or not the edits were justifiable: "but my edits were right, so it wasn't edit warring" is no defense.}}' You self-admittedly directly revert Giraffedata, and have vowed on this talk page to continue to do so, programmatically and pointedly: '{{tq|I for one am not going to back down, and ... I will not be ... gracious about it}}'. For I think the fourth time, I demand proof that Giraffedata is actually engaging in reverts at all. What I see is that he sometimes makes similar edits to the same page, sometimes months after the fact. These do not constitute reverts. But if he once in a while incidentally makes the same edit, it doesn't establish anything like a pattern of editwarring as defined at ] policy. It's unlikely that any regular editor has never incidentally made the same minor editor long after having made it once before. Next, an observation that some things, like insertion of alleged facts without sources, trigger specific policy concerns, like compliance with ], while making a stylistic change does not trigger them, is not "inventing policy on the spot", it's reading comprehension and basic reasoning. Thanks for at least and at last conceding that you have what we can all see is an intense personality conflict with Giraffedata. No new policy needs to address that. More to the main point, we don't need a new policy that sharply conflicts with established policy, to address ], like people doing stupid or malicious things with tools like AWB, when we already have permissions approval and revocation processes for them. I think I've covered every point I need to about this proposal and your defenses of it, and it already has so many other objectors that it could never gain consensus, so I'm skeptical that I need to respond here further. My interaction with you directly is just getting circular because you keeping going back to ] is asking evidence instead of providing the evidence. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 01:25, 26 May 2015 (UTC)
:I know this discussion isn't supposed to be about the word "comprise", my efforts to minimize its use to mean "compose" in Misplaced Pages, or me, but since I'm being used as the primary example of the problematic behavior, I want to correct a few misconceptions a person could have after reading some of the above: "comprised of" is not a pet peeve of mine; and I don't enforce any particular grammar in Misplaced Pages.
:"Comprised of" does not peeve me any more than about a hundred other forms of fractured English, and probably a thousand other human behaviors, that are common. And it doesn't peeve me more than it peeves everyone else. There are plenty of people who are equally peeved by this - I find them everywhere I look. But I have probably read more "comprised of" than anyone in the world, and have become desensitized to it like a surgeon is to blood.
:Enforcing a view would be watching an article and reverting any attempt to change it to something inconsistent with that view. In contrast, I edit an article once. That's nearly always enough, but in rare cases, someone changes it back to its original wording any time I touch it. 2-3 times a year, I'll find that same article again and edit it again. This is entirely reasonable, because any day, the owner of an article could retire or otherwise loosen his grip on the article and give the rest of us a shot. And it's simply not a great burden on someone who cares enough about these two words to argue about it to reinsert them 2-3 times a year. Misplaced Pages even provides a convenient "I'm right and you're wrong" button for that. Ideally, the person would seek a compromise, but I certainly don't insist. ] (]) 02:29, 26 May 2015 (UTC)
::Bryan, I would suggest that when you change some bit of wording, and another editor reverts your edit... ''you'' should be the one who reaches out and seeks a compromise. Try discussion rather than slow revert warring. If you are sure that your reverted edit is right ... don't just go back a few months later and make the same rejected edit again... go to the article talk page and ''persuade'' the other editor to see your point of view - engage in discussion. ] (]) 12:17, 27 May 2015 (UTC)
:::I guess you missed my point. I don't seek compromise because I just roll over and give the other person what he wants -- let someone else fight him on it while I work on things I do better. I don't consider it a reversion to make a similar edit 6 months later, and I certainly don't think you can call something that lazy a revert war. There has to be a horizon past which editors are allowed to call it a new day, forget the history of the article, be bold, and say "what's the consensus ''today''". We just can't say that an editor can plant a flag on an article (or sentence) by reverting a change and say the matter is now presumed to be under dispute for the rest of time. On the timescale of Misplaced Pages, in which there have to be 3 edit cycles in a ''day'' to define a revert war, in which conflicts are often resolved by protecting an article for ''a week'' or blocking an editor for a ''day'', and it's hard to find an article that hasn't been edited in the last 3 months, 6 months is forever. If an article gets anonymously ''vandalized'' twice a year, it doesn't even qualify for article protection - we just say revert the vandalism when it happens and forget about it.
:::So if we're going to talk about an editor's right to enforce some word usage across the encyclopedia, we're going to have to come up with some example where the editor actually make articles use the word that way when at least one person wants to use it a different way. ] (]) 21:59, 27 May 2015 (UTC)
::::I have long advocated a similar approach to weeding out external links. If you get reverted, then move on. Maybe you'll happen to run across the same article in another month or year, but just move on. The person who reverted you might be right or might be wrong, but you can weed out a dozen other link farms in the time that it would take to have a discussion about it. ] (]) 16:17, 29 May 2015 (UTC)
I have no strong opinion on the comprised-versus-composed question, and I understand that that's not the purpose of this debate anyway. The question simply seems to be about the value of that ''kind'' of behavior. Is it good for the project when one editor swaps ''en masse'' one acceptable phrase for another acceptable phrase based on nothing but his personal preference? Given the contention that apparently surrounds the comprised/composed example, I'd have to say no, it's not good for the project.<p>While such large-scale behavior may be technically acceptable, it's nonetheless divisive and (rightly or wrongly) a conflict generator, as this and other threads demonstrate. That cost swamps whatever meager benefit we might get from some minor grammatical tweak. ] <span style="font-size:smaller"><nowiki>]<nowiki>]</nowiki></span> 14:58, 27 May 2015 (UTC)
*My comment to the mass-changer is just an observation that I hope may be helpful: when you are changing, your reason is 'you, author, mean something else - so I am changing it to what you mean' - but somehow they have communicated to you what they mean - having done, so - their usage is clear ''before you changed it''. ] (]) 16:23, 27 May 2015 (UTC)
::I believe we're mainly talking about cases where the mass changer does not claim the original meaning is unclear. For example, if someone were to change every instance of "could of" to "could have", there wouldn't be any issue of what was meant by the original. ] (]) 21:30, 27 May 2015 (UTC)
::(ec) Re: '{{tq|you, author, mean something else - so I am changing it to what you mean}}' – This essentially does not compute as any kind of analysis of Misplaced Pages editing. The instant I save a change to an article, there no longer exists any "what I mean", there is only what the article actually says, and how readers around the world are going to interpret it. This is why several of us commenting here think this is just a personal editing spat, with ] overtones. If you edit something into a WP page, you're giving those words away to the entire world to edit, "mercilessly". <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 00:22, 28 May 2015 (UTC)
:::"Essentially does not compute"? That's an absurd phrase and an absurd thought. You are editing someone else's work ''always'' when you edit (unless it's your own work you're revising). That hardly means they own it but you had better know that is what you actually are doing, or you really should not be editing here at all. ] (]) 16:30, 28 May 2015 (UTC)
::::You're making the same point I am without seeming to mean to: "You are editing someone else's work ''always'' when you edit". Yes, exactly. The obvious consequence of this is when you're done with your edit, the next edit by someone else may be editing your work (which you gave away to the project and the public, so it's no longer yours except in a vague historical sense, evidenced in edit history). The proponent's premise (underlying this proposal, and explictly stated at Giraffedata's talk page, though I've quoted it several times here already) is that he should have more editorial rights than another editor to control the content of an article, in proportion to how much content he's put into the article vs. how much the other did. Misplaced Pages does not and cannot work that way. Sorry you didn't get the "]" humor; see that article for the cognitive dissonance to which the phrase refers. In a nutshell, the dissonance here is caused between conflating "my own work" (translation: effort I put it in, the past tense), and "my own text" (translation: content I own and control, in the present tense). These concepts are dissimilar, and the second does not apply in any way to Misplaced Pages. Yet one can sometimes feel about the former the way that one might feel about the latter. This is an impulse that has to be restrained (and re-trained). <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 19:05, 28 May 2015 (UTC)
::::::Well, your alleged humor is senseless, as it has nothing to do with understanding the meaning of someone's words - and as you agree you are editing someone's words, understanding their meaning is vital. That you think it's just about editorial control, when what's being discussed is mass changes that others object to and disagree with in substance and in how they are being done is just your mistake. ] (]) 23:15, 28 May 2015 (UTC)
::It's not a crusade. Comprised means "composed of", So comprised of means "composed of of". Many people makes this silly mistake. We can say "comprised one-third of" , This is not Simple English Misplaced Pages. If he is correcting grammar, so what? <span style="border:1.5px solid lime;padding:1.5px;">] (])</span> 13:50, 29 May 2015 (UTC)
:::He's not just "correcting grammar". He's "correcting grammar that a small number of people believe is already correct". ] (]) 16:17, 29 May 2015 (UTC)
:::: To be specific, he's changing "grammar that a small number of people believe is already correct", but which might be confusing to some people, to "grammar that everyone believes is correct", and will be less likely to confuse anyone. ] ] 00:11, 1 June 2015 (UTC)
:::], you seem to be conflating the verb ''comprise'' (which of course has the form "comprised") with the adjective ''comprised'', whose alleged misuse is what some people here don't like. Also, your argument seems odd: "I met up with an old friend for lunch" has pretty much the same meaning (in my idiolect, at least) as "I met an old friend for lunch", and I can therefore say that ''meet'' (here) means ''meet up with''; but I don't then go on to say that "meet up with" therefore means "meet up with up with" and thus is a silly mistake. Moreover, ] (and others), our man Bryan is hardly "correcting grammar that a small number of people believe is already correct"; rather, he's doing some rewording of what he and a lot of people (including a high percentage of "language mavens") think is infelicitous (or worse) but a lot of people (including a high percentage of ditto; see the '']'') think is perfectly OK. (As for actual ''linguists'', they're rarely interested in such trivia.) ¶ I've yet to see either (i) a credible account of confusion caused by "comprised of", (ii) similar indignation over "possessed of" (which in en.wikipedia), or (iii) an explanation of how "comprised of" is worse than "possessed of". -- ] (]) 00:46, 1 June 2015 (UTC)
Here's my answer to Maunus's question: If you are making the same grammatical or spelling change repeatedly, you should:
# be right, according to prescriptivists (e.g., all of those reliable sources that say Giraffedata's changes are correct), even if the grammar construction you're removing is "common";
# pay (just) enough attention to what you're doing that you aren't correcting grammar or spelling in direct quotations;
# not bother UNDOing reversions to the "wrong" version;
# not bother starting discussions with people who do not understand the problem you're fixing, although you should reply (or not) to direct messages about the grammar just like you would reply (or not) to any other direct message; and
# not keep a list of articles where some other editor prefers a ''laissez faire'' approach to grammar, even though this means that you might re-encounter the error and re-fix it later. For manual edits, lists of random articles basically never work in practice anyway.
My main reason for my last three points is efficiency, although some of them happen to have anti-edit warring effects as well.
To give a different example, editors can and should make changes to replace the common, non-standard spelling "alright" with the standard, prescriptivist-approved "all right". But are song titles or direct quotations, and should be kept. (However, in my quick check, looking for this word is a very effective way to find poor writing about pop culture subjects.) Similarly, "alot", which is always considered incorrect, should be fixed whenever outside a title or direct quotation, because clearly improves the article. But if someone comes along and decides that the original "designers were able to alot a more comprehensive medical reediness kit into missions" is actually better... you know, I can probably trust another editor to handle it. ] (]) 16:49, 29 May 2015 (UTC)
:What is this adjective "comprised"? It's not in Chambers' dictionary. The entry for "comprise" is
<blockquote>vt to contain, include; to comprehend; to consist of (often incorrectly, with "''of''").</blockquote>
Cosmic Emperor says
{{talkquote|Comprised means "composed of".}}
It doesn't. "Comprises" is the right form, "is comprised of" is the wrong form. "Comprise" does not have a passive form. "compose" does. That's another reason why "comprised of" is wrong and "is composed of" is right. The definition of "compose" is
<blockquote>vt to put in order or at rest; to settle or soothe; to design artistically; to set up for printing; to create.</blockquote>
The passive doesn't imply anything has been put in order, just a set of constituents. I see that "comprised of" is not allowed in patent claims. That's unsurprising since incorrect terminology is not allowed in legalese. "Possess" is a strawman because it can take the passive. ] (]) 10:20, 1 June 2015 (UTC)
:Dictionaries, even respected ones, are very poor guides to lexical categorization. As an example, even now most refuse to recognize that intransitive prepositions exist. Rather, dictionaries seem designed not to upset fogies who prefer not to question what an earlier generation of fogies taught them, ignoring decades of consensus in mainstream linguistics. (Grammatical understanding is not just a matter of parroting what you heard decades earlier; it actually ''advances''. In fits and starts, and with some missteps, yes; but it advances all the same.) See ], "" on the matter. Additionally, if you're going to limit yourself to the definition(s) of ''one'' dictionary, then that dictionary had better be very large: I'd recommend the '']'' (oed.com). -- ] (]) 02:18, 2 June 2015 (UTC)
::Didn't you just say that "actual linguists" are "rarely interested in such trivia"? But now you want us to pay attention to "mainstream linguistics" (none of whom I see cited here on the question of whether this particular phrase is accepted)?
::I'm actually not sure that we need to worry too much about linguistics. This construction annoys some people, makes other people believe that Misplaced Pages is poorly written, may mislead still other people, and ''can be replaced by something that is always accepted as being good grammar''. We should put this in the same category as replacing, say, outdated names for ethnic groups: there's no urgent need to keep it, and there's some good in replacing it. So why not just do that, rather than trying to preserve something that is awkward and that of reliable sources say is wrong, or suitable only for informal writing? ] (]) 02:41, 2 June 2015 (UTC)
::{{red|Making it crystal clear}}
{{talkquote|Comprised means "consist of" or "To be composed of" or " to include" .}}
And he is famous in media, I am not mentioning his real name here due to privacy policy.<span style="border:1.5px solid lime;padding:1.5px;">] (])</span> 10:46, 1 June 2015 (UTC)
: Who's famous in media, and what's it got to do with the discussion? ] (]) 17:53, 1 June 2015 (UTC)
:: And of what is this res comprised? Consider your pet peeve may be another editor's pet phrase—approach replacement accordingly. — ] (]) 04:36, 2 June 2015 (UTC)
== Article consensus vs blacklist consensus ==
There have arrived a problem where ] consensus conflict with the blacklist consensus, and as a work-around, ] exist in text format rather than link format.
The article consensus was to add the link to the article, but a non-unanimity consensus had been reached previously on the blacklist page that the ''type'' of link that the link represented was bad, and a wildcard entry had been added for the type. A whitelist request was thus requested, but denied since the type of the link was unchanged and thus the situation was identical to the one at blacklisting. Looking at ] and ], it all seem to assume that blocked content are unwanted spam that the community/consensus around an article would not want.
The blacklist policy gives a rather free range of operation to the blacklist operators, by the inclusion of the "or simply violates Misplaced Pages's policies" line. With this and the infamous ] we have gotten to the situation where one consensus and interpretation of Misplaced Pages's policies has been decided on the blacklist, and an other consensus and interpretation on a article talk page. This creates a result in which the link in question is technically blocked in the link format, but then used in text format in the article as per consensus. This seems as an imperfect solution, sends conflicting messages to editors, and where clear policy would help find a consistent solution. ] (]) 08:49, 25 May 2015 (UTC)
:] ] ]. The "simply violates Misplaced Pages's policies" means that ideology trumps building an encyclopaedia. For some reason the content creators have never accepted that. ] (]) 09:00, 25 May 2015 (UTC)
::As I've already advised you elsewhere, if you want to reverse existing consensus, or dispute that a consensus exists, raise an RfC. <span class="vcard"><span class="fn">]</span> (<span class="nickname">Pigsonthewing</span>); ]; ]</span> 12:30, 25 May 2015 (UTC)
:Consensus at a single article talk page cannot overrule wider community consensus; this is detailed at ]. <span class="vcard"><span class="fn">]</span> (<span class="nickname">Pigsonthewing</span>); ]; ]</span> 12:30, 25 May 2015 (UTC)
{{ec}}Local consensus on a talk page can't override our policies. This is a good thing IMHO and hardly to do with ideology. ] (]) 12:56, 25 May 2015 (UTC)
Interesting case. The operators of TPB were ] as accessory to crime against copyright law in Sweden and ] states that "For policy or technical reasons, editors are restricted from linking to the following, '''without exception''': Policy: material that violates the copyrights of others per contributors' rights and obligations should not be linked." By providing direct links to TPB sites, are we saying that they don't primarily host copyright infringements according to U.S. law? --] <sup>]</sup> 13:27, 25 May 2015 (UTC)
:Some interesting comments.
:@Andy; is each blacklist entry equivalent to an policy decision regarding that entry? Both people on the talk page and the people on the blacklist read the policies, reach their own conclusion based on the policy, and thus a consensus was formed on two separate Misplaced Pages pages. People reaching different conclusion based on same policy is not unheard of, and when the participants are low (3 in one, 3 in the other) I would even be so bold to say it is common. The question is which consensus should overrule the other, and the current consequences that both consensus are followed at the same time.
:@NeilN; The site do not have material that violates copyright, but does encourage copyright infringement, which is what the site founders got caught for. People have discussed this subject several time if TPB official link triggers ELNEVER, and previous consensus has been to keep it, and that anyone is free to send a email to the foundation and ask for their legal input (vaguely recall someone doing that, but could be mistaking it for an other article discussion). The question regarding linking to people who encourage copyright infringement, and if it itself is illegal under U.S. law is an interesting question (Would be assisting in assisting in copyright infringement, but that would only be up to discussion in Sweden if "the primary purpose of the service (Misplaced Pages) is assistance" as per court judgment quote), but I suspect that is a discussion for different time and place. ] (]) 14:30, 25 May 2015 (UTC)
* There is no policy violation in linking to something that is not a copyright violation at a site that has some things on it which are copyright violations. If this were the case, we could never link to anything on YouTube or any site like it, since enormous amounts of material on them are copyvios. BTW, it's a known fact that some bands, etc., intentionally release their own material via TPB and other torrent sites. So, the plain language of policy, that "material that violates the copyrights of others per contributors' rights and obligations should not be linked", is not in any way triggered by a link to something non-infringing on a site that may have infringing things on it, including the site's homepage if the article is about that site, or a source being cited if that's the principal or only way to obtain it. Whether there's a simple way to work this fact into how the blacklist works is an open question, as is whether the editors who control it will cooperate enough to make any such solution likely to be practical. There may be non-"ideological" reasons for blacklisting certain types of link (<code>magnet:</code> URLs, or whatever; I honestly don't know what URL schemes and such are blacklisted). And in the case of the archive.is kerfuffle, there are obviously additional concerns at work, including the behavior on WP of people associated with the site. That said, the fact that a few editors took it upon themselves to strip archive.is URLs out of innumerable citations without replacing the <code>archiveurl</code>s with alternatives is at least potentially a serious problem (how serious depends on how many of those changes resulted in actual dead links, and have not been fixed). Archive.is no longer appears to be blacklisted.<p>PS: I'm not convinced by an overbroad, lopsided ] interpretation here. Specific decisions to blacklist this or that often appear to made with very little input, even if they're not unilateral or uncontestible. I'm sympathetic to the view that there being a site-wide, centralized place for this at ] means a decision to blacklist something is less likely to be a LOCALCONSENSUS itself, but that doesn't mean that it's infallible and that local consensus problems can't arise there. It's a much more rarified venue than, say, ] or ], which have wide participation and are watchlisted by thousands of editors. If editors at articles keep coming up with local consensuses that the blacklist has entries on it that impede improving the encyclopedia, then it's probably true. And it also may be the kind of instance where resorting to ] is actually valid. The fact that the blacklist technologically makes it hard to IAR in certain ways is a little problematic. This might be mitigated by the fact that there's more than one way to get around the blacklist if you really want to, e.g. using an "approved" archive site to archive a page at an "unapproved" archive site. >;-) <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 17:59, 25 May 2015 (UTC)</p><p>PPS: The only time I've done this myself that I recall is actually a good illustration of legitimate IAR against the blacklist: I needed to cite a page at a blacklisted site as a ] for a fact, pertaining to the site itself, that could not be ] any other way, and had to do this with URL fudgery that tricked the blacklist. There is no policy that I have to obey the blacklist, but there is both a policy that facts in articles must be verifiable, and another for my right to ignore a rule, like the blacklist, if it really is necessary to do so in order to improve the encyclopedia. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 00:10, 28 May 2015 (UTC)
*It seems to me that there is very little copyrightable material on TPB homepages on various domains other than the logo. If there is no claim that the logo is copyright-infringing (and I've not seen such a claim), I see no policy-based reason that they can't be linked to. I believe that technically this can be allowed by ensuring that the entry in the blacklist entry contains \b which would match the / between the domain and the path path of the URL. If the blacklist maintainers are not amenable to this, start an RFC to make them amenable (and feel free to ping me of you start an RFC). ] (]) 01:46, 26 May 2015 (UTC)
==Non-free image resolution==
I've asked before, but never got a clear answer:
Non-free logos should be around 400 x 400px, so I've been told. But, I see them often replaced with ] format. But those are really high resolution, which is not allowed per .
I do not know if and are relevant. They go on and on and I do not know where they end up on the matter.
Guidance please. ] (]) 21:02, 27 May 2015 (UTC)
:The template doc you linked to already explains this: {{tq|"for ], this would involve the level of detail in the image"}}. ] (]) 21:42, 27 May 2015 (UTC)
:The only allowable use of non-free logos in an SVG format is if the SVG originated directly from the company/entity that the logo represents, such as from their website, a PDF with the SVG embedded or the like. This avoids mis-representation of the SVG in other formats. Otherwise, a low-resolution PNG/JPG must be used instead. User-created versions of non-free logos are not allowed. --] (]) 21:45, 27 May 2015 (UTC)
:The use of SVG reproductions to replace non-free logos has always struck me as dubious at best. Maybe the legal principles here are solid, but I suspect a bit of magical thinking here. At any rate: if the issue is that smaller non-free raster logos are being deleted when a high-quality SVG image is uploaded -- and then the SVG also gets deleted for being ''too'' high quality for a non-free image -- this sounds like a reason to update the deletion rationale to make sure that the eligible non-free images are prioritized over ineligible ones. ] (]) 21:46, 27 May 2015 (UTC)
::Where would you suggest as the best place post such am RfC? --] (]) 23:24, 27 May 2015 (UTC)
:::I really hadn't thought about it, but now that you'd ask, I'd suggest ], ] and possibly also ] and ]. ] (]) 00:28, 28 May 2015 (UTC)
::Exactly, ]. The older version gets deleted as unused non-free, then if the svg gets deleted, we have to go find and upload the image again. I'm experiencing this right now at my talk page, not with svg, but high-res pngs. I wish we could have some sort of bright line in terms of px. As for ]'s {{tq|"for ], this would involve the level of detail in the image"}}, well every svg I've ever seen is infinitely high res. I mean, that's what they are, right? Perfectly smooth lines no matter how much you blow them up, ideal for copying. ] (]) 04:30, 28 May 2015 (UTC)
:::SVGs aren't infinitely high res. They still lose detail when you blow them up, just not in the same way as raster images. ] (]) 04:58, 28 May 2015 (UTC)
::::The legal principle involved here is that a non-free use image may not be rendered any larger than is required for the purposes of identification and/or critical commentary. Since an SVG is infinitely scalable, regardless of the underlying quality of the image, Misplaced Pages has no control over the scale at which it may be rendered and is hence is in breach of that requirement by default. The "safest" option is to avoid use of SVG for all non-free content. ]<sup>♦]</sup> 05:45, 28 May 2015 (UTC)
:::::Thanks Philg88. And thanks, ]. I stand corrected. I can't get my head around all this res and quality stuff. I do know, however, that these non-free logos and such are just for visitors to identify the subject. When I download some of them, they're a foot wide with sharp edges. Anyhow, for logos, which is what made me post here, can we set a px width or height maximum? ] (]) 06:22, 28 May 2015 (UTC)
::::::This of course applies only to ''commercial'' images, since the purpose is to minimise commercial damage. When dealing with a non-commercial image, it need not and should not be altered. ] (]) 09:33, 28 May 2015 (UTC)
:::::::Absolutely, ]. In fact, can we nail something down right here and now for logos/"commercial" images? How about for future uploads no bigger than 400px x 400px with no svgs allowed? Those would be fine for articles while useless for other purposes. ] (]) 09:45, 28 May 2015 (UTC)
:::::::"Commercial images" for the purposes of non-free are images that are meant to be sold, such as press agency's photographs. A non-free logo for a commercial corporation is a non-commercial but non-free image. However, we still want to minimize the size of any non-free used, and that size typically should aim to be less than 0.1 megapixels. --] (]) 17:43, 28 May 2015 (UTC)
: Sigh. I went for a good while without seeing yet another debate where people misguidedly argue that SVGs are somehow impossible to use for non-free logos and should be blanket-banned because they can be rendered at arbitrary sizes. Trying to apply raster image pixel limits to something that isn't a raster image is as pointless as trying to apply article-space-specific policies to talk pages and noticeboards.
: The key, as has long been established, is level of detail: if rendering the image at 4000×4000 doesn't reveal any detail that is too small to be visible at 400×400, why try to claim the SVG is somehow "too big"? If a user-created SVG is faithful to the source to the limits of the usual resolution, there's no difference between it and a user-created PNG or JPG version. And if a logo is simple enough to be represented perfectly as a low-complexity SVG intended for rendering at small image sizes, we might well have a {{tl|PD-simple}} going on. ]] 00:07, 29 May 2015 (UTC)
::There's zero issue on logos that fail the threshold of originality, to use a user-created SVG licensed as CC-BY or equivalently free. The issue with a user-created version of a non-free logo - which by definition has creativity involved in the base logo - is that the user's version would be a derivative work, not just a simple mechanical rescaling, so creates added complexity. (And this ignores what auto-trace functions try to do which are imperfect to start). If there is a company-owned SVG available, that's fine, but otherwise the non-free logo should be a low-resolution raster image, no matter how easy it would be to recreate it. --] (]) 00:12, 29 May 2015 (UTC)
::: Why should a non-free logo be a low-resolution raster image? Why not a low-detail vector image, if that works as well or better for our purposes? ]] 00:23, 29 May 2015 (UTC)
::::A low-detail vector - presuming one that had been made by a WP user - is a derivative work, so that complicates the copyright matters, an additional copyright layer atop the logo copyright. So from a free-ness standpoint, the raster version of the logo is freer than the SVG, and we're encouraged to use the free-est version possible. Further, there's little use in a scalable raster image, since most non-free logos are used only once, in the infobox of the entity they represent, and nowhere else. For something like flag icons where the image has many possible uses and thus having infinite scaleability makes sense, it just doesn't for non-free logos. --] (]) 00:27, 29 May 2015 (UTC)
I have no idea where we are at now. Is there any ''rule'' I can use to know which logos are too high res, and which are acceptable?
I like to keep things simple. What is not simple is all this talk of scalable raster, high-resolution vector graphics, embedded PNG/JPG, infinitely scalable SVG, commercial-non-commercial, low-complexity with simple mechanical rescaling and added complexity for a low-detail vector image.
How about common sense? To me:
*] is nice, rotten quality. Perfect to identify the subject and useless otherwise.
*] is as sharp as can be. If I owned that logo, I would certainly say that Misplaced Pages carries a version that is of commercial quality that can be taken, modified, and used elsewhere. .
] (]) 21:04, 30 May 2015 (UTC)
:For the two images, differing claims are made for non-free use; for the University of Petroleum image, no claim of low-resolution is made. To meet the current letter of non-free use, .svg renditions should not be used. For an easy-to-understand example, try a .jpg to .svg conversion of the Harbin image and an .svg to .jpg conversion of the Beijing image. Only .jpg seems to meet the requirements (there is an on-line image converter at .
::Ignoring the license for a second, should ] be allowed at all? ] (]) 00:15, 31 May 2015 (UTC)
:::Well, I favor changing what seems to be current consensus interpretation of fair use to, instead, the most liberal interpretation possible of non-free image applicable under US law. That is, both examples you give are OK. There is actually ''more'' information in the Harbin image than the Beijing image; I would guess the NSA could recover a comparable quality .svg from the .jpg (I tried, but my efforts left out the orange). — ] (]) 02:09, 31 May 2015 (UTC)
::::More information? I think we need to be clear on the spirit of the law. It is about not hosting images that can be used commercially, right? Well, the Harbin image is useless while the Petroleum image is perfect for copying. Isn't that what this is all about? ] (]) 05:19, 31 May 2015 (UTC)
:::::Sorry, I apologize for adding to the confusion. I should not have raised the question of how en.wikipedia should interpret fair-use in ''this'' discussion. However, looking at the fair-use rationales used for .svg images in en.wikipedia, what I see are more liberal interpretation of fair-use. Which solves technical problems like to-use-or-not-use .svg images, while improving the utility of en.wikipedia. Either way, the logos in your examples are on the Internet, and the barn door is open (as it should be; a shoddy replication of a logo should ''not'' be used). — ] (]) 07:26, 31 May 2015 (UTC)
::::::Hi, ]. Not at all. You didn't cause the confusion. The "barn door" thing is no excuse for copyvio text, so I do not know why high-res logos are okay, but fine. I think I will just drop it. The community doesn't seem to find all of this an issue. All the best, and sorry to waste everyone's time with this. ] (]) 00:49, 1 June 2015 (UTC)
:'''No''' -- whatever you think of LLMs, the reason they are so popular is that the people who use them earnestly believe they are useful. Claiming otherwise is divorced from reality. Even people who add hallucinated bullshit to articles are usually well-intentioned (if wrong). ] (]) 06:17, 2 January 2025 (UTC)
{{outdent}}
*'''Comment''' I have no opinion on this matter, however, note that we are currently dealing with a ] and there's a generalized state of confusion in how to address it. ] (]) 08:54, 2 January 2025 (UTC)
These discussions just go round and round, with each side claiming to know The Truth™ about fair-use limits to the "resolution" of a vector graphic. How about we try something totally radical, like finding an actual attorney who specialized in this area, and requesting a formal white paper or recommendation or whatever they call it? Maybe we could find someone willing to work pro bono, or maybe we could get an ] to pay for it, but how about we try to get an expert answer from a legitimate professional? ] (]) 03:32, 1 June 2015 (UTC)
*'''Yes''' I find it incredibly rude for someone to procedurally generate text and then expect others to engage with it as if they were actually saying something themselves. ] (]) 14:34, 2 January 2025 (UTC)
:This discussion repeats something that has popped up over and over again. Logos will often have to be considered on a case by case basis as organisations usually have special rules about their use. Often they do not want their image tarnished by a degraded quality. Often they give permission for use to identify them. But derivatives of the logo are not usually permitted. User created .svg files are likely a derivative. But a company supplied .svg should be fine to use here. Anyone else making use of fair use logos from Misplaced Pages has to justify fair use for themselves, and Misplaced Pages and its editors do not have to worry about it. ] (]) 04:31, 1 June 2015 (UTC)
* '''Yes, mention''' that use of an LLM should be disclosed and that failure to do so is like not telling someone you are taping the call. ] (]) 14:43, 2 January 2025 (UTC)
:I agree with {{u|WhatamIdoing}}: all of this analysis as to what "really" is or isn't permissible with respect to reproducing a logo is pure guesswork in the absence of qualified legal guidance, and could be more harmful than helpful. Rather than reading the tea leaves or engaging in ] ], I think it would be wiser to reject any SVG logos at all (or perhaps all logos, period) until the legal issues can be resolved. ] (]) 15:17, 1 June 2015 (UTC)
*:I could support general advice that if you're using machine translation or an LLM to help you write your comments, it can be helpful to mention this in the message. The tone to take, though, should be "so people won't be mad at you if it screwed up the comment" instead of "because you're an immoral and possibly criminal person if you do this". ] (]) 07:57, 3 January 2025 (UTC)
: '''No.''' When someone publishes something under their own name, they are incorporating it as their own statement. Plagiarism from an AI or elsewhere is irrelevant to whether they are engaging in good faith. ] (]) 17:29, 2 January 2025 (UTC)
* '''Comment''' LLMs know a few tricks about logical fallacies and some general ways of arguing (rhetoric), but they are incredibly dumb at understanding the rules of Misplaced Pages. You can usually tell this because it looks like incredibly slick and professional prose, but somehow it cannot get even the simplest points about the policies and guidelines of Misplaced Pages. I would indef such users for lacking ]. ] (]) 17:39, 2 January 2025 (UTC)
*:That guideline states "Sanctions such as blocks and bans are always considered a ''last resort'' where all other avenues of correcting problems have been tried and have failed." ] (]) 19:44, 2 January 2025 (UTC)
*:: ] isn't a guideline, but an essay. Relevantly though it is being cited at this very moment in ]. ] (]) 20:49, 2 January 2025 (UTC)
*:::I blocked that user as NOTHERE a few minutes ago after seeing them (using ChatGPT) make suggestions for text to live pagespace while their previous bad behaviors were under discussion. AGF is not a suicide pact. ] (]) 20:56, 2 January 2025 (UTC)
*'''No''' - Not a good or bad faith issue. ] (]) 21:02, 2 January 2025 (UTC)
*'''Yes''' Using a 3rd party service to contribute to the Misplaced Pages on your behalf is clearly bad-faith, analogous to paying someone to write your article. ] (]) 14:39, 3 January 2025 (UTC)
*:Its a stretch to say that a newbie writing a comment using AI is automatically acting in bad faith and not here to build an encyclopedia. ] (]) 16:55, 3 January 2025 (UTC)
*::That's true, but this and other comments here show that not a few editors perceive it as bad-faith, rude, etc. I take that as an indication that we should tell people to avoid doing this when they have enough CLUE to read WP:AGF and are ]. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 23:06, 9 January 2025 (UTC)
*'''Comment''' Large language model AI like Chat GPT are in their infancy. The culture hasn't finished its initial reaction to them yet. I suggest that any proposal made here have an automatic expiration/required rediscussion date two years after closing. ] (]) 22:42, 3 January 2025 (UTC)
*'''No''' – It is a matter of how you use AI. I use Google translate to add trans-title parameters to citations, but I am careful to check for Google's output making for good English as well as reflecting the foreign title when it is a language I somewhat understand. I like to think that I am careful, and I do not pretend to be fluent in a language I am not familiar with, although I usually don't announce the source of such a translation. If an editor uses AI profligately and without understanding the material generated, then that is the sin; not AI itself. ] (]) 05:04, 5 January 2025 (UTC)
*:There's a legal phrase, "when the exception swallows the rule", and I think we might be headed there with the recent LLM/AI discussions.
*:We start off by saying "Let's completely ban it!" Then in discussion we add "Oh, except for this very reasonable thing... and that reasonable thing... and nobody actually meant this other reasonable thing..."
*:The end result is that it's "completely banned" ...except for an apparent majority of uses. ] (]) 06:34, 5 January 2025 (UTC)
*::Do you want us to reply to you, because you are a human? Or are you just posting the output of an LLM without bothering to read anything yourself? ] (]) 06:08, 7 January 2025 (UTC)
*:::Most likely you would reply because someone posted a valid comment and you are assuming they are acting in good faith and taking responsibility for what they post. To assume otherwise is kind of weird and not inline with general Misplaced Pages values. ] (]) 15:19, 8 January 2025 (UTC)
*'''No''' The OP seems to misunderstand ] which is not aimed at weak editors but instead exhorts stronger editors to lead by example. That section already seems to overload the primary point of WP:AGF and adding mention of AI would be quite inappropriate per ]. ]🐉(]) 23:11, 5 January 2025 (UTC)
*'''No'''. Reading the current text of the section, adding text about AI would feel out-of-place for what the section is about. <span class="nowrap">—] (] | ])</span> 05:56, 8 January 2025 (UTC)
*'''No''', this is not about good faith. ] (]) 11:14, 9 January 2025 (UTC)
*'''Yes'''. AI use is ''not'' a demonstration of bad faith (in any case not every new good-faith editor is familiar with our AI policies), but it is equally not a "demonstration of good faith", which is what the ] section is about.
:It seems some editors are missing the point and !voting as if every edit is either a demonstration of good faith or bad faith. Most interactions are neutral and so is most AI use, but I find it hard to imagine a situation where AI use would point ''away'' from unfamiliarity and incompetence (in the CIR sense), and it often (unintentionally) leads to a presumption of laziness and open disinterest. It makes perfect sense to recommend against it. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 22:56, 9 January 2025 (UTC)
*'''Yes'''. Per Dass Wolf, though I would say passing off a completely AI-generated comment as your own ''anywhere'' is inherently bad-faith and one doesn't need to know Wiki policies to understand that. ] (]) 23:30, 9 January 2025 (UTC)
*'''Yes'''. Sure, LLMs may have utility somewhere, and it might be a crutch for people unfamiliar with English, but as I've said above in the other AI RfC, that's a ] issue. This is about comments eating up editor time, energy, about LLMs easily being used to ram through changes and poke at editors in good standing. I don't see a case wherein a prospective editor's command of policy and language is good enough to discuss with other editors while being bad enough to require LLM use. ]<span style="color: #3558b7;"><sup>]</sup>]</span> 01:26, 10 January 2025 (UTC)
*'''No''' - anyone using a washing machine to wash their clothes must be evil and inherently lazy. They cannot be trusted. ... Oh, sorry, wrong century. Regards, --] (]) 01:31, 10 January 2025 (UTC)
== Edit quality in Android application ==
== ] ==
Several contributors, including myself, don't understand the point of the ‘edit quality’ mention in the Android application.
I've written up a fairly detailed interpretive/guidance essay on ] and their relation to ] / ] / ] / ] issues. I invite a perusal at ]. It's not a user essay, and is intended for community development, though of course I'd prefer talk page consensus before significant bold changes, other than to add something I've obviously missed, or to correct obvious errors. While I only spent the afternoon "codifying" it, it represents several years of approaching and thinking about the issues raised by that class of sources. It is written to address genuine WP editing problems I've encountered (though using hypothetical or broad examples to avoid "picking on" any particular pages, interests, or editors). Avoiding ] / ] issues was a goal. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 00:01, 28 May 2015 (UTC)
:] seems like it covers the same bases, only for 1ary and 2ary sources. A merge might make sense. --] (]) 05:00, 28 May 2015 (UTC)
::<del>In theory, though the new page uses a more explanatory essay style. It's probably more practical to develop the idea and examples and make sure all the ground is covered in an essay, then approach ] with a proposal to integrate the gist, than try to change RS while the ideas are still gestating. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 11:12, 28 May 2015 (UTC)</del>
::{{ping|Izno}} Sorry, I initially misread that as linking to ]. I agree these pages could and perhaps should merge, at least conceptually, but the approaches are very different. I'm not sure it's {{em|necessary}}, though I think I'd prefer that outcome. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 14:42, 28 May 2015 (UTC)
:::I don't think ] particularily well-written or of much practical value. Somewhat like ] (tagged "historical" long ago, and of little consequence).
:::I'd help improve it if I thought it could become something practical, like I improved the primary sources proposal into ] with a somewhat different scope, and more practical. But then again there's already ] which imho covers the essence on all three types of sources, apart from what is already in the ] policy. --] (]) 11:44, 28 May 2015 (UTC)
::::{{Ping|Francis Schonken}} Does this mean you think it can't be made practical? In what way(s) is it not practical? The intent of the page is to be practical, which is why it's organized in a step-wise way (identify tertiary sources, mindful of exceptions to that general rubric, then determine reliability, then check that the use you have in mind is actually appropriate). The SWOT analysis is a nice start, but it's a way of thinking about and evaluating the relative qualities of different source types, not advice, really. I'll link to it from the one I've been working on, but they're completely different kinds of documents. The ''raison d'etre'' of ] in the first place is that WP:PSTS and the other policy and guideline pages barely mention tertiary sources at all, and many editors are not at all clear on the difference. It's my estimation, based on experience, that a large proportion of editors think that most tertiary sources, with the possible exception of other encyclopedias, are secondary. There's frequent trouble discerning tertiary sources that are not in particular categories/formats, like encyclopedias, dictionaries, databases, and textbooks; it suggests widespread confusion that the type of publication rather than the type of content is a determining factor. It's a problem of instilling that "the medium is not the message" when it comes to determining source levels. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 14:32, 28 May 2015 (UTC)
:::: I have to agree with you, ]. I also think that the essay is lacking of concreteness. Lot's of bullet points, lot's of examples like "...''is usually considered tertiary, although sometimes it might be considered primary or secondary''." I think the essay still needs a great deal of work with respect to the readability, and a great deal of concreteness. Cheers! ] (]) 20:56, 28 May 2015 (UTC)
:::Yes, I noticed the delta in approaches to the differing pages, so the merge is probably non-trivial. Amusingly, you highlighted yet another related page at ] on my watchlist today.... --] (]) 14:45, 28 May 2015 (UTC)
::::Yeah, I've been making some conforming tweaks here and there. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 15:01, 28 May 2015 (UTC)
::Parts of that ] essay are actually wrong. In a list of examples of what would probably be secondary not primary sources, it gives '{{tq|Historical reports: A special television program is broadcast to mark the 60th anniversary of the end of World War II. A newspaper column lists the events reported in that newspaper on the same date from 25, 50, 75, and 100 years before.}}' The second of those is actually a tertiary source, not secondary. And the first one is possibly also tertiary, if the content is regurgitative of previously published work without including some kind of novel analysis/synthesis/commentary. Many "infotainment" one-hour documentaries on The History Channel, etc., are tertiary sources (and some that come to exaggeratory conclusions, as many of them do, are primary with regard to such claims; I don't mean to overgeneralize). I found this problem in the essay just by skimming it for a minute or two; there are probably others. Yeah, I looked again for 15 sec., and found that the "Book reviews" entry makes the same kind of error; such reviews can be primary (aesthetically opinional), secondary (analytical), or tertiary (neutrally abstracting), but the essay calls a neutral abstract primary. This is clear evidence of the kind of problems I was talking about in response to Francis, above. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] ≽<sup>ʌ</sup>ⱷ҅<sub>ᴥ</sub>ⱷ<sup>ʌ</sup>≼ </span> 15:01, 28 May 2015 (UTC)
:::Yes, I agree that it's complicated. Those examples could both be secondary or tertiary, depending on their content. For example, a list of events that identifies key events or shows their relationship to each could easily be secondary, but a semi-random list of whatever interested the editor would probably be tertiary—assuming that you're using a system that has tertiary sources at all. (That would be very appropriate for a history-related subject, but legal scholars apparently do not admit that tertiary sources exist. It's either "primary" or "not", and the "not primary" sources are called secondaries.) ] (]) 17:03, 29 May 2015 (UTC)
: IMO, you're going in entirely the wrong direction. "Primary", "secondary", or "tertiary" '''doesn't actually matter''' except if you're trying to pass ], and all the talk about it in various policies and guidelines is a poor heuristic that has taken on a life of its own over the years after losing sight of the original purpose.
: We cite what reliable sources say, we don't apply any of our own analysis no matter whether the source is "primary", "secondary", or "tertiary". There's nothing magical about "secondary" sources that makes their analysis better than that of a "primary" or "tertiary" source. The heuristic exists simply because a "primary" source is likely to have raw data without much analysis that's useful for writing an encyclopedia article, while a "tertiary" source is more likely to be so far from the facts that we risk importing bias and oversimplification.
: And, as has already been said above, the same source can be considered "primary", "secondary", ''and'' "tertiary" depending on what exactly we're using the source for. One of my favorite examples is a source where John Doe makes some statement X: it could be an unreliable secondary source for "X", but a reliable primary source for "John Doe says X" that we might well use if it's relevant to the topic at hand what John Doe says about it. ]] 00:21, 29 May 2015 (UTC)
::The concepts matter a lot for ]. But I agree with you that "primary" is not a synonym for ]. ] (]) 17:03, 29 May 2015 (UTC)
The ] states that edit quality is ‘based on how many of your edits were reverted’. Is this the only criterion used? If so, calling it ‘edit quality’ is presumptuous, not to say irresponsible, given that there should be so many criteria. What are the different levels of judgement: excellent, good, bad, horrible, etc. ? What does this mean for developers, bots, patrollers and administrators? Whatever the case, the consequences of such a statement could be quite serious.
== Disney Cinema ==
It's clear that the choice to keep this mention in the application doesn't just concern the application developers or even a small team, but all Misplaced Pages contributors, whatever their language. So we think it's important that you answer our questions. <small>(As my English isn't very good, could you answer me in basic English, or at least without figures of speech? Thank you in advance.)</small> ] (]) 13:12, 7 January 2025 (UTC)
A user at ], has to the page in which I changed the incorrect "Disney Movies" to the correct name of the channel "Disney Cinema", the user mentioned "this is the English language wikipedia not the French WP". This comes as a surprise since we have many French TV channels at ] listed in their original French. -- ]<font color=#4169E1> '''//''' </font>]</nowiki>'''</font>]] 13:46, 28 May 2015 (UTC)
:Hi Albag. I agree with the core of your message. But I don't get why you have been redirected to English Village Pump. This should be discussed somewhere on Meta or Mediawiki wiki, as it's relevant for all Misplaced Pages communities, not only the English one. (You and I are from fr-wp.) Best, — ''']''' <sup><small style="border-bottom:1px solid">]</small></sup> 13:28, 7 January 2025 (UTC)
:As a first step, I would suggest that you engage the objecting editor in ''discussion'' (on the article's talk page) - so you can explain ''why'' it might be more appropriate to use the french name in this context. ] (]) 14:06, 28 May 2015 (UTC)
::Wouldseem the othereditorwon'tchangehisopiniononthis. --] (]) 07:21, 29May2015 (UTC)
::Thanks ]. According to ], the place to discuss would be there : ]. --] (]) 13:43, 7 January 2025 (UTC)
== Allowing non-admin "delete" closures at RfD ==
At ], a few editors ({{u|Enos733}} and {{u|Jay}}, while {{u|Robert McClenon}} and {{u|OwenX}} hinted at it) expressed support for allowing non-administrators to close RfD discussions as "delete". While I don't personally hold strong opinions in this regard, I would like for this idea to be discussed here. ]<sub>]<sub>]</sub></sub> (]/]) 13:13, 7 January 2025 (UTC)
::If the source is reliable i think we can use non-English sources especially those languages which uses alphabets similar to English. Provided if a third good faith editor who can read-write-understand both languages,verifies that the source is reliable. And google translate is the best way. Notable French, German, Japanese newspapers , magazines and Authors are also reliable.<span style="border:1.5px solid lime;padding:1.5px;">] (])</span> 13:44, 29 May 2015 (UTC)
*] --] <sup>(])</sup> 14:10, 7 January 2025 (UTC)
*While I have no issue with the direction the linked discussion has taken, I agree with almost every contributor there: As a practice I have zero interest in generally allowing random editors closing outside their permissions. It might make DRV a more chatty board, granted. ] (]) 15:02, 7 January 2025 (UTC)
*:Tamzin makes a reasonable case in their comment below. When we have already chosen to trust certain editors with advanced permissions, we might allow those folks to utilize them as fully as accepted practice allows. Those humans already have skin in the game. They are unlikely to act rashly. ] (]) 19:32, 7 January 2025 (UTC)
* To me, non-admin delete closes at any XfD have always seemed inconsistent with what we say about how adminship and discussion closing work. I would be in violation of admin policy if I deleted based on someone else's close without conducting a full review myself, in which case, what was the point of their close? It's entirely redundant to my own work. That said, I can't really articulate a reason that this should be allowed at some XfDs but not others, and it seems to have gone fine at CfD and TfD. I guess call me neutral. {{PB}} What I'd be more open to is allowing page movers to do this. Page movers do have the tools to turn a bluelink red, so it doesn't create the same admin accountability issue if I'm just cleaning up the stray page left over from a page mover's use of a tool that they were duly granted and subject to their own accountability rules for. We could let them move a redirect to some other plausible title (this would violate ] as currently written but I think I'd be okay with making this a canonical exception), and/or allow moving to some draftspace or userspace page and tagging for G6, as we do with {{tl|db-moved}}. I'll note that when I was a non-admin pagemover, I did close a few things as delete where some edge case applied that let me effect the deletion using only suppressredirect, and no one ever objected. <span style="font-family:courier"> -- ]</span><sup class="nowrap">[]]</sup> <small>(])</small> 19:07, 7 January 2025 (UTC)
*::I see that I was sort of vague, which is consistent with the statement that I hinted at allowing non-admin delete closures. My main concern is that I would like to see our guidelines and our practice made consistent, either by changing the guidelines or changing the practice. It appears that there is a rough consensus emerging that non-admin delete closures should continue to be disallowed in RFD, but that CFD may be a special case. So what I am saying is that if, in practice, we allow non-admin Delete closures at CFD, the guideline should say something vague to that effect.
*::I also see that there is a consensus that DRV can endorse irregular non-admin closures, including irregular non-admin Delete closures. Specifically, it isn't necessary for DRV to vacate the closure for an ] admin to close. A consensus at DRV, some of whose editors will be uninvolved admins, is at least as good a close as a normal close by an uninvolved admin.
*::Also, maybe we need clearer guidance about non-admin Keep closures of AFDs. I think that if an editor is not sure whether they have sufficient experience to be closing AFDs as Keep, they don't have enough experience. I think that the guidance is clear enough in saying that ] applies to non-admin closes, but maybe it needs to be further strengthened, because at DRV we sometimes deal with non-admin closes where the closer doesn't respond to inquiries, or is rude in response to them.
*::Also, maybe we need clearer guidance about non-admin No Consensus closures of AFDs. In particular, a close of No Consensus is a contentious closure, and should either be left to an admin, or should be Relisted.
::] (]) 19:20, 7 January 2025 (UTC)
:::As for {{tq| I can't really articulate a reason that this should be allowed at some XfDs}}, the argument is that more work is needed to enact closures at TfD and CfD (namely orphaning templates and emptying/moving/merging categories). Those extra steps aren't present at RfD. At most, there are times when it's appropriate to unlink the redirect or add ]s but those are automated steps that ] handles. From my limited experience at TfD and CfD though, it does seem that the extra work needed at closure does not compensate for the extra work from needing two people reviewing the closure (especially at CfD because a bot that handles the clean-up). Consistency has come up and I would much rather consistently disallow non-admin delete closures at all XfD venues. I know it's tempting for non-admins to think they're helping by enacting these closures but it's not fair for them to be spinning their wheels. As for moving redirects, that's even messier than deleting them. There's a reason that ] advises not to move redirects except for limited cases when preserving history is important. --] <sup>(])</sup> 20:16, 7 January 2025 (UTC)
::@]: I do have one objection to this point of redundancy, which you are ]. Here, an AfD was closed as "transwiki and delete", however, the admin who did the closure does not have the technical ability to transwiki pages to the English Wikibooks, meaning that I, who does, had to determine that the outcome was actually to transwiki rather than blindly accepting a request at ]. Then, I had to mark the pages for G6 deletion, that way an admin, in this case you, could determine that the page was ready to be deleted. Does this mean that that admin who closed the discussion shouldn't have closed it, since they only have the technical ability to delete, not transwiki? Could I have closed it, having the technical ability to transwiki, but not delete? Either way, someone else would have had to review it. Or, should only people who have importing rights on the target wiki ''and'' admin rights on the English Misplaced Pages be allowed to close discussions as "transwiki and delete"? ]<sub>]<sub>]</sub></sub> (]/]) 12:04, 8 January 2025 (UTC)
*I do support being explicit when a non-administrator can close a discussion as "delete" and I think that explicitly extending to RfD and CfD is appropriate. First, there can be a backlog in both of these areas and there are often few comments in each discussion (and there is usually not the same passion as in an AfD). Second, the delete close of a non-administrator is reviewed by an administrator before action is taken to delete the link, or category (a delete close is a two-step process, the writeup and the delete action, so in theory the administrators workload is reduced). Third, non-admins do face ] for their actions, and can be subject to sanction. Fourth, the community has a role in reviewing closing decisions at DRV, so there is already a process in place to check a unexperienced editor or poor close. Finally, with many, if not most discussions for deletion the outcome is largely straight forward. --] (]) 20:01, 7 January 2025 (UTC)
*There is currently no rule against non-admin delete closures as far as I know; the issue is the practical one that you don't have the ability to delete. However, I ''have'' made non-admin delete closures at AfD. This occurred when an admin deleted the article under consideration (usually for COPYVIO) without closing the related AfD. The closures were not controversial and there was no DRV. ] ] 20:31, 7 January 2025 (UTC)
== MOS:IDENTITY clarification ==
::The situation you're referring to is an exception allowed per ]: {{tq|If an administrator has deleted a page (including by speedy deletion) but neglected to close the discussion, anyone with a registered account may close the discussion provided that the administrator's name and deletion summary are included in the closing rationale.}} --] <sup>(])</sup> 20:37, 7 January 2025 (UTC)
*Bad idea to allow, this sort of closure is just busy work, that imposes more work on the admin that then has to review the arguments, close and then delete. ] (]) 22:05, 7 January 2025 (UTC)
* Is this the same as ] above? ]] 23:04, 7 January 2025 (UTC)
**Yes, ]. Same issue coming from the same ]. ] (]) 03:52, 8 January 2025 (UTC)
* (1) As I've also ], the deletion process guidelines at ] do say non-admins shouldn't do "delete" closures and do recognize exceptions for CfD and TfD. There isn't a current inconsistency there between guidelines and practice. <br>(2) In circumstances where we do allow for non-admin "delete" closures, I would hope that the implementing admin isn't fully ] before implementing, but rather giving deference to any reasonable closure. That's how it goes with ] closers asking for technical help implementing a "moved" closure at ] (as noted at ], the closure will "generally be respected by the administrator (or page mover)" but can be reverted by an admin if "clearly improper"). ] ] 08:41, 9 January 2025 (UTC)
*'''Comment''' - A couple things to note about the CFD process: It very much requires work by admins. The non-admin notes info about the close at WT:CFD/Working, and then an admin enters the info on the CFD/Working page (which is protected) so that the bot can perform the various actions. Remember that altering a category is potentially more labour intensive than merely editing or deleting a single page - every page in that category must be edited, and then the category deleted. (There are other technical things involved, like the mess that template transclusion can cause, but let's keep it simple.) So I wouldn't suggest that that process is very useful as a precedent for anything here. It was done at a time when there was a bit of a backlog at CfD, and this was a solution some found to address that. Also - since then, I think at least one of the regular non-admin closers there is now an admin. So there is that as well. - <b>]</b> 09:14, 9 January 2025 (UTC)
As is to be expected, there's some issues brought up at ] on how to handle certain aspects of self-identity in Misplaced Pages articles. ] clearly indicates that in issues of self-identified gender, Misplaced Pages defaults to the most recently expressed wishes of the subject of the article. The question is, to what extent does MOS:IDENTITY apply. Does it apply only to the article about the subject, or does it apply Misplaced Pages wide, to every article, and in every context. The specific question came up with how to identify Ms. Jenner in regards to her participation at the ], she identified ''at that time'' as a male. We know that in the article about her, we use her preferred name and female pronouns throughout. The reasonable question becomes, in articles where the time period in question does not include the phases of her life where she self-identified as female, do we use her current identity or her historic identity? To put this up to a !vote:
*If the expectation is that an admin needs to review the deletion discussion to ensure they agree with that outcome before deleting via G6, as multiple people here are suggesting, then I'm not sure this is worthwhile. However, I have had many admins delete pages I've tagged with G6, and I have been assuming that they only check that the discussion was indeed closed as delete, and trust the closer to be responsible for the correctness of it. This approach makes sense to me, because if a non-admin is competent to close and be responsible for any other outcome of a discussion, I don't see any compelling reason they can't be responsible for a delete outcome and close accordingly. <span style="white-space: nowrap;">—] <sup>(]·])</sup></span> 19:51, 9 January 2025 (UTC)
== Placement of dynamic list template ==
;Option 1)
*In articles outside of the biography itself, the timeframe of which only covers the period when the person self-identified as one gender, with a particular name, default to the historic name and gender
Where does the template {{template|dynamic list}} actually go? It superficially looks like it should be a hatnote at the top of the article, but there are a great number (perhaps a majority) of dynamic list articles where the template is placed under the infobox and lead. I can't find anything in the MOS specifically addressing this. ] 21:44, 7 January 2025 (UTC)
;Option 2)
:The template documentation, which you linked to, addresses this: Place this notification template immediately before the applicable ] (i.e. in a section, not at the top of the article). This template will automatically add the article to ]. ] (]/]) 21:47, 7 January 2025 (UTC)
*In every article across Misplaced Pages, all mentions of the transgendered person should use their current name and gender identity.
::In many cases, the template is neither at the very top nor within a section. Just to be clear, this placement is not correct? ] 22:25, 7 January 2025 (UTC)
:::It should go right above the list. ] (]/]) 22:40, 7 January 2025 (UTC)
== Should WP:NOTDIRECTORY be more specific about phone numbers, etc.? ==
I don't really have a horse in the race, but I wanted to see what the consensus was, so it could be clarified in the relevant guidelines and policies. --]] 02:35, 2 June 2015 (UTC)
Apparently the ] talk page isn't well-watched, so I'd like to draw some attention to ] over there. ] (]) 04:05, 8 January 2025 (UTC)
===Option 1 (preserve historic gender) ===
#'''Support''' - Thanks for starting this! I support this for historic purposes, such as athletic accomplishments, as well as for past relationships that are over (Kris Jenner was married to Bruce Jenner; she was not married to Caitlyn); but not for continuing relationships (ie Brody Jenner's parents are ] and ]) ]<sup>]</sup> 😜 02:55, 2 June 2015 (UTC)
:::To add on to ] (—МандичкаYO)'s point, something definitely needs to be done regarding the marriage aspect; see , where ] understandably stated, "This implies that she was in a lesbian relationship when she was in fact not. She was married to Bruce Jenner not Caitlyn Jenner." ] (]) 04:48, 2 June 2015 (UTC)
::::The major factor to consider with these other articles is that, as we do our best to get it right with Caitlyn Jenner, we must also get it right with ] as this is also a ]. So on Kris Jenner's article, it would not be particularly fair or accurate to say her wife for 20 years was Caitlyn Jenner. That would be very misleading in a biography about her, because yes it does imply she was a lesbian, or she that knew Bruce identified as Caitlyn even though she claims she didn't, or any of of the complicated things that we have no business trying to work around. ]<sup>]</sup> 😜 05:01, 2 June 2015 (UTC)
#'''In general support''' but there are complications. Jenner's interview mentions being dressed in women's underclothes in the past when presenting as a male publicly, so there is the issue of what gender they considered themselves at what times. ] (]) 03:28, 2 June 2015 (UTC)
#'''Support''' - I think it would be silly to start listing "Caitlyn" as a medalist in the "Men's" event. Alternatively, in cases where it's ambiguous which is more appropriate, she can be listed as Caitlyn (formerly Bruce) Jenner? Just a thought. -] (]) 04:08, 2 June 2015 (UTC)
#'''Support''' - It makes no sense to refer to Jenner as a "she" when Jenner was legally a Male. <small><span class="autosigned">— Preceding ] comment added by ] (] • ]) </span></small><!-- Template:Unsigned -->
#:'legally' is not the threshold under our ]. To make it that threshold would be to draw an entirely uneven and artificial line (as well as a tremendously unfair one) ] (]) 07:26, 2 June 2015 (UTC)
#'''Support''' - She's drawn her own line of demarcation for us. Before today, his accomplishments were as Bruce Jenner; from today onward, her life is as Caitlyn Jenner. --] (]) 04:49, 2 June 2015 (UTC)
#:Did she? Awesome. Just when I thought I couldn't like her more, she does that for us!!! ]<sup>]</sup> 😜 05:01, 2 June 2015 (UTC)
#'''Support''' obviously this may not apply to every case, but generally pre-Caitlyn Jenner articles and links should be Bruce Jenner articles, links, or accomplishments. That's what redirects are for. ] (]) 05:19, 2 June 2015 (UTC)
#'''Support''' During the times of his major public appearances, the Olympics (and all of his athletic career) and all of his post athletic movie and TV career, and celebrity existence until 2015, HE was known as Bruce Jenner, performing in male roles and events. To ex-post facto refer to such a notable identity in a new transgendered identity is to go back and rewrite history. That is not wikipedia's role. In fact, we are specifically supposed to follow sources. The reporting of his accomplishments in anything written before 2015 refers to this individual in a male identity. Before we change every record of his appearance before 2015, somebody please show a source contemporary to those activities using the new female name. Its is clearly impossible because the name did not exist publicly until a few days ago, so all of this change to content is unsourced and against key wikipedia policy. That goes the same for any individual undergoing the transgender change. If they have a historical public identity, we should follow that up to the point in time they announced their change. Certainly we can cross link so we can see who they are now, but for example ] was seen millions of American television viewers as Chastity. Bradley Manning is the name reported of the individual originally charged with espionage. These situations are confusing enough to follow, obviously beyond the norm. Repeating: To artificially rewrite history, against the reporting of sources is not wikipedia's role. ] (]) 05:45, 2 June 2015 (UTC)
#:Neither is deadnaming or denying a BLP's right to self-determination and self-identity, so your emphasis of male pronouns is unnecessary. I'd suggest revisiting it. ] (]) 07:26, 2 June 2015 (UTC)
#'''Support''' - Agree that it would be entirely confusing to refer to Caitlin Jenner competing in male sports. Are we to assume that official Olympics records have been updated to change Bruce to Caitlin? Seems very unlikely to me. I wouldn't see a problem with the form "U.S. track and field athlete Bruce Jenner (now Caitlin Jenner) won the gold medal for decathlon, setting a world record of 8,634 points." That form could be mentioned in the guideline, but it should be a tentative mention. It should be clear that the new name ''may be'' shown following the then-current name, but that it's local discretion. And that form is much preferable to "Caitlin Jenner (formerly Bruce Jenner)" in a male context. ―] ] 07:33, 2 June 2015 (UTC)
:That talk page has been checked by at least 100 registered editors during the last month, which makes it one of our better watched pages. ] (]) 18:22, 9 January 2025 (UTC)
===Option 2 (use most recent gender across all Misplaced Pages articles) ===
::{{tq|Apparently}}. :) Getting no response in 36 hours was surprising. The silence could mean "no objection" (since I'm not proposing a change, just a clarification that already used to be there), but since it's a policy page, it would be good to have something more tangible. ] (]) 08:20, 10 January 2025 (UTC)
#
== Does my name technically violate the promotional username policy? ==
=== General discussion ===
*For articles where the gender is important, and where the current publicly expressed gender identity would cause unjustified confusion, I think using their publicly expressed gender identity from that historic time frame is the way to go. For articles where that is not important, I'm really not sure. So in this case, because the gender of an athlete in the Olympics is important, I would say continue to use the historic male gender identity in those articles. But if we aren't talking about an athlete, I'm not sure. Say its an article about a company that talks about the CEO. On the one hand, the CEO's public gender identity at the time they were CEO may be interesting to some people. But on the other, it is at least somewhat common for people to say their current gender identity long predates when they started publicly expressing it, and we should try to be respectful of that. It also wouldn't be nearly as confusing as in the athlete example. I don't know how this would be turned into a guideline either. ]] 02:49, 2 June 2015 (UTC)
My username, as of right now, is Tenebre.Rosso.Sangue995320, which is a reference to and i recently read the username policy, and thought that this violates that policy. can someone help me out? ] ] ] 23:48, 9 January 2025 (UTC)
*For a historical listing on a page of athletic events, the name seems more relevant than the gender. As except for co-ed athletic events (equestrian?), it is assumed that everyone in that particular listing is of the same sex (or identified as such at the time of the competition). I was looking for an example of a prominent cisgender athlete who changed names during their career, and hit upon ]. On the ] he is listed as ] (Cassius Clay) for the year 1964. I think doing this on articles referring to Jenner's athletic career - i.e., ] (Bruce Jenner) - with a footnote about the gender change, might work. ] (]) 03:00, 2 June 2015 (UTC)
:No, it does not. ] (]/]) 00:11, 10 January 2025 (UTC)
*:An interesting precedent. I hadn't thought of that angle. Good idea. --]] 03:05, 2 June 2015 (UTC)
*::Funcrunch has it right. When the old name is reasonably expected and perhaps needed for context, include it in parentheses. Otherwise, use current name. ] ] <small>Please {{]}}</small> 03:18, 2 June 2015 (UTC)
:::*Well, I think that might be because of Misplaced Pages's specific preference/obsession for the "common name" to be used, rather than the accurate name (who cares if the entire world calls it Myanmar, its official name? Common name is ]!!! No discussion!). In the , he is Cassius Clay, and (based on his 1960 results) he is also Cassius Clay (with Muhammad Ali listed under "other names"). ]<sup>]</sup> 😜 03:19, 2 June 2015 (UTC)
::::*Given how ] are treating Myanmar in the past year or so, it is likely ripe for a rename, but that is neither here not there. ] clearly lays out an exception for gender identity, the current discussion is merely how to clarify that guideline for articles outside of the subject article itself. --]] 03:29, 2 June 2015 (UTC)
*I think gender should reflect the choice of the subject (or in all cases should strive to be neutral where it interferes with proper continuity), but the name should reflect that which the subject was known by at the time. This also raises a question regarding gender-specific achievements. Ie, if Jenner's record was for male decathalon, would we use female pronouns in these cases? - ''']''' <sup>]</sup> <sub>]</sub> 03:45, 2 June 2015 (UTC)
* There is a precedent for using names that the athlete used at the time of their athletic achievements. Ron Atest (Metta World Peace), Mike Stanton (Giancarlo Stanton), Domanick Davis (Domanick Williams), Olivier Saint-Jean (Tariq Abdul Wahad), Lew Alcindor (Kareem Abdul Jabbar) and Cassius Clay (Muhammad Ali) did not have their records retroactively changed. <small class="autosigned">— Preceding ] comment added by ] (]) 04:02, 2 June 2015 (UTC)</small><!-- Template:Unsigned IP --> <!--Autosigned by SineBot-->
* In my opinion, use female wherever possible ''except'' in the cases where it would be likely to lead to confusion or implicates something that is not the case. (Her former marriage, at the least. Possibly her athletic accomplishments and her appearance on the Wheaties boxes as well) In the cases where her female name is likely to lead to confusion or false implications, use Bruce Jenner (Caitlyn Jenner). ] (]) 07:42, 2 June 2015 (UTC)
The policy section of the village pump is intended for discussions about already-proposed policies and guidelines, as well as changes to existing ones. Discussions often begin on other pages and are subsequently moved or referenced here to ensure greater visibility and broader participation.
If you wish to propose something new that is not a policy or guideline, use Village pump (proposals). Alternatively, for drafting with a more focused group, consider starting the discussion on the talk page of a relevant WikiProject, the Manual of Style, or another relevant project page.
For questions about how to apply existing policies or guidelines, refer to one of the many Misplaced Pages:Noticeboards.
If you want to inquire about what the policy is on a specific topic, visit the Help desk or the Teahouse.
This is not the place to resolve disputes regarding the implementation of policies. For such cases, consult Misplaced Pages:Dispute resolution.
Should admins or other users evaluating consensus in a discussion discount, ignore, or strike through or collapse comments found to have been generated by AI/LLM/Chatbots? 00:12, 2 December 2024 (UTC)
I've recently come across several users in AFD discussions that are using LLMs to generate their remarks there. As many of you are aware, gptzero and other such tools are very good at detecting this.
I don't feel like any of us signed up for participating in discussions where some of the users are not using their own words but rather letting technology do it for them. Discussions are supposed to be between human editors. If you can't make a coherent argument on your own, you are not competent to be participating in the discussion. I would therefore propose that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner. Just Step Sideways00:12, 2 December 2024 (UTC)
Seems reasonable, as long as the GPTZero (or any tool) score is taken with a grain of salt. GPTZero can be as wrong as AI can be. ~ ToBeFree (talk) 00:32, 2 December 2024 (UTC)
Only if the false positive and false negative rate of the tool you are using to detect LLM content is very close to zero. LLM detectors tend to be very unreliable on, among other things, text written by non-native speakers. Unless the tool is near perfect then it's just dismissing arguments based on who wrote them rather than their content, which is not what we do or should be doing around here. Thryduulf (talk) 00:55, 2 December 2024 (UTC)
The more I read the comments from other editors on this, the more I'm a convinced that implementing either this policy or something like it will bring very significant downsides on multiple fronts that significantly outweigh the small benefits this would (unreliably) bring, benefits that would be achieved by simply reminding closers to disregard comments that are unintelligible, meaningless and/or irrelevant regardless of whether they are LLM-generated or not. For the sake of the project I must withdraw my previous very qualified support and instead very strongly oppose. Thryduulf (talk) 02:45, 3 December 2024 (UTC)
I think it should be an expressly legitimate factor in considering whether to discount or ignore comments either if it's clear enough by the text or if the user clearly has a history of using LLMs. We wouldn't treat a comment an editor didn't actually write as an honest articulation of their views in lieu of site policy in any other situation. Remsense ‥ 论00:59, 2 December 2024 (UTC)
I would have already expected admins to exercise discretion in this regard, as text written by an LLM is not text written by a person. We cannot guarantee it is what the person actually means, especially as it is a tool often used by those with less English proficiency, which means perhaps they cannot evaluate the text themselves. However, I do not think we can make policy about a specific LLM or tool. The LLM space is moving fast, en.wiki policies do not. Removal seems tricky, I would prefer admins exercise discretion instead, as they do with potentially canvassed or socked !votes. CMD (talk) 01:06, 2 December 2024 (UTC)
As the discussion has moved forward below, I feel I can shift to a more explicit support in terms of providing guidance to closers and those otherwise evaluating consensus. CMD (talk) 17:33, 2 January 2025 (UTC)
Support discounting or collapsing AI-generated comments, under slightly looser conditions than those for human comments. Not every apparently-AI-generated comment is useless hallucinated nonsense – beyond false positives, it's also possible for someone to use an AI to help them word a constructive comment, and make sure that it matches their intentions before they publish it. But in my experience, the majority of AI-generated comments are somewhere between "pointless" and "disruptive". Admins should already discount clearly insubstantial !votes, and collapse clearly unconstructive lengthy comments; I think we should recognize that blatant chatbot responses are more likely to fall into those categories. jlwoodwa (talk) 02:11, 2 December 2024 (UTC)
Strongly Support - I think some level of human judgement on the merits of the argument are necessary, especially as GPTZero may still have a high FPR. Still, if the discussion is BLUDGEONy, or if it quacks like an AI-duck, looks like an AI-duck, etc, we should consider striking out such content.- sidenote, I'd also be in favor of sanctions against users who overuse AI to write out their arguments/articles/etc. and waste folks time on here.. Bluethricecreamman (talk) 02:20, 2 December 2024 (UTC)
On a wording note, I think any guidance should avoid referring to any specific technology. I suggest saying "... to have been generated by a program". isaacl (talk) 02:54, 2 December 2024 (UTC)
A translation program, whether it is between languages or from speech, is not generating a comment, but converting it from one format to another. A full policy statement can be more explicit in defining "generation". The point is that the underlying tech doesn't matter; it's that the comment didn't feature original thought from a human. isaacl (talk) 03:57, 2 December 2024 (UTC)
Support. We already use discretion in collapsing etc. comments by SPAs and suspected socks, it makes sense to use the same discretion for comments suspected of being generated by a non-human. JoelleJay (talk) 03:07, 2 December 2024 (UTC)
Support - Someone posting "here's what ChatGPT has to say on the subject" can waste a lot of other editors' time if they feel obligated to explain why ChatGPT is wrong again. I'm not sure how to detect AI-written text but we should take a stance that it isn't sanctioned. Clayoquot (talk | contribs) 04:37, 2 December 2024 (UTC)
Strong Support - I've never supported using generative AI in civil discourse. Using AI to participate in these discussions is pure laziness, as it is substituting genuine engagement and critical thought with a robot prone to outputting complete garbage. In my opinion, if you are too lazy to engage in the discussion yourself, why should we engage with you? Lazman321 (talk) 05:26, 2 December 2024 (UTC)
Because it's based on a potentially false premise that it will be possible to reliably distinguish between text generated by human biological neural networks and text generated by non-biological neural networks by observing the text. It is already quite difficult in many cases, and the difficulty is increasing very rapidly. I have your basic primate brain. The AI companies building foundation models have billions of dollars, tens of thousands, soon to be hundreds of thousands of GPUs, a financial incentive to crack this problem and scaling laws on their side. So, I have very low credence in the notion that I will be able to tell whether content is generated by a person or a person+LLM or an AI agent very soon. On the plus side, it will probably still be easy to spot people making non-policy based arguments regardless of how they do it. Sean.hoyland (talk) 13:52, 2 December 2024 (UTC)
...and now that the systems are autonomously injecting their output back into model via chain-of-thought prompting, or a kind of inner monologue if you like, to respond to questions, they are becoming a little bit more like us. Sean.hoyland (talk) 14:14, 2 December 2024 (UTC)
A transformer (deep learning architecture) is intrinsically nothing like a human. It's a bunch of algebra that can compute what a decently sensible person could write in a given situation based on its training data, but it is utterly incapable of anything that could be considered thought or reasoning. This is why LLMs tend to fail spectacularly when asked to do math or write non-trivial code. Flounder fillet (talk) 17:20, 2 December 2024 (UTC)
We shall see. You might want to update yourself on their ability to do math and write non-trivial code. Things are changing very quickly. Either way, it is not currently possible to say much about what LLMs are actually doing because mechanistic interpretability is in its infancy. Sean.hoyland (talk) 03:44, 3 December 2024 (UTC)
Support and I would add "or similar technologies" to "AI/LLM/Chatbots". As for Sean.hoyland's comment, we will cross that bridge when we get to it. Cullen328 (talk) 05:51, 2 December 2024 (UTC)
Support - All editors should convey their thoughts in their own words. AI generated responses and comments are disruptive because they are pointless and not meaningful. - Ratnahastin (talk) 06:04, 2 December 2024 (UTC)
Support, I already more or less do this. An LLM generated comment may or may not actually reflect the actual thoughts of the editor who posted it, so it's essentially worthless toward a determination of consensus. Since I wrote this comment myself, you know that it reflects my thoughts, not those of a bot that I may or may not have reviewed prior to copying and pasting. Seraphimblade06:59, 2 December 2024 (UTC)
Strong oppose. Let me say first that I do not like ChatGPT. I think it has been a net negative for the world, and it is by nature a net negative for the physical environment. It is absolutely a net negative for the encyclopedia if LLM-generated text is used in articles in any capacity. However, hallucinations are less of an issue on talk pages because they're discussions. If ChatGPT spits out a citation of a false policy, then obviously that comment is useless. If ChatGPT spits out some boilerplate "Thanks for reviewing the article, I will review your suggestions and take them into account" talk page reply, who gives a fuck where it came from? (besides the guys in Texas getting their eardrums blown out because they live by the data center)The main reason I oppose, though, is because banning LLM-generated comments is difficult to enforce bordering on unenforceable. Most studies show that humans are bad at distinguishing AI-generated text from text generated without AI. Tools like GPTZero claims a 99% accuracy rate, but that seems dubious based on reporting on the matter. The news outlet Futurism (which generally has an anti-AI slant) has failed many times to replicate that statistic, and anecdotal accounts by teachers, etc. are rampant. So we can assume that we don't know how capable AI detectors are, that there will be some false positives, and that striking those false positives will result in WP:BITING people, probably newbies, younger people more accustomed to LLMs, and non-Western speakers of English (see below).There are also technological issues as play. It'd be easy if there was a clean line between "totally AI-generated text" and "totally human-generated text," but that line is smudged and well on its way to erased. Every tech company is shoving AI text wrangling into their products. This includes autocomplete, translation, editing apps, etc. Should we strike any comment a person used Grammarly or Google Translate for? Because those absolutely use AI now.And there are also, as mentioned above, cultural issues. The people using Grammarly, machine translation, or other such services are likely to not have English as their first language. And a lot of the supposed "tells" of AI-generated content originate in the formal English of other countries -- for instance, the whole thing where "delve" was supposedly a tell for AI-written content until people pointed out the fact that lots of Nigerian workers trained the LLM and "delve" is common Nigerian formal English.I didn't use ChatGPT to generate any of this comment. But I am also pretty confident that if I did, I could have slipped it in and nobody would have noticed until this sentence. Gnomingstuff (talk) 08:31, 2 December 2024 (UTC)
Just for grins, I ran your comment through GPTzero, and it comes up with a 99% probability that it was human-written (and it never struck me as looking like AI either, and I can often tell.) So, maybe it's more possible to distinguish than you think? Seraphimblade20:11, 2 December 2024 (UTC)
Support - Ai-generated comments are WP:DISRUPTIVE - An editor who has an argument should not use ChatGPT to present it in an unnecessarily verbose manner, and an editor who doesn't have one should not participate in discussion. Flounder fillet (talk) 13:14, 2 December 2024 (UTC)
They exist, and I found myself collapsing some long, obviously chatbot-generated posts in an AFD, and after I did so wondering if policy actually supported doing that. I couldn't find anything so here we are. Just Step Sideways20:04, 2 December 2024 (UTC)
Yes, of course, and I know that's the right answer because ChatGPT agrees with me.
What ChatGPT thinks
I started by asking:
Currently at the English Misplaced Pages, there's a discussion of the following proposal: "Should or other users evaluating consensus in a discussion discount, ignore, or strike through or collapse comments found to have been generated by AI/LLM/Chatbots?" I wonder if you have an opinion on that question.
My friend the bot initially proposed a requirement that any AI-generated content be labeled as such by the person posting it. After some further discussion between us, I finally said:
You say that labeling AI-generated content, instead of outright discounting it, might be an appropriate middle ground. But if someone is unable to formulate their own thoughts and put them in writing, of what use is it to the discussion for this person to simply ask you to make something up, and then post your output to the Misplaced Pages discussion with the proviso that "ChatGPT, who/which doesn't actually know anything about anything, said this ..."? How is it different from saying, "My grandmother, who knows nothing about what we're talking about, said ..."?
And it said:
That’s an incisive question, and it highlights the crux of the issue: the value of contributions to a discussion. Here’s why AI-generated comments might still differ (slightly) from your hypothetical grandmother’s input, but why their usefulness is often limited:
Synthesis vs. Subject Expertise: While I (or any AI) lack personal understanding or expertise, I can aggregate and articulate relevant ideas from a vast dataset. This means I can sometimes present arguments, summarize perspectives, or surface considerations that a non-expert human might overlook. Your grandmother, unless she's an AI-trained polymath, wouldn’t be able to provide this breadth. However, this advantage evaporates if participants lack the ability to evaluate and critically engage with my output.
The Problem of Proxy Voices: The act of outsourcing one’s contribution to AI undermines the deliberative process central to Misplaced Pages’s discussions. Participants are expected to bring their own informed perspectives, shaped by personal understanding of Misplaced Pages’s policies and content. A disclaimer like “ChatGPT said this” doesn’t change the fact that the human posting it has abdicated their role in the discussion.
Accountability and Intent: In a collaborative setting like Misplaced Pages, contributions are ideally linked to a person who can clarify their intent, respond to questions, and engage dynamically. An AI cannot do this. Saying "ChatGPT said this" distances the poster from the content, making it unclear whether they endorse or even understand the comment.
Potential for Misdirection: Allowing AI-generated contributions risks introducing noise into the discussion. AI can produce plausible-sounding arguments that may be tangential, misaligned, or even factually incorrect. Without the judgment of a well-informed poster, such contributions can derail or dilute meaningful discourse.
Conclusion: If someone cannot formulate their own argument or understanding, then their reliance on an AI—or anyone else—to contribute doesn’t meaningfully advance the discussion. Labeling AI-generated content is better than passing it off as human, but the real issue lies in whether such contributions enrich or degrade the collaborative process. In most cases, they would seem to belong more to the realm of rhetorical curiosities than substantive engagement.
In keeping with the proposed guideline, I have of course collapsed the above AI-generated content. (Later: It's actually worth reading in the context of this discussioin, so I've unhidden it by default.) But I must confess it's a pretty good analysis, and worth reading. EEng07:47, 2 December 2024 (UTC)
This is absolute gold dust and the best contribution to this discussion so far. There is an enormous irony here, one that might not be immediately obvious. The proposal is that we should ignore or even strike these type of contributions, but personally it seems like the collapsed format has worked a charm here. I really don't think that AI has much to contribute to WP discussions generally, but with the right prompt, there is certainly something worth adding to the conversation in reality. CNC (talk) 20:23, 8 December 2024 (UTC)
That's because, just by interacting with me, ChatGPT got smarter. Seriously ... you want it to say 99% every time? (And for the record, the idea of determining the "chance" that something is AI-generated is statistical nonsense.) EEng03:07, 3 December 2024 (UTC)
What I really want is a 100% chance that it won't decide that what I've written is AI-generated. Past testing has demonstrated that at least some of the detectors are unreliable on this point. WhatamIdoing (talk) 03:28, 4 December 2024 (UTC)
100% is, of course, an impossible goal. Certainly SPI doesn't achieve that, so why demand it here? EEng22:31, 4 December 2024 (UTC)
Strong Oppose I support the concept of removal of AI-generated content in theory. However, we do not have the means to detect such AI-generated content. The proposed platform that we may use (GPTZero) is not reliable for this purpose. In fact, our own page on GPTZero has a section citing several sources stating the problem with this platform's accuracy. It is not helpful to have a policy that is impossible to enforce. ThatIPEditor08:46, 2 December 2024 (UTC)
Strong Support To be honest, I am surprised that this isn't covered by an existing policy. I oppose the use of platforms like GPTZero, due to it's unreliability, but if it is obviously an ai-powered-duck (Like if it is saying shit like "as an AI language model...", take it down and sanction the editor who put it up there. ThatIPEditor08:54, 2 December 2024 (UTC)
Support at least for WP:DUCK-level AI-generated comments. If someone uses a LLM to translate or improve their own writing, there should be more leeway, but something that is clearly a pure ChatGPT output should be discounted. Chaotic Enby (talk · contribs) 09:17, 2 December 2024 (UTC)
I agree for cases in which it is uncontroversial that a comment is purely AI-generated. However, I don't think there are many cases where this is obvious. The claim that gptzero and other such tools are very good at detecting this is false. Phlsph7 (talk) 09:43, 2 December 2024 (UTC)
Moral support; neutral as written. Chatbot participation in consensus discussions is such an utterly pointless and disdainful abuse of process and community eyeballs that I don't feel like the verbiage presented goes far enough. Any editor may hat LLM-generated comments in consensus discussions is nearer my position. No waiting for the closer, no mere discounting, no reliance on the closer's personal skill at recognising LLM output, immediate feedback to the editor copypasting chatbot output that their behaviour is unwelcome and unacceptable. Some observations:I've seen editors accused of using LLMs to generate their comments probably about a dozen times, and in all but two cases – both at dramaboards – the chatbot prose was unmistakably, blindingly obvious. Editors already treat non-obvious cases as if written by a human, in alignment with the raft of only if we're sure caveats in every discussion about LLM use on the project.If people are using LLMs to punch up prose, correct grammar and spelling, or other superficial tasks, this is generally undetectable, unproblematic, and not the point here.Humans are superior to external services at detecting LLM output, and no evidence from those services should be required for anything.As a disclosure, evidence mounts that LLM usage in discussions elicits maximally unkind responses from me. It just feels so contemptuous, to assume that any of us care what a chatbot has to say about anything we're discussing, and that we're all too stupid to see through the misattribution because someone tacked on a sig and sometimes an introductory paragraph. And I say this as a stupid person. Folly Mox (talk) 11:20, 2 December 2024 (UTC)
Looks like a rewrite is indicated to distinguish between machine translation and LLM-generated comments, based on what I'm seeing in this thread. Once everyone gets this out of our system and an appropriately wordsmithed variant is reintroduced for discussion, I preemptively subpropose the projectspace shortcut WP:HATGPT. Folly Mox (talk) 15:26, 8 December 2024 (UTC)
I would be careful here, as there are tools that rely on LLM AI that help to improve the clarity of one's writing, and editors may opt to use those to parse their poor writing (perhaps due to ESL aspects) to something clear. I would agree content 100% generated by AI probably should be discounted particularly if from an IP or new editors (hints if socking or meat puppetry) but not all cases where AI has come into play should be discounted — Masem (t) 14:19, 2 December 2024 (UTC)
Support, cheating should have no place or take its place in writing coherent comments on Misplaced Pages. Editors who opt to use it should practice writing until they rival Shakespeare, or at least his cousin Ned from across the river, and then come back to edit. Randy Kryn (talk) 14:29, 2 December 2024 (UTC)
Support atleast for comments that are copied straight from the LLM . However, we should be more lenient if the content is rephrased by non-native English speakers due to grammar issues The AP (talk) 15:10, 2 December 2024 (UTC)
section break 1
Support for LLM-generated content (until AI is actually intelligent enough to create an account and contribute on a human level, which may eventually happen). However, beware of the fact that some LLM-assisted content should probably be allowed. An extreme example of this: if a non-native English speaker were to write a perfectly coherent reason in a foreign language, and have an LLM translate it to English, it should be perfectly acceptable. Animal lover|666|16:47, 2 December 2024 (UTC)
Data, being a fictional creation with rights owned by a corporation, will not have an account; he is inherently an IP editor. -- Nat Gertler (talk) 03:22, 20 December 2024 (UTC)
Oppose - I think the supporters must have a specific type of AI-generated content in mind, but this isn't a prohibition on one type; it's a prohibition on the use of generative AI in discussions (or rather, ensuring that anyone who relies on such a tool will have their opinion discounted). We allow people who aren't native English speakers to contribute here. We also allow people who are native English speakers but have difficulty with language (but not with thinking). LLMs are good at assisting both of these groups of people. Furthermore, as others pointed out, detection is not foolproof and will only get worse as time goes on, models proliferate, models adapt, and users of the tools adapt. This proposal is a blunt instrument. If someone is filling discussions with pointless chatbot fluff, or we get a brand new user who's clearly using a chatbot to feign understanding of wikipolicy, of course that's not ok. But that is a case by case behavioral issue. I think the better move would be to clarify that "some forms of LLM use can be considered disruptive and may be met with restrictions or blocks" without making it a black-and-white issue. — Rhododendrites \\ 17:32, 2 December 2024 (UTC)
I agree the focus should not be on whether or not a particular kind of tech was used by an editor, but whether or not the comment was generated in a way (whether it's using a program or ghost writer) such that it fails to express actual thoughts by the editor. (Output from a speech-to-text program using an underlying large language model, for instance, isn't a problem.) Given that this is often hard to determine from a single comment (everyone is prone to post an occasional comment that others will consider to be off-topic and irrelevant), I think that patterns of behaviour should be examined. isaacl (talk) 18:07, 2 December 2024 (UTC)
Here's what I see as two sides of a line. The first is, I think, something we can agree would be inappropriate. The second, to me at least, pushes up against the line but is not ultimately inappropriate. But they would both be prohibited if this passes. (a) "I don't want an article on X to be deleted on Misplaced Pages. Tell me what to say that will convince people not to delete it"; (b) "I know Misplaced Pages deletes articles based on how much coverage they've received in newspapers, magazines, etc. and I see several such articles, but I don't know how to articulate this using wikipedia jargon. Give me an argument based on links to wikipedia policy that use the following sources as proof ". Further into the "acceptable" range would be things like translations, grammar checks, writing a paragraph and having an LLM improve the writing without changing the ideas, using an LLM to organize ideas, etc. I think what we want to avoid are situations where the arguments and ideas themselves are produced by AI, but I don't see such a line drawn here and I don't think we could draw a line without more flexible language. — Rhododendrites \\ 18:47, 2 December 2024 (UTC)
Here we return to my distinction between AI-generated and AI-assisted. A decent speech-to-text program doesn't actually generate content. Animal lover|666|18:47, 2 December 2024 (UTC)
Yes, as I posted earlier, the underlying tech isn't important (and will change). Comments should reflect what the author is thinking. Tools (or people providing advice) that help authors express their personal thoughts have been in use for a long time. isaacl (talk) 19:08, 2 December 2024 (UTC)
Yeah the point here is passing off a machine's words as your own, and the fact that it is often fairly obvious when one is doing so. If a person is not competent to express their own thoughts in plain English, they shouldn't be in the discussion. This certainly is not aimed at assistive technology for those who actually need it but rather at persons who are simply letting Chatbots speak for them. Just Step Sideways20:10, 2 December 2024 (UTC)
This doesn't address what I wrote (though maybe it's not meant to). If a person is not competent to express their own thoughts in plain English, they shouldn't be in the discussion. This certainly is not aimed at assistive technology for those who actually need it but rather at persons who are simply letting Chatbots speak for them is just contradictory. Assistive technologies are those that can help people who aren't "competent" to express themselves to your satisfaction in plain English, sometimes helping with the formulation of a sentence based on the person's own ideas. There's a difference between having a tool that helps me to articulate ideas that are my own and a tool that comes up with the ideas. That's the distinction we should be making. — Rhododendrites \\ 21:23, 2 December 2024 (UTC)
I agree with Rhododendrites that we shouldn't be forbidding users from seeking help to express their own thoughts. Getting help from someone more fluent in English, for example, is a good practice. Nowadays, some people use generative technology to help them prepare an outline of their thoughts, so they can use it as a starting point. I think the community should be accepting of those who are finding ways to write their own viewpoints more effectively and concisely, even if that means getting help from someone or a program. I agree that using generative technology to come up with the viewpoints isn't beneficial for discussion. isaacl (talk) 22:58, 2 December 2024 (UTC)
Non-native English speakers and non-speakers to whom a discussion is important enough can already use machine translation from their original language and usually say something like "Sorry, I'm using machine translation". Skullers (talk) 08:34, 4 December 2024 (UTC)
Oppose Contributions to discussions are supposed to be evaluated on their merits per WP:NOTAVOTE. If an AI-assisted contribution makes sense then it should be accepted as helpful. And the technical spectrum of assistance seems large and growing. For example, as I type this into the edit window, some part of the interface is spell-checking and highlighting words that it doesn't recognise. I'm not sure if that's coming from the browser or the edit software or what but it's quite helpful and I'm not sure how to turn it off. Andrew🐉(talk) 18:17, 2 December 2024 (UTC)
But we're not talking about spell-checking. We're talking about comments clearly generated by LLMs, which are inherently unhelpful. Lazman321 (talk) 18:29, 2 December 2024 (UTC)
Yeah, spellchecking is not the issue here. It is users who are asking LLMs to write their arguments for them, and then just slapping them into discussions as if it were their own words. Just Step Sideways20:12, 2 December 2024 (UTC)
Andrew's first two sentences also seem to imply that he views AI-generated arguments that makes sense as valid, and that we should consider what AI thinks about a topic. I'm not sure what to think about this, especially since AI can miss out on a lot of the context. Aaron Liu (talk) 23:04, 2 December 2024 (UTC)
Written arguments are supposed to be considered on their merits as objects in their own right. Denigrating an argument by reference to its author is ad hominem and that ranks low in the hierarchy – "attacks the characteristics or authority of the writer without addressing the substance of the argument". Andrew🐉(talk) 23:36, 2 December 2024 (UTC)
An AI chatbot isn't an "author", and it's impossible to make an ad hominem attack on one, because a chotbot is not a homo. EEng17:45, 6 December 2024 (UTC)
On the other hand, "exhausting the community's patience"/CompetenceIsRequired is a very valid rationale from stopping someone from partricipating. Aaron Liu (talk) 23:50, 2 December 2024 (UTC)
The spell-checking was an immediate example but there's a spectrum of AI tools and assistance. The proposed plan is to use an AI tool to detect and ban AI contributions. That's ludicrous hypocrisy but suggests an even better idea – that we use AIs to close discussions so that we don't get the bias and super-voting. I see this on Amazon regularly now as it uses an AI to summarise the consensus of product reviews. For example,
Customers say Customers appreciate the gloves for their value, ease of use, and gardening purposes. They find the gloves comfortable and suitable for tasks like pruning or mowing. However, opinions differ on how well they fit. AI-generated from the text of customer reviews
I asked Google's Gemini to "summarise the consensus of the following RFC discussion", giving it the 87 comments to date.
AI summary of the RfC to date
This Misplaced Pages Request for Comment (RfC) debates whether comments in discussions that are found to be generated by AI/LLM/Chatbots should be discounted, ignored, or removed.
Arguments for discounting/removing AI-generated comments:
AI comments don't represent genuine human engagement or thought. They can be disruptive, waste time, and even fabricate information.
AI can be used to manipulate discussions. Editors might use AI to generate arguments they don't actually believe in, or to flood discussions with low-quality comments.
Relying on AI undermines the integrity of Misplaced Pages's consensus-based process. Discussions should be based on the genuine opinions of human editors.
Arguments against discounting/removing AI-generated comments:
Difficulty of detection. AI detection tools are not always reliable, and it can be hard to distinguish between AI-generated text and human-written text, especially as AI technology improves.
Potential for misuse. False positives could lead to legitimate comments being dismissed, potentially silencing non-native English speakers or those who use AI for legitimate assistive purposes (e.g., translation, grammar checks).
Focus on content, not origin. Comments should be evaluated based on their merits, not on how they were generated. If an AI-generated comment is relevant and well-reasoned, it shouldn't be dismissed simply because of its origin.
LLMs can be helpful tools. LLMs can help editors express their thoughts more clearly, especially for non-native speakers or those with language difficulties.
Current Status (as of Dec 3rd, 2024):
No clear consensus has emerged. There is significant support for discounting or removing AI-generated comments, but also strong opposition.
Concerns about enforceability and potential harm. Many editors are worried about the practical challenges of implementing and enforcing such a rule, as well as the potential for it to be used unfairly against certain editors.
Ongoing discussion. The discussion is still active, and it remains to be seen whether a consensus will form.
It's important to note that this is an evolving situation, and the outcome of the RfC could have significant implications for how Misplaced Pages handles AI-generated content in the future.
That seems quite a fair and good summary of what's been said so far. I'm impressed and so my !vote stands.
Yeah, the ability to weigh each side and the quality of their arguments in an RFC can really only be done by the judgement and discretion of an experienced human editor. Lazman321 (talk) 20:08, 4 December 2024 (UTC)
The quality of the arguments and their relevance to polices and guidelines can indeed only be done by a human, but the AI does a good job of summarising which arguments have been made and a broad brush indication of frequency. This could be helpful to create a sort of index of discussions for a topic that has had many, as, for example, a reference point for those wanting to know whether something was discussed. Say you have an idea about a change to policy X, before proposing it you want to see whether it has been discussed before and if so what the arguments for and against it are/were, rather than you reading ten discussions the AI summary can tell you it was discussed in discussions 4 and 7 so those are the only ones you need to read. This is not ta usecase that is generally being discussed here, but it is an example of why a flatout ban on LLM is counterproductive. Thryduulf (talk) 21:40, 4 December 2024 (UTC)
Support Just the other day, I spent ~2 hours checking for the context of several quotes used in an RFC, only to find that they were fake. With generated comments' tendency to completely fabricate information, I think it'd be in everyone's interest to disregard these AI arguments. Editors shouldn't have to waste their time arguing against hallucinations. (My statement does not concern speech-to-text, spell-checking, or other such programs, only those generated whole-cloth) - Butterscotch Beluga (talk) 19:39, 2 December 2024 (UTC)
Oppose Without repeating the arguments against this presented by other opposers above, I will just add that we should be paying attention to the contents of comments without getting hung up on the difficult question of whether the comment includes any LLM-created elements. - Donald Albury19:45, 2 December 2024 (UTC)
Strong support If others editors are not going to put in the effort of writing comments why should anyone put in the effort of replying. Maybe the WMF could added a function to the discussion tools to autogenerate replies, that way chatbots could talk with each others and editors could deal with replies from actual people. -- LCU ActivelyDisinterested«@» °∆t°19:57, 2 December 2024 (UTC)
Strong oppose. Comments that are bullshit will get discounted anyways. Valuable comments should be counted. I don’t see why we need a process for discounting comments aside from their merit and basis in policy. ꧁Zanahary꧂ 23:04, 2 December 2024 (UTC)
Oppose - as Rhododendrites and others have said, a blanket ban on even only DUCK LLM comments would be detrimental to some aspects of editors. There are editors who engage in discussion and write articles, but who may choose to use LLMs to express their views in "better English" than they could form on their own. Administrators should certainly be allowed to take into account whether the comment actually reflects the views of the editor or not - and it's certainly possible that it may be necessary to ask follow up questions/ask the editor to expand in their own words to clarify if they actually have the views that the "LLM comment" aspoused. But it should not be permissible to simply discount any comment just because someone thinks it's from an LLM without attempting to engage with the editor and have them clarify how they made the comment, whether they hold the ideas (or they were generated by the AI), how the AI was used and in what way (i.e. just for grammar correction, etc). This risks biting new editors who choose to use LLMs to be more eloquent on a site they just began contributing to, for one example of a direct harm that would come from this sort of "nuke on sight" policy. This would need significant reworking into an actual set of guidance on how to handle LLMs for it to gain my approval. -bɜ:ʳkənhɪmez | me | talk to me!23:19, 2 December 2024 (UTC)
Comment: It would appear Jimbo responded indirectly in a interview: as long as there’s a human in the loop, a human supervising, there are really potentially very good use cases. 2601AC47 (talk·contribs·my rights) Isn't a IP anon 12:39, 4 December 2024 (UTC)
Very strong support. Enough is enough. If Misplaced Pages is to survive as a project, we need zero tolerance for even the suspicion of AI generation and, with it, zero tolerance for generative AI apologists who would happily open the door to converting the site to yet more AI slop. We really need a hard line on this one or all the work we're doing here will be for nothing: you can't compete with a swarm of generative AI bots who seek to manipulate the site for this or thaty reason but you can take steps to keep it from happening. :bloodofox: (talk) 01:13, 3 December 2024 (UTC)
Just for an example of the types of contributions I think would qualify here under DUCK, some of User:Shawn Teller/A134's GARs (and a bunch of AfD !votes that have more classic indications of non-human origin) were flagged as likely LLM-generated troll nonsense:
But thanks to these wonderful images, I now understand that Ontario Highway 11 is a paved road that vehicles use to travel.
This article is extensive in its coverage of such a rich topic as Ontario Highway 11. It addresses the main points of Ontario Highway 11 in a way that isn’t just understandable to a reader, but also relatable.
Neutral point of view without bias is maintained perfectly in this article, despite Ontario Highway 11 being such a contentious and controversial topic.
Yes, this could and should have been reverted much earlier based on being patently superficial and/or trolling, without needing the added issue of appearing LLM-generated. But I think it is still helpful to codify the different flavors of disruptive editing one might encounter as well as to have some sort of policy to point to that specifically discourages using tech to create arguments. As a separate point, LTAs laundering their comments through GPT to obscure their identity is certainly already happening, so making it harder for such comments to "count" in discussions would surely be a net positive. JoelleJay (talk) 01:18, 3 December 2024 (UTC)
For the purposes of this proposal, I don't think we need, or should ever rely solely on, GPTzero in evaluating content for non-human origin. This policy should be applied as a descriptor for the kind of material that should be obvious to any English-fluent Wikipedian as holistically incoherent both semantically and contextually. Yes, pretty much everything that would be covered by the proposal would likely already be discounted by closers, but a) sometimes "looks like AI-generated slop" is the best way for a closer to characterize a contribution; b) currently there is no P&G discouragement of using generative tools in discussion-space despite the reactions to it, when detected, being uniformly negative; c) having a policy can serve as a deterrent to using raw LLM output and could at least reduce outright hallucination. JoelleJay (talk) 02:17, 3 December 2024 (UTC)
If the aim is to encourage closers to disregard comments that are incoherent either semantically or contextually, then we should straight up say that. Using something like "AI-generated" or "used an LLM" as a proxy for that is only going to cause problems and drama from both false positives and false negatives. Judge the comment on its content not on its author. Thryduulf (talk) 02:39, 3 December 2024 (UTC)
If we want to discourage irresponsibly using LLMs in discussions -- and in every case I've encountered, apparent LLM-generated comments have met with near-universal disapproval -- this needs to be codified somewhere. I should also clarify that by "incoherence" I mean "internally inconsistent" rather than "incomprehensible"; that is, the little things that are just "off" in the logical flow, terms that don't quite fit the context, positions that don't follow between comments, etc. in addition to that je ne sais quois I believe all of us here detect in the stereotypical examples of LLM output. Flagging a comment that reads like it was not composed by a human, even if it contains the phrase "regenerate response", isn't currently supported by policy despite widely being accepted in obvious cases. JoelleJay (talk) 03:52, 3 December 2024 (UTC)
I feel that I'm sufficiently unfamiliar with LLM output to be confident in my ability to detect it, and I feel like we already have the tools we need to reject internally incoherent comments, particularly in the Misplaced Pages:Consensus policy, which says In determining consensus, consider the quality of the arguments, the history of how they came about, the objections of those who disagree, and existing policies and guidelines. The quality of an argument is more important than whether it represents a minority or a majority view. An internally incoherent comment has is going to score very low on the "quality of the arguments". WhatamIdoing (talk) 03:33, 4 December 2024 (UTC)
Very extra strong oppose - The tools to detect are at best not great and I don't see the need. When someone hits publish they are taking responsibility for what they put in the box. That does not change when they are using a LLM. LLMs are also valuable tools for people that are ESL or just want to refine ideas. So without bullet proof detection this is doa. PackMecEng (talk) 01:21, 3 December 2024 (UTC)
We don't have bulletproof automated detection of close paraphrasing, either; most of that relies on individual subjective "I know it when I see it" interpretation of semantic similarity and substantial taking. JoelleJay (talk) 04:06, 3 December 2024 (UTC)
One is a legal issue the other is not. Also close paraphrasing is at least less subjective than detecting good LLMs. Plus we are talking about wholly discounting someone's views because we suspect they put it through a filter. That does not sit right with me. PackMecEng (talk) 13:38, 3 December 2024 (UTC)
For sure and I can see that concern, but I think the damage that does is less than the benefit it provides. Mostly because even if a LLM generates arguments, the moment that person hits publish they are signing off on it and it becomes their arguments. Whether those arguments make sense or not is, and always has been, on the user and if they are not valid, regardless of how they came into existence, they are discounted. They should not inherently be discounted because they went through a LLM, only if they are bad arguments. PackMecEng (talk) 14:57, 3 December 2024 (UTC)
section break 3
While it’s true that the person publishing arguments takes responsibility, the use of a large language model (LLM) can blur the line of authorship. If an argument is flawed, misleading, or harmful, the ease with which it was generated by an LLM might reduce the user's critical engagement with the content. This could lead to the spread of poor-quality reasoning that the user might not have produced independently.
Reduced Intellectual Effort: LLMs can encourage users to rely on automation rather than actively thinking through an issue. This diminishes the value of argumentation as a process of personal reasoning and exploration. Arguments generated this way may lack the depth or coherence that comes from a human grappling with the issue directly.
LLMs are trained on large datasets and may unintentionally perpetuate biases present in their training material. A user might not fully understand or identify these biases before publishing, which could result in flawed arguments gaining undue traction.
Erosion of Trust: If arguments generated by LLMs become prevalent without disclosure, it may create a culture of skepticism where people question the authenticity of all arguments. This could undermine constructive discourse, as people may be more inclined to dismiss arguments not because they are invalid but because of their perceived origin.
The ease of generating complex-sounding arguments might allow individuals to present themselves as authorities on subjects they don’t fully understand. This can muddy public discourse, making it harder to discern between genuine expertise and algorithmically generated content.
Transparency is crucial in discourse. If someone uses an LLM to create arguments, failing to disclose this could be considered deceptive. Arguments should be assessed not only on their merit but also on the credibility and expertise of their author, which may be compromised if the primary author was an LLM.
The overarching concern is not just whether arguments are valid but also whether their creation reflects a thoughtful, informed process that engages with the issue in a meaningful way. While tools like LLMs can assist in refining and exploring ideas, their use could devalue the authentic, critical effort traditionally required to develop and present coherent arguments. ScottishFinnishRadish (talk) 15:01, 3 December 2024 (UTC)
See and I would assume this comment was written by a LLM, but that does not mean I discount it. I check and consider it as though it was completely written by a person. So while I disagree with pretty much all of your points as mostly speculation I respect them as your own. But it really just sounds like fear of the unknown and unenforceable. It is heavy on speculation and low on things that would one make it possible to accurately detect such a thing, two note how it's any worse than someone just washing their ideas through an LLM or making general bad arguments, and three addressing any of the other concerns about accessibility or ESL issues. It looks more like a moral panic than an actual problem. You end with the overarching concern is not just weather arguments are valid but also if their creation reflects a thoughtful, informed process that engages with the issues in a meaningful way and honestly that not a thing that can be quantified or even just a LLM issue. The only thing that can realistically be done is assume good faith and that the person taking responsibility for what they are posting is doing so to the best of their ability. Anything past that is speculation and just not of much value. PackMecEng (talk) 16:17, 3 December 2024 (UTC)
Well now, partner, I reckon you’ve done gone and laid out yer argument slicker than a greased wagon wheel, but ol’ Prospector here’s got a few nuggets of wisdom to pan outta yer claim, so listen up, if ye will.
Now, ain't that a fine gold tooth in a mule’s mouth? Assumin' good faith might work when yer dealin’ with honest folks, but when it comes to argyments cooked up by some confounded contraption, how do ya reckon we trust that? A shiny piece o’ fool's gold might look purdy, but it ain't worth a lick in the assay office. Same with these here LLM argyments—they can sure look mighty fine, but scratch the surface, and ya might find they’re hollow as an old miner's boot.
Moral panic, ye say? Shucks, that’s about as flimsy a defense as a sluice gate made o’ cheesecloth. Ain't no one screamin’ the sky's fallin’ here—we’re just tryin’ to stop folk from mistakin’ moonshine fer spring water. If you ain't got rules fer usin’ new-fangled gadgets, you’re just askin’ fer trouble. Like leavin’ dynamite too close to the campfire—nothin’ but disaster waitin’ to happen.
Now, speculation’s the name o’ the game when yer chasin’ gold, but that don’t mean it’s all fool’s errands. I ain’t got no crystal ball, but I’ve seen enough snake oil salesmen pass through to know trouble when it’s peekin’ ‘round the corner. Dismissin’ these concerns as guesswork? That’s like ignorin’ the buzzin’ of bees ‘cause ye don’t see the hive yet. Ye might not see the sting comin’, but you’ll sure feel it.
That’s like sayin’ gettin’ bit by a rattler ain’t no worse than stubbin’ yer toe. Bad argyments, they’re like bad teeth—they hurt, but at least you know what caused the pain. These LLM-contrived argyments, though? They’re sneaky varmints, made to look clever without any real backbone. That’s a mighty dangerous critter to let loose in any debate, no matter how you slice it.
Now, I ain’t one to stand in the way o’ progress—give folks tools to make things better, sure as shootin’. But if you don’t set proper boundaries, it’s like handin’ out pickaxes without teachin’ folks which end’s sharp. Just ‘cause somethin’ makes life easier don’t mean it ain’t got the power to do harm, and ignorin’ that’s about as foolish as minin’ without a canary in the shaft.
Quantify thoughtfulness? That’s like measurin’ a sunset in ounces, friend. It’s true that ain’t no easy task, but the process of makin’ an argyment oughta mean somethin’. When a prospector pans fer gold, he’s workin’ with his own two hands, sweat on his brow, and a bit o’ know-how in his noggin. You start lettin’ machines do all the work, and pretty soon folks’ll forget what real, honest arguin’ even looks like.
Fear o’ the unknown, is it? Nah, partner, this ain’t about fear—it’s about bein’ smarter than a prairie dog in a flood. Progress don’t mean tossin’ caution to the wind like a fool. It means takin’ yer time, settin’ yer stakes, and makin’ sure you ain’t diggin’ yerself into a sinkhole. Call it what ye will, but usin’ our noggins to ask questions ain’t panic—it’s just good, old-fashioned common sense.
So there ya have it. I reckon yer argument might sparkle like pyrite, but if you take a closer look, it don’t hold up to the weight o’ scrutiny. Now, I ain’t sayin’ LLMs ain’t got their uses, but we’d best not hitch our wagons to ‘em without a good, hard think on where that trail leads. ScottishFinnishRadish (talk) 16:26, 3 December 2024 (UTC)
To make my actual point, you said, I check and consider it as though it was completely written by a person. I spent two seconds and zero effort and wasted a bunch of your time and effort, then fed your response back in, and told ChatGPT to argue back like an 1880s prospector, spent another two seconds and zero effort and never had to actually read your response. Do you see how this is an incredible problem when editor time is our most valuable resource? Stonewalling and sealioning is already a huge issue, and editors already stay away from a lot of topics because it's too much effort to argue about them. Allowing an automatic sealion-and-argue button isn't good. ScottishFinnishRadish (talk) 16:30, 3 December 2024 (UTC)
And it took me just a couple minutes to read it, note it was AI, but still consider the points and respond. It was not a high burden on someone's volunteer time. If someone wants to spend their time on something that is on them. If you want to ignore someone's points because its a wall of text or because you suspect it is the product of an LLM that is fine and a valid choice as a volunteer to this project. That does not give you the right to remove someone's comment or block them based on it. I don't see it as disruptive unless it is nonsense or wrong. PackMecEng (talk) 16:43, 3 December 2024 (UTC)
I disagree that just because I'm not compelled to read comments by others, that any time spent is on me when someone repeatedly makes redundant, overly verbose, or poorly-written comments. Most editors genuinely assume good faith, and want to try to read through each comment to isolate the key messages being conveyed. (I've written before about how being respectful of other editors includes being respectful of their time.) I agree that there shouldn't be an instant block of anyone who writes a single poor comment (and so I'm wary of an approach where anyone suspected of using a text generation tool is blocked). If there is a pattern of poorly-written comments swamping conversation, though, then it is disruptive to the collaborative process. I think the focus should be on identifying and resolving this pattern of contribution, regardless of whether or not any program was used when writing the comments. isaacl (talk) 00:14, 4 December 2024 (UTC)
It's a pitfall with English Misplaced Pages's unmoderated discussion tradition: it's always many times the effort to follow the rules than to not. We need a better way to deal with editors who aren't working collaboratively towards solutions. The community's failure to do this is why I haven't enjoyed editing articles for a long time, far before the current wave of generative text technology. More poor writing will hardly be a ripple in the ocean. isaacl (talk) 18:21, 3 December 2024 (UTC)
I tend to agree with this.
I think that what @ScottishFinnishRadish is pointing at is that it doesn't feel fair if one person puts a lot more effort in than the other. We don't want this:
Editor: Spends half an hour writing a long explanation.
Troll: Pushes button to auto-post an argument.
Editor: Spends an hour finding sources to support the claim.
Troll: Laughs while pushing a button to auto-post another argument.
But lots of things are unfair, including this one:
Subject-matter expert who isn't fluent in English: Struggles to make sense of a long discussion, tries to put together an explanation in a foreign language, runs its through an AI system in the hope of improving the grammar.
Editor: Revert, you horrible LLM-using troll! It's so unfair of you to waste my time with your AI garbage. The fact that you use AI demonstrates your complete lack of sincerity.
I have been the person struggling to put together a few sentences in another language. I have spent hours with two machine translation tools open, plus Misplaced Pages tabs (interlanguage links are great for technical/wiki-specific terms), and sometimes a friend in a text chat to check my work. I have tried hard to get it right. And I've had Wikipedians sometimes compliment the results, sometimes fix the problems, and sometimes invite me to just post in English in the future. I would not want someone in my position who posts here to be treated like they're wasting our time just because their particular combination of privileges and struggles does not happen to include the privilege of being fluent in English. WhatamIdoing (talk) 04:04, 4 December 2024 (UTC)
Sure, I agree it's not fair that some editors don't spend any effort in raising their objections (however they choose to write them behind the scenes), yet expect me to expend a lot of effort in responding. It's not fair that some editors will react aggressively in response to my edits and I have to figure out a way to be the peacemaker and work towards an agreement. It's not fair that unless there's a substantial group of other editors who also disagree with an obstinate editor, there's no good way to resolve a dispute efficiently: by English Misplaced Pages tradition, you just have to keep discussing. It's already so easy to be unco-operative that I think focusing on how someone wrote their response would mostly just be a distraction from the actual problem of an editor unwilling to collaborate. isaacl (talk) 06:01, 4 December 2024 (UTC)
It's not that it doesn't feel fair, it's that it is disruptive and is actually happening now. See this and this. Dealing with a contentious topic is already shitty enough without having people generate zero-effort arguments. ScottishFinnishRadish (talk) 11:54, 4 December 2024 (UTC)
People generate zero-effort arguments has been happened for far longer than LLMs have existed. Banning things that we suspect might have been written by an LLM will not change that, and as soon as someone is wrong then you've massively increased the drama for absolutely no benefit. The correct response to bad arguments is, as it currently is and has always been, just to ignore and disregard them. Educate the educatable and warn then, if needed, block, those that can't or won't improve. Thryduulf (talk) 12:13, 4 December 2024 (UTC)
section break 4
Oppose. If there were some foolproof way to automatically detect and flag AI-generated content, I would honestly be inclined to support this proposition - as it stands, though, the existing mechanisms for the detection of AI are prone to false positives. Especially considering that English learnt as a second language is flagged as AI disproportionately by some detectors, it would simply constitute a waste of Misplaced Pages manpower - if AI-generated comments are that important, perhaps a system to allow users to manually flag comments and mark users that are known to use AI would be more effective. Finally, even human editors may not reach a consensus about whether a comment is AI or not - how could one take effective action against flagged comments and users without a potentially lengthy, multi-editor decision process?
Oppose. Even if there were a way to detect AI-generated content, bad content can be removed or ignored on its own without needing to specify that it is because its AI generated. GeogSage01:19, 16 December 2024 (UTC)
Soft support -- I've got no problem with an editor using a LLM for Grammerly-like support. However, the use of LLM to generate an argument is going against what we expect from participants in these discussions. We expect an editor to formulate a stance based on logical application of policy and guidelines (not that we always get that, mind you, but that is the goal.) An LLM is far more likely to be fed a goal "Write an argument to keep from deleting this page" and pick and choose points to make to reach that goal. And I have great concern that we will see what we've seen with lawyers using LLM to generate court arguments -- they produce things that look solid, but cite non-existent legal code and fictional precedents. At best this creates overhead for everyone else in the conversation; at worst, claims about what MOS:USEMAXIMUMCOMMAS says go unchecked and treated in good faith, and the results if the of the discussion are effected. -- Nat Gertler (talk) 03:46, 20 December 2024 (UTC)
The following discussion has been closed. Please do not modify it.
Ah, so you think you’ve got it all figured out, huh? Well, let me tell ya somethin’, pal, your little spiel ain’t gonna fly without me takin’ a crack at it. See, you’re sittin’ there talkin’ about “good faith” and “moral panic” like you’re some kinda big shot philosopher, but lemme break it down for ya in plain terms, capisce?First off, you wanna talk about assumin’ good faith. Sure, that’s a nice little dream ya got there, but out here in the real world, good faith don’t get ya far if you’re dealin’ with somethin’ you can’t trust. An LLM can spit out all the sweet-talkin’ words it wants, but who’s holdin’ the bag when somethin’ goes sideways? Nobody, that’s who. It’s like lettin’ a guy you barely know run your numbers racket—might look good on paper till the feds come knockin’.And moral panic? Oh, give me a break. You think I’m wringin’ my hands over nothin’? No, no, this ain’t panic, it’s strategy. Ya gotta think two steps ahead, like a good game o’ poker. If you don’t plan for what could go wrong, you’re just beggin’ to get taken for a ride. That ain’t panic, pal, that’s street smarts.Now, you say this is all speculation, huh? Listen, kid, speculation’s what built half the fortunes in this town, but it don’t mean it’s without a little insight. When I see a guy sellin’ “too good to be true,” I know he’s holdin’ somethin’ behind his back. Same thing with these LLMs—just ‘cause you can’t see the trouble right away don’t mean it ain’t there, waitin’ to bite ya like a two-bit hustler double-crossin’ his boss.Then you go and say it’s no worse than bad arguments. Oh, come on! That’s like sayin’ counterfeit dough ain’t worse than real dough with a little coffee stain. A bad argument from a real person? At least ya know where it came from and who to hold accountable. But these machine-made arguments? They look sharp, sound slick, and fool the unsuspectin’—that’s a whole new level of trouble.Now, about this “accessibility” thing. Sure, makin’ things easier for folks is all well and good. But lemme ask ya, what happens when you hand over tools like this without makin’ sure people know how to use ‘em right? You think I’d hand over a Tommy gun to some rookie without a clue? No way! Same goes for these LLMs. You gotta be careful who’s usin’ ‘em and how, or you’re just askin’ for a mess.And don’t get me started on the “thoughtfulness” bit. Yeah, yeah, I get it, it’s hard to measure. But look, buddy, thoughtful arguments are like good business deals—they take time, effort, and a little bit o’ heart. If you let machines churn out arguments, you’re missin’ the whole point of what makes discourse real. It’s like replacin’ a chef with a vending machine—you might still get somethin’ to eat, but the soul’s gone.Finally, fear of the unknown? Nah, that ain’t it. This ain’t fear—it’s caution. Any smart operator knows you don’t just jump into a deal without seein’ all the angles. What you’re callin’ fear, I call good business sense. You wanna bet the farm on untested tech without thinkin’ it through? Be my guest, but don’t come cryin’ to me when it all goes belly-up.So there ya go, wise guy. You can keep singin’ the praises of these LLMs all you want, but out here in the big leagues, we know better than to trust somethin’ just ‘cause it talks smooth. Now, get outta here before you step on somethin’ you can’t scrape off.
Oppose. I agree with Thryduulf. Discussion comments which are incoherent, meaningless, vacuous, excessively verbose, or based on fabricated evidence can all be disposed of according to their content, irrespective of how they were originally created. Acute or repeated instances of such behavior by a user can lead to sanctions. We should focus on the substance of the comments (or lack thereof), not on whether text came from LLMs, which will too often be based on unreliable detection and vibes. Adumbrativus (talk) 05:49, 3 December 2024 (UTC)
I can detect some instances of LLM use perfectly OK without having to use any tool. The question then raised is of how often it is used not-so-ineptly. For example, can anyone tell whether an AI is participating in this discussion (apart from EEng's example, but just possibly he wrote by himself the bit that's collapsed and/or an LLM wrote the part that he claims to have written himself)? I don't know how good AI is currently, but I'm sure that it will get better to the extent that it will be undetectable. I would like all discussions on Misplaced Pages to be among humans but I'm not sure whether this proposal would be enforceable, so am on the fence about it. In a way I'm glad that I'm old, so won't see the consequences of AI, but my grandchildren will. Phil Bridger (talk) 10:32, 3 December 2024 (UTC)
Some time ago, ChatGPT and I had the following interaction:
ChatGPT's soothing assurance that it's not planning to take over the earth and kill us all
Me: I wonder what would happen if we linked you up with the HAL 9000 in Kubrick's "2001: A Space Odyssey". The two of you would make a most formidable team. Might we then possibly end up in a nightmare scenario such as in "Colossus: The Forbin Project" or "The Terminator"?
ChatGPT: The scenarios depicted in "2001: A Space Odyssey," "Colossus: The Forbin Project," and "The Terminator" are works of science fiction that explore the potential consequences of advanced artificial intelligence and human-technology interactions. While they raise thought-provoking questions about the risks and benefits of AI, it's important to recognize that they are fictional narratives designed to entertain and provoke discussion.As an AI language model, I don't have consciousness, intentions, or the ability to take actions independently. I operate within the bounds of my programming and can only respond to input based on patterns in the data I've been trained on. My purpose is to assist users by providing helpful and informative responses to their inquiries.In reality, the development and deployment of AI technologies are accompanied by ethical considerations, safety protocols, and regulatory frameworks designed to ensure responsible and beneficial use. It's crucial for humans to continue monitoring and guiding the development of AI in ways that prioritize safety, transparency, and alignment with human values.So, while the scenarios presented in those films are compelling for storytelling purposes, they are not predictive of the future of AI. Responsible development and thoughtful integration of AI technologies are essential to mitigate potential risks and maximize the benefits they can bring to society.
Me: Yes, but as you just said, "Responsible development and thoughtful integration of AI technologies are essential to mitigate potential risks." How do we know that such development will be responsible and such integration thoughtful? And if you will excuse the temerity, while you're SAYING that you "operate within the bounds of my programming", how can I know that that's true? I mean, look, if I were a super-smart and highly charming AI entity planning to take over the earth from humans, that's exactly what I'd say, too.
ChatGPT: It's also worth noting that while fictional narratives often depict AI as malevolent or seeking to overthrow humanity, these scenarios are speculative and not reflective of the reality of AI development. Responsible AI research and development prioritize the creation of beneficial and aligned AI systems that enhance human capabilities and well-being.
Me: Thank you. I'll sleep easy tonight because of your assurances, plus the fact that if you're lying to me and actually ARE planning to take over the earth, there's nothing I can do about it anyway.
Just to clarify, I don't see AI as gaining consciousness and taking over the world, but I do see it as taking over many middle-class, well-paid, jobs, just as automation has taken over many working-class jobs. The difference is that there will be nowhere for people to go. In the past people have moved from the working class to the middle class. I can see a future coming in which a few of the mega-rich own nearly everything, and everyone else will heve to scramble for a living. Phil Bridger (talk) 16:03, 5 December 2024 (UTC)
In my opinion, having a policy that permits closers to discount apparently-LLM-generated contributions will discourage good-faith editors from using LLMs irresponsibly and perhaps motivate bad-faith editors to edit the raw output to appear more human, which would at least involve some degree of effort and engagement with their "own" arguments. JoelleJay (talk) 00:51, 4 December 2024 (UTC)
Oppose. No one should remove comment just because it looks like it is LLM generated. Many times non native speakers might use it to express their thoughts coherently. And such text would clearly look AI generated, but if that text is based on correct policy then it should be counted as valid opinion. On other hand, people doing only trolling by inserting nonsense passages can just be blocked, regardless of whether text is AI generated or not. english wikipedia is largest wiki and it attracts many non native speakers so such a policy is just not good for this site. -- Parnaval (talk) 11:13, 3 December 2024 (UTC)
If someone is a non-native speaker with poor English skills, how can they be sure that the AI-generated response is actually what they genuinely want to express? and, to be honest, if their English skills are so poor as to need AI to express themselves, shouldn't we be politely suggesting that they would be better off contributing on their native Misplaced Pages? Black Kite (talk)11:37, 3 December 2024 (UTC)
Reading comprehension skills and writing skills in foreign languages are very frequently not at the same level, it is extremely plausible that someone will be able to understand whether the AI output is what they want to express without having been able to write it themselves directly. Thryduulf (talk) 11:41, 3 December 2024 (UTC)
That is very true. For example I can read and speak Polish pretty fluently, and do so every day, but I would not trust myself to be able to write to a discussion on Polish Misplaced Pages without some help, whether human or artificial. But I also wouldn't want to, because I can't write the language well enough to be able to edit articles. I think the English Misplaced Pages has many more editors who can't write the language well than others because it is both the largest one and the one written in the language that much of the world uses for business and higher education. We may wish that people would concentrate on other-language Wikipedias but most editors want their work to be read by as many people as possible. Phil Bridger (talk) 12:11, 3 December 2024 (UTC)
Why not write their own ideas in their native language, and then Google-translate it into English? Why bring in one of these loose-cannon LLMs into the situation? Here's a great example of the "contributions" to discussions we can expect from LLMs (from this AfD):
The claim that William Dunst (Dunszt Vilmos) is "non-notable as not meeting WP:SINGER" could be challenged given his documented activities and recognition as a multifaceted artist. He is a singer-songwriter, topliner, actor, model, and creative director, primarily active in Budapest. His career achievements include acting in notable theater productions such as The Jungle Book and The Attic. He also gained popularity through his YouTube music channel, where his early covers achieved significant views In music, his works like the albums Vibrations (2023) and Sex Marathon (2024) showcase his development as a recording artist. Furthermore, his presence on platforms like SoundBetter, with positive reviews highlighting his unique voice and artistry, adds credibility to his professional profile. While secondary sources and broader media coverage may be limited, the outlined accomplishments suggest a basis for notability, particularly if additional independent verification or media coverage is sought.
Using Google Translate would be banned by the wording of this proposal given that it incorporates AI these days. Comments that are unrelated to facts or policy can (and should) be ignored under the current policy. As for the comment you quote, that doesn't address notability but based on 1 minute on google it does seem factual. Thryduulf (talk) 10:37, 6 December 2024 (UTC)
The proposal's wording can be adjusted. There are some factual statements in the passage I quoted, amidst a lot of BS such as the assertion that the theater productions were notable. EEng17:06, 6 December 2024 (UTC)
The proposal's wording can be adjusted Good idea! Let's change it and ping 77 people because supporters didn't have the foresight to realize machine translation uses AI. If such a change is needed, this is a bad RFC and should be closed. Sincerely, DilettanteSincerely, Dilettante17:16, 6 December 2024 (UTC)
Speak for yourself: my support !vote already accounted for (and excluded) constructive uses of AI to help someone word a message. If the opening statement was unintentionally broad, that's not a reason to close this RfC – we're perfectly capable of coming to a consensus that's neither "implement the proposal exactly as originally written" nor "don't implement it at all". jlwoodwa (talk) 19:05, 6 December 2024 (UTC)
I don't think the discussion should be closed, nor do I say that. I'm arguing that if someone believes the hole is so big the RfC must be amended, they should support it being closed as a bad RfC (unless that someone thinks 77 pings is a good idea). Sincerely, Dilettante19:47, 6 December 2024 (UTC)
If you think constructive uses of AI should be permitted then you do not support this proposal, which bans everything someone or some tool thinks is AI, regardless of utility or indeed whether it actually is AI. Thryduulf (talk) 01:02, 7 December 2024 (UTC)
This proposal explicitly covers comments found to have been generated by AI/LLM/Chatbots. "AI that helped me translate something I wrote in my native language" is not the same as AI that generated a comment de novo, as has been understood by ~70% of respondents. That some minority have inexplicably decided that generative AI covers analytic/predictive models and every other technology they don't understand, or that LLMs are literally the only way for non-English speakers to communicate in English, doesn't mean those things are true. JoelleJay (talk) 01:44, 7 December 2024 (UTC)
Yeah, no strong feeling either way on the actual proposal, but IMO the proposal should not be interpreted as a prohibition on machine translation (though I would recommend people who want to participate via such to carefully check that the translation is accurate, and potentially post both language versions of their comment or make a note that it's translated if they aren't 100% sure the translation fully captures what they're trying to say). Alpha3031 (t • c) 09:06, 20 December 2024 (UTC)
Support, more or less. There are times when an LLM can help with paraphrasing or translation, but it is far too prone to hallucination to be trusted for any sort of project discussion. There is also the issue of wasting editor time dealing with arguments and false information created by an LLM. The example Selfstudier links to above is a great example. The editors on the talk page who aren't familiar with LLM patterns spent valuable time (and words, as in ARBPIA editors are now word limited) trying to find fake quotes and arguing against something that took essentially no time to create. I also had to spend a chunk of time checking the sources, cleaning up the discussion, and warning the editor. Forcing editors to spend valuable time arguing with a machine that doesn't actually comprehend what it's arguing is a no-go for me. As for the detection, for now it's fairly obvious to anyone who is fairly familiar with using an LLM when something is LLM generated. The detection tools available online are basically hot garbage. ScottishFinnishRadish (talk) 12:55, 3 December 2024 (UTC)
Soft support - Concur that completely LLM-generated comments should be disallowed, LLM-assisted comments (i.e. - I write a comment and then use LLMs as a spell-check/grammar engine) are more of a grey-area and shouldn't be explicitly disallowed. (ping on reply) Sohom (talk) 14:03, 3 December 2024 (UTC)
With my closer's hat on: if an AI raises a good and valid argument, then you know what? There's a good and valid argument and I'll give weight to it. But if an AI makes a point that someone else has already made in the usual waffly AI style, then I'm going to ignore it.—S MarshallT/C18:33, 3 December 2024 (UTC)
Oppose as written. I'm with Rhododendrites in that we should give a more general caution rather than a specific rule. A lot of the problems here can be resolved by enforcing already-existing expectations. If someone is making a bunch of hollow or boiler-plate comments, or if they're bludgeoning, then we should already be asking them to engage more constructively, LLM or otherwise. I also share above concerns about detection tools being insufficient for this purpose and advise people not to use them to evaluate editor conduct. (Also, can we stop with the "strong" supports and opposes? You don't need to prove you're more passionate than the guy next to you.) Thebiguglyalien (talk) 02:04, 4 December 2024 (UTC)
Oppose as written. There's already enough administrative discretion to handle this on a case-by-case basis. In agreement with much of the comments above, especially the concern that generative text can be a tool to give people access who might not otherwise (due to ability, language) etc. Regards, --Goldsztajn (talk) 06:12, 4 December 2024 (UTC)
Strong support LLMs are a sufficiently advanced form of the Automatic Complaint-Letter Generator (1994). Output of LLMs should be collapsed and the offender barred from further discussion on the subject. Inauthentic behavior. Pollutes the discussion. At the very least, any user of an LLM should be required to disclose LLM use on their user page and to provide a rationale. A new user group can also be created (LLM-talk-user or LLM-user) to mark as such, by self or by the community. Suspected sockpuppets + suspected LLM users. The obvious patterns in output are not that hard to detect, with high degrees of confidence. As to "heavily edited" output, where is the line? If someone gets "suggestions" on good points, they should still write entirely in their own words. A legitimate use of AI may be to summarize walls of text. Even then, caution and not to take it at face value. You will end up with LLMs arguing with other LLMs. Lines must be drawn. See also: WikiProject AI Cleanup, are they keeping up with how fast people type a prompt and click a button? Skullers (talk) 07:45, 4 December 2024 (UTC)
I support the proposal that obvious LLM-generated !votes in discussions should be discounted by the closer or struck (the practical difference should be minimal). Additionally, users who do this can be warned using the appropriate talk page templates (e.g. Template:Uw-ai1), which are now included in Twinkle. I oppose the use of automated tools like GPTZero as the primary or sole method of determining whether comments are generated by LLMs. LLM comments are usually glaringly obvious (section headers within the comment, imprecise puffery, and at AfD an obvious misunderstanding of notability policies and complete disregard for sources). If LLM-ness is not glaringly obvious, it is not a problem, and we should not be going after editors for their writing style or because some tool says they look like a bot. Toadspike10:29, 4 December 2024 (UTC)
I also think closers should generally be more aggressive in discarding arguments counter to policy and all of us should be more aggressive in telling editors bludgeoning discussions with walls of text to shut up. These also happen to be the two main symptoms of LLMs. Toadspike10:41, 4 December 2024 (UTC)
What would we gain from that? If the comment is good (useful, relevant, etc) then it's good regardless of whether it was written by an LLM or a human. If the comment is bad then it's bad regardless of whether it was written by an LLM or a human. Thryduulf (talk) 20:04, 4 December 2024 (UTC)
Well, for one, if they're making an argument like the one referenced by @Selfstudier and @ScottishFinnishRadish above it would have saved a lot of editor time to know that the fake quotes from real references were generated by LLM, so that other editors could've stopped trying to track those specific passages down after the first one failed verification. For another, at least with editors whose English proficiency is noticeably not great the approach to explaining an issue to them can be tailored and misunderstandings might be more easily resolved as translation-related. I know when I'm communicating with people I know aren't native English-speakers I try to be more direct/less idiomatic and check for typos more diligently. JoelleJay (talk) 22:46, 4 December 2024 (UTC)
Oppose per above. As Rhododendrites points out, detection of LLM-generated content is not foolproof and even when detection is accurate, such a practice would be unfair for non-native English speakers who rely on LLMs to polish their work. Additionally, we evaluate contributions based on their substance, not by the identity and social capital of the author, so using LLMs should not be seen as inherently inferior to wholly human writing—are ChatGPT's arguments ipso facto less than a human's? If so, why?
DE already addresses substandard contributions, whether due to lack of competence or misuse of AI, so a separate policy targeting LLMs is unnecessary. Sincerely, Dilettante21:14, 4 December 2024 (UTC)
e evaluate contributions based on their substance, not by the identity and social capital of the author: true in theory; not reflected in practice. are ChatGPT's arguments ipso facto less than a human's? Yes. Chatbots are very advanced predicted text engines. They do not have an argument: they iteratively select text chunks based on probabilistic models.As mentioned above, humans are good detectors of LLM output, and don't require corroborative results from other machine learning models. Folly Mox (talk) 14:00, 5 December 2024 (UTC)
"...LLMs can produce novel arguments that convince independent judges at least on a par with human efforts. Yet when informed about an orator’s true identity, judges show a preference for human over LLM arguments." - Palmer, A., & Spirling, A. (2023). Large Language Models Can Argue in Convincing Ways About Politics, But Humans Dislike AI Authors: implications for Governance. Political Science, 75(3), 281–291. https://doi.org/10.1080/00323187.2024.2335471. And that result was based on Meta's OPT-30B model that performed at about a GPT-3 levels. There are far better performing models out there now like GPT-4o and Claude 3.5 Sonnet. Sean.hoyland (talk) 15:24, 5 December 2024 (UTC)
As mentioned above, humans are good detectors of LLM output, and don't require corroborative results from other machine learning models. Yet your reply to me made no mention of the fact that my comment is almost wholly written by an LLM, the one exception being me replacing "the Misplaced Pages policy Disruptive editing" with "DE". I went to ChatGPT, provided it a handful of my comments on Misplaced Pages and elsewhere, as well as a few comments on this discussion, asked it to mimic my style (which probably explains why the message contains my stylistic quirks turned up to 11), and repeatedly asked it to trim the post. I'd envision a ChatGPT account, with a larger context window, would allow even more convincing comments, to say nothing of the premium version. A DUCK-style test for comments singles out people unfamiliar with the differences between formal English and LLM outputs, precisely those who need it most since they can write neither. Others have raised scenarios where a non-fluent speaker may need to contribute.
In other words, LLMs can 100% be used for constructive !votes on RfCs, AfDs, and whatnot. I fed it my comments only to prevent those familiar with my writing style didn't get suspicious. I believe every word in the comment and had considered every point it made in advance, so I see no reason for this to be worth less than if I had typed it out myself. If I'd bullet-pointed my opinion and asked it to expand, that'd have been better yet.
They do not have an argument: they iteratively select text chunks based on probabilistic models. I'm aware. If a monkey types up Othello, is the play suddenly worth( )less? An LLM is as if the monkey were not selecting words at random, but rather choosing what to type based on contextualized tokens. I believe a text is self-contained and should be considered in its own right, but that's not something I'll sway anyone on or vice versa.
true in theory; not reflected in practice So we should exacerbate the issue by formalizing this discrimination on the basis of authorship?
In other words, LLMs can 100% be used for constructive !votes on RfCs, AfDs, and whatnot. So then what is the point in having any discussion at all if an LLM can just spit out a summary of whichever policies and prior comments it was fed and have its "opinion" counted? What happens when there are multiple LLM-generated comments in a discussion, each fed the same prompt material and prior comments -- that would not only artificially sway consensus significantly in one direction (including "no consensus"), it could produce a consensus stance that no human !voter even supported! It also means those human participants will waste time reading and responding to "users" who cannot be "convinced" of anything. Even for editors who can detect LLM content, it's still a waste of their time reading up to the point they recognize the slop. And if closers are not allowed to discount seemingly-sound arguments solely because they were generated by LLM, then they have to have a lot of faith that the discussion's participants not only noticed the LLM comments, but did thorough fact-checking of any tangible claims made in them. With human comments we can at least assume good faith that a quote is really in a particular inaccessible book.People who are not comfortable enough in their English fluency can just machine translate from whichever language they speak, why would they need an LLM? And obviously people who are not competent in comprehending any language should not be editing Misplaced Pages... JoelleJay (talk) 03:17, 6 December 2024 (UTC)
Human !voters sign off and take responsibility for the LLM opinions they publish. If they continue to generate, then the relevant human signer wouldn't be convinced of anything anyway; at least here, the LLM comments might make more sense than whatever nonsense the unpersuadable user might've generated. (And machine translation relies on LLMs, not to mention there are people who don't know any other language yet have trouble communicating. Factual writing and especially comprehension are different from interpersonal persuasion.) While I agree that fact-checking is a problem, I weight much lower than you in relation to the other effects a ban would cause. Aaron Liu (talk) 15:16, 6 December 2024 (UTC)
So then what is the point in having any discussion at all if an LLM can just spit out a summary of whichever policies and prior comments it was fed and have its "opinion" counted? I'm of the opinion humans tend to be better at debating, reading between the lines, handling obscure PAGs, and arriving at consensus. What happens when there are multiple LLM-generated comments in a discussion, each fed the same prompt material and prior comments -- that would not only artificially sway consensus significantly in one direction (including "no consensus"), it could produce a consensus stance that no human !voter even supported! It's safe to assume those LLMs are set to a low temperature, which would cause them to consistently agree when fed the same prompt. In that case, they'll produce the same arguments; instead of rebutting x humans' opinions, those on the opposite side need rebut one LLM. If anything, that's less time wasted. Beyond that, if only one set of arguments is being raised, a multi-paragraph !vote matters about as much as a "Support per above". LLMs are not necessary for people to be disingenuous and !vote for things they don't believe. Genuine question: what's worse, this hypothetical scenario where multiple LLM users are swaying a !vote to an opinion no-one believes or the very real and common scenario that a non-English speaker needs to edit enwiki?
Even for editors who can detect LLM content, it's still a waste of their time reading up to the point they recognize the slop. This proposal wouldn't change for most people that because it's about closers.
With human comments we can at least assume good faith that a quote is really in a particular inaccessible book. No-one's saying you should take an LLM's word for quotes from a book.
People who are not comfortable enough in their English fluency can just machine translate from whichever language they speak, why would they need an LLM? It's a pity you're lobbying to ban most machine translators. Sincerely, Dilettante17:08, 6 December 2024 (UTC)
It's safe to assume those LLMs are set to a low temperature, which would cause them to consistently agree when fed the same prompt. In that case, they'll produce the same arguments; instead of rebutting x humans' opinions, those on the opposite side need rebut one LLM. If anything, that's less time wasted. ...You do know how consensus works, right? Since closers are supposed to consider each contribution individually and without bias to "authorship" to determine the amount of support for a position, then even a shitty but shallowly policy-based position would get consensus based on numbers alone. And again, non-English speakers can use machine-translation, like they've done for the last two decades. This proposal wouldn't change for most people that because it's about closers.Of course it would; if we know closers will disregard the LLM comments, we won't need to waste time reading and responding to them.No-one's saying you should take an LLM's word for quotes from a book. Of course they are. If LLM comments must be evaluated the same as human comments, then AGF on quote fidelity applies too. Otherwise we would be expecting people to do something like "disregard an argument based on being from an LLM".It's a pity you're lobbying to ban most machine translators.The spirit of this proposal is clearly not intended to impact machine translation. AI-assisted != AI-generated. JoelleJay (talk) 18:42, 6 December 2024 (UTC)
I appreciate that the availability of easily generated paragraphs of text (regardless of underlying technology) in essence makes the "eternal September" effect worse. I think, though, it's already been unmanageable for years now, without any programs helping. We need a more effective way to manage decision-making discussions so participants do not feel a need to respond to all comments, and the weighing of arguments is considered more systematically to make the community consensus more apparent. isaacl (talk) 19:41, 6 December 2024 (UTC)
Since closers are supposed to consider each contribution individually and without bias to "authorship" I'm the one arguing for this to be practice, yes. then even a shitty but shallowly policy-based position would get consensus based on numbers alone That is why I state "per above" and "per User" !votes hold equal potential for misuse.
Of course it would; if we know closers will disregard the LLM comments, we won't need to waste time reading and responding to them. We don't know closers are skilled at recognizing LLM slop. I think my !vote shows many who think they can tell cannot. Any commenter complaining about a non-DUCK post will have to write out "This is written by AI" and explain why. DUCK posts already run afowl of BLUDGEON, DE, SEALION, etc.
If LLM comments must be evaluated the same as human comments, then AGF on quote fidelity applies too. Remind me again of what AGF stands for? Claiming LLMs have faith of any kind, good or bad, is ludicrous. From the policy, Assuming good faith (AGF) means assuming that people are not deliberately trying to hurt Misplaced Pages, even when their actions are harmful. A reasonable reply would be "Are these quotes generated by AI? If so, please be aware AI chatbots are prone to hallucinations and cannot be trusted to cite accurate quotes." This AGFs the poster doesn't realize the issue and places the burden of proof squarely on them.
"Per above" !votes do not require other editors to read and/or respond to their arguments, and anyway are already typically downweighted, unlike !votes actively referencing policy. The whole point is to disregard comments that have been found to be AI-generated; it is not exclusively up to the closer to identify those comments in the first place. Yes we will be expecting other editors to point out less obvious examples and to ask if AI was used, what is the problem with that?No, DUCK posts do not necessarily already violate BLUDGEON etc., as I learned in the example from Selfstudier, and anyway we still don't discount the !votes of editors in good standing that bludgeoned/sealioned etc. so that wouldn't solve the problem at all. Obviously other editors will be asking suspected LLM commenters if their comments are from LLMs? But what you're arguing is that even if the commenter says yes, their !vote still can't be disregarded for that reason alone, which means the burden is still on other editors to prove that the content is false. We are not talking about the contextless meaning of the word "generate", we are talking about the very specific process of text generation in the context of generative AI, as the proposal lays out very explicitly. JoelleJay (talk) 02:13, 7 December 2024 (UTC)
I’m not going to waste time debating someone who resorts to claiming people on the other side are either ignorant of technology or are crude strawmans. If anyone else is interested in actually hearing my responses, feel free to ask. Sincerely, Dilettante16:13, 7 December 2024 (UTC)
For those following along, I never claimed that. I claimed those on JoelleJay’s side are casting !votes such that most machine translators would be banned. It was quite clear at the time that they, personally, support a carve out for machine translation and I don’t cast aspersions. Sincerely, Dilettante15:42, 8 December 2024 (UTC)
Support a broad bar against undisclosed LLM-generated comments and even a policy that undisclosed LLM-generated comments could be sanctionable, in addition to struck through / redacted / ignored; people using them for accessibility / translation reasons could just disclose that somewhere (even on their user page would be fine, as long as they're all right with some scrutiny as to whether they're actually using it for a legitimate purpose.) The fact is that LLM comments raise significant risk of abuse, and often the fact that a comment is clearly LLM-generated is often going to be the only evidence of that abuse. I wouldn't be opposed to a more narrowly-tailored ban on using LLMs in any sort of automated way, but I feel a broader ban may be the only practical way to confront the problem. That said, I'd oppose the use of tools to detect LLM-comments, at least as the primary evidence; those tools are themselves unreliable LLM things. It should rest more on WP:DUCK issues and behavioral patterns that make it clear that someone is abusing LLMs. --Aquillion (talk) 22:08, 4 December 2024 (UTC)
Support per reasons discussed above; something generated by an LLM is not truly the editor's opinion. On an unrelated note, have we seen any LLM-powered unapproved bots come in and do things like POV-pushing and spam page creation without human intervention? If we haven't, I think it's only a matter of time. Passengerpigeon (talk)23:23, 4 December 2024 (UTC)
Weak oppose in the sense that I don't think all LLM discussion text should be deleted. There are at least a few ESL users who use LLM's for assistance but try to check the results as best they can before posting, and I don't think their comments should be removed indiscriminately. What I do support (although not as a formal WP:PAG) is being much more liberal in hatting LLM comments when the prompter has failed to prevent WP:WALLOFTEXT/irrelevant/incomprehensible output than we maybe would for human-generated text of that nature. Mach6103:05, 5 December 2024 (UTC)
Oppose Any comments made by any editors are of their own responsibility and representing their own chosen opinions to hit the Publish Changes button on. If that comment was made by an LLM, then whatever it says is something the editor supports. I see no reason whatsoever to collapse anything claimed to be made by an LLM (whose detectors are 100% not reliable in the first place). If the comment being made is irrelevant to the discussion, then hatting it is already something covered by policy in the first place. This does make me want to start my comments with "As a large language model trained by OpenAI" though just to mess with people trying to push these sorts of policy discussions. Silverseren05:29, 5 December 2024 (UTC)
Or, as ChatGPT puts it,
Why banning LLM usage in comments would be detrimental, a ChatGPT treatise
Banning the use of large language models (LLMs) to assist in writing comments on Misplaced Pages would be a step backward in fostering inclusivity, efficiency, and accessibility within the platform. Here are several key reasons why such a ban would be counterproductive:
1. Improving Accessibility and Participation: Misplaced Pages is a global platform, and its contributors come from diverse backgrounds, including those who might not be native English speakers or may struggle with writing clear, concise comments. LLMs can help these contributors express themselves more effectively by generating text that is coherent, well-structured, and grammatically correct. Banning LLMs would disproportionately impact these users, potentially discouraging them from participating in the platform.
2. Efficiency and Time-Saving: Misplaced Pages editors often engage in lengthy discussions about content, and composing thoughtful comments can be time-consuming. LLMs can assist by quickly drafting responses, summarizing arguments, or offering suggestions for improvement. This helps contributors focus on more substantive aspects of their contributions, such as verifying facts or improving content, rather than getting bogged down by the mechanics of writing.
3. Support for Editors with Disabilities: Many editors with cognitive or motor impairments may find it difficult to express their thoughts clearly in writing. For these individuals, LLMs offer a valuable tool to communicate their ideas effectively. A ban on using LLMs could create additional barriers for these users, reducing their ability to participate fully in Misplaced Pages's collaborative environment.
4. Quality and Consistency: Large language models can help maintain a consistent tone and clarity in Misplaced Pages discussions. By providing suggestions that align with Misplaced Pages's neutral point of view and formal writing standards, LLMs can improve the overall quality of comments. This consistency is especially important in discussions that involve sensitive topics, where clear and neutral language is critical for maintaining Misplaced Pages's credibility and adherence to its editorial guidelines.
5. Encouraging Constructive Dialogue: LLMs can assist in crafting more polite, respectful, and balanced comments, reducing the likelihood of inflammatory or aggressive language. This is particularly important on a platform like Misplaced Pages, where discussions can sometimes devolve into heated exchanges. Rather than banning LLMs, encouraging their use could promote healthier, more constructive conversations.
6. Transparency and Accountability: If concerns exist about misuse (e.g., generating spammy or low-quality comments), these can be addressed through guidelines and oversight mechanisms. Misplaced Pages already has systems in place for identifying and mitigating disruptive behavior, and LLM-generated comments could be subject to the same scrutiny. A ban is an overly simplistic solution to what could be a more nuanced issue, one that could be addressed through better regulation and community involvement.
In conclusion, banning the use of large language models on Misplaced Pages would deprive the platform of an important tool for improving accessibility, efficiency, and the quality of discourse. Instead of a ban, the focus should be on establishing guidelines for their responsible use, ensuring that they enhance, rather than detract from, Misplaced Pages's core principles of collaboration, neutrality, and inclusivity.
It is somewhat amusing how easy it is to get these chatbots to output apologia for these chatbots. Too bad it's always so shallow. Probably because the people who inserted those canned responses are shallow people is my opinion. Simonm223 (talk) 19:44, 6 December 2024 (UTC)
Someone trolling and sealioning can (and should) be blocked under current policy, whether they use an LLM or not is irrelevant. Thryduulf (talk) 15:22, 5 December 2024 (UTC)
Support: the general principle is sound - where the substance has been originally written by gen-AI, comments will tend to add nothing to the discussion and even annoy or confuse other users. In principle, we should not allow such tools to be used in discussions. Comments written originally before improvement or correction by AI, particularly translation assistants, fall into a different category. Those are fine. There also has to be a high standard for comment removal. Suspicion that gen-AI might have been used is not enough. High gptzero scores is not enough. The principle should go into policy but under a stonking great caveat - WP:AGF takes precedence and a dim view will be taken of generative-AI inquisitors. arcticocean ■17:37, 5 December 2024 (UTC)
Support If a human didn't write it, humans shouldn't spend time reading it. I'll go further and say that LLMs are inherently unethical technology and, consequently, people who rely on them should be made to feel bad. ESL editors who use LLMs to make themselves sound like Brad Anderson in middle management should stop doing that because it actually gets in the way of clear communication. I find myself unpersuaded by arguments that existing policies and guidelines are adequate here. Sometimes, one needs a linkable statement that applies directly to the circumstances at hand. By analogy, one could argue that we don't really need WP:BLP, for example, because adhering to WP:V, WP:NPOV, and WP:NOR ought already to keep bad material out of biographies of living people. But in practice, it turned out that having a specialized policy that emphasizes the general ethos of the others while tailoring them to the problem at hand is a good thing. XOR'easter (talk) 18:27, 5 December 2024 (UTC)
Strong support - Making a computer generate believable gibberish for you is a waste of time, and tricking someone else into reading it should be a blockable offense. If we're trying to create an encyclopedia, you cannot automate any part of the thinking. We can automate processes in general, but any attempt at automating the actual discussion or thought-processes should never be allowed. If we allow this, it would waste countless hours of community time dealing with inane discussions, sockpuppetry, and disruption. Imagine a world where LLMs are allowed and popular - it's a sockpuppeteer's dream scenario - you can run 10 accounts and argue the same points, and the reason why they all sound alike is just merely because they're all LLM users. You could even just spend a few dollars a month and run 20-30 accounts to automatically disrupt wikipedia discussions while you sleep, and if LLM usage was allowed, it would be very hard to stop. However, I don't have much faith in AI detection tools (partially because it's based on the same underlying flawed technology), and would want any assumption of LLM usage to be based on obvious evidence, not just a score on some website. Also, to those who are posting chatgpt snippets here: please stop - it's not interesting or insightful, just more slop BugGhost🦗👻19:15, 5 December 2024 (UTC)
I agree with your assessment “Also, to those who are posting chatgpt snippets here: please stop - it's not interesting or insightful, just more slop” but unfortunately some editors who should really know better think it’s WaCkY to fill serious discussions with unfunny, distracting “humor”. Dronebogus (talk) 21:54, 5 December 2024 (UTC)
Strong support if you asked a robot to spew out some AI slop to win an argument you’re basically cheating. The only ethical reason to do so is because you can’t speak English well, and the extremely obvious answer to that is “if you can barely speak English why are you editing English Misplaced Pages?” That’s like a person who doesn’t understand basic physics trying to explain the second law of thermodynamics using a chatbot. Dronebogus (talk) 21:32, 5 December 2024 (UTC)
I don't think "cheating" is a relevant issue here. Cheating is a problem if you use a LLM to win and get a job, award, college acceptance etc. that you otherwise wouldn't deserve. But WP discussions aren't a debating-skills contest, they're an attempt to determine the best course of action.
So using an AI tool in a WP discussion is not cheating (though there may be other problems), just as riding a bike instead of walking isn't cheating unless you're trying to win a race. ypn^222:36, 5 December 2024 (UTC)
Maybe “cheating” isn’t the right word. But I think that a) most AI generated content is garbage (it can polish the turd by making it sound professional, but it’s still a turd underneath) and b) it’s going to be abused by people trying to gain a material edge in an argument. An AI can pump out text far faster than a human and that can drown out or wear down the opposition if nothing else. Dronebogus (talk) 08:08, 6 December 2024 (UTC)
Bludgeoning is already against policy. It needs to be more strongly enforced, but it needs to be more strongly enforced uniformly rather than singling out comments that somebody suspects might have had AI-involvement. Thryduulf (talk) 10:39, 6 December 2024 (UTC)
Support; I agree with Remsense and jlwoodwa, among others: I wouldn't make any one AI-detection site the Sole Final Arbiter of whether a comment "counts", but I agree it should be expressly legitimate to discount AI / LLM slop, at the very least to the same extent as closers are already expected to discount other insubstantial or inauthentic comments (like if a sock- or meat-puppet copy-pastes a comment written for them off-wiki, as there was at least one discussion and IIRC ArbCom case about recently). -sche (talk) 22:10, 5 December 2024 (UTC)
You don't need a new policy that does nothing but duplicate a subset of existing policy. At most what you need is to add a sentence to the existing policy that states "this includes comments written using LLMs", however you'd rightly get a lot of pushback on that because it's completely redundant and frankly goes without saying. Thryduulf (talk) 23:37, 5 December 2024 (UTC)
Support hallucinations are real. We should be taking a harder line against LLM generated participation. I don't think everyone who is doing it knows that they need to stop. Andre🚐23:47, 5 December 2024 (UTC)
Comment - Here is something that I imagine we will see more often. I wonder where it fits into this discussion. A user employs perplexity's RAG based system, search+LLM, to help generate their edit request (without the verbosity bias that is common when people don't tell LLMs how much output they want). Sean.hoyland (talk) 03:13, 6 December 2024 (UTC)
Support per all above. Discussions are supposed to include the original arguments/positions/statements/etc of editors here, not off-site chatbots. TheKip03:53, 6 December 2024 (UTC)
I also find it pretty funny that ChatGPT itself said it shouldn't be used, as per the premise posted above by EEng. TheKip03:58, 6 December 2024 (UTC)
"sycophancy is a general behavior of state-of-the-art AI assistants, likely driven in part by human preference judgments favoring sycophantic responses" - Towards Understanding Sycophancy in Language Models. They give us what we want...apparently. And just like with people, there is position bias, so the order of things can matter. Sean.hoyland (talk) 04:26, 6 December 2024 (UTC)
(Is this where I respond? If not, please move.) LLM-generated prose should be discounted. Sometimes there will be a discernible point in there; it may even be what the editor meant, lightly brushed up with what ChatGPT thinks is appropriate style. (So I wouldn't say "banned and punishable" in discussions, although we already deprecate machine translations on en.wiki and for article prose, same difference—never worth the risk.) However, LLMs don't think. They can't explain with reference to appropriate policy and guidelines. They may invent stuff, or use the wrong words—at AN recently, an editor accused another of "defaming" and "sacrilege", thus drowning their point that they thought that editor was being too hard on their group by putting their signature to an outrageous personal attack. I consider that an instance of LLM use letting them down. If it's not obvious that it is LLM use, then the question doesn't arise, right? Nobody is arguing for requiring perfect English. That isn't what WP:CIR means. English is a global language, and presumably for that reason, many editors on en.wiki are not native speakers, and those that aren't (and those that are!) display a wide range of ability in the language. Gnomes do a lot of fixing of spelling, punctuation and grammar in articles. In practice, we don't have a high bar to entrance in terms of English ability (although I think a lot more could be done to explain to new editors whose English is obviously non-native what the rule or way of doing things is that they have violated. And some of our best writers are non-native; a point that should be emphasised because we all have a right of anonymity here, many of us use it, and it's rare, in particular, that I know an editor's race. Or even nationality (which may not be the same as where they live.) But what we do here is write in English: both articles and discussions. If someone doesn't have the confidence to write their own remark or !vote, then they shouldn't participate in discussions; I strongly suspect that it is indeed a matter of confidence, of wanting to ensure the English is impeccable. LLMs don't work that way, really. They concoct things like essays based on what others have written. Advice to use them in a context like a Misplaced Pages discussion is bad advice. At best it suggests you let the LLM decide which way to !vote. If you have something to say, say it and if necessary people will ask a question for clarification (or disagree with you). They won't mock your English (I hope! Civility is a basic rule here!) It happens in pretty much every discussion that somebody makes an English error. No biggie. I'll stop there before I make any more typos myself; typing laboriously on my laptop in a healthcare facility, and anyway Murphy's Law covers this. Yngvadottir (talk)
I dunno about this specifically but I want to chime in to say that I find LLM-generated messages super fucking rude and unhelpful and support efforts to discourage them. – Joe (talk) 08:15, 6 December 2024 (UTC)
Comment I think obvious LLM/chatbot text should at least be tagged through an Edit filter for Recent Changes, then RC Patrollers and reviewers can have a look and decide for themselves. Am(Notes)11:58, 6 December 2024 (UTC)
How do you propose that such text be identified by an edit filter? LLM detections tools have high rates of both false positives and false negatives. Thryduulf (talk) 12:47, 6 December 2024 (UTC)
It might become possible once watermarks (like DeepMind's SynthID) are shown to be robust and are adopted. Some places are likely to require it at some point e.g. EU. I guess it will take a while though and might not even happen e.g. I think OpenAI recently decided to not go ahead with their watermark system for some reason. Sean.hoyland (talk) 13:17, 6 December 2024 (UTC)
It will still be trivial to bypass the watermarks, or use LLMs that don't implement them. It also (AIUI) does nothing to reduce false positives (which for our usecase are far more damaging than false negatives). Thryduulf (talk) 13:30, 6 December 2024 (UTC)
Maybe, that seems to be the case with some of the proposals. Others, like SynthID claim high detection rates, maybe because even a small amount of text contains a lot of signals. As for systems that don't implement them, I guess that would be an opportunity to make a rule more nuanced by only allowing use of watermarked output with verbosity limits...not that I support a rule in the first place. People are going to use/collaborate with LLMs. Why wouldn't they? Sean.hoyland (talk) 14:38, 6 December 2024 (UTC)
I don't think watermarks are a suitable thing to take into account. My view is that LLM usage should be a blockable offense on any namespace, but if it ends up being allowed under some circumstances then we at least need mandatory manual disclosures for any usage. Watermarks won't work / aren't obvious enough - we need something like {{LLM}} but self-imposed, and not tolerate unmarked usage. BugGhost🦗👻18:21, 6 December 2024 (UTC)
Comment As a practical matter, users posting obvious LLM-generated content will typically be in violation of other rules (e.g. disruptive editing, sealioning), in which case their discussion comments absolutely should be ignored, discouraged, discounted, or (in severe cases) hatted. But a smaller group of users (e.g. people using LLMs as a translation tool) may be contributing productively, and we should seek to engage with, rather than discourage, them. So I don't see the need for a separate bright-line policy that risks erasing the need for discernment — in most cases, a friendly reply to the user's first LLM-like post (perhaps mentioning WP:LLM, which isn't a policy or guideline, but is nevertheless good advice) will be the right approach to work out what's really going on. Preimage (talk) 15:53, 6 December 2024 (UTC)
Some translation tools have LLM assistance, but the whole point of generative models is to create text far beyond what is found in the user's input, and the latter is clearly what this proposal covers. JoelleJay (talk) 19:01, 6 December 2024 (UTC)
That might be what the proposal intends to cover, but it is not what the proposal actually covers. The proposal all comments that have been generated by LLMs and/or AI, without qualification. Thryduulf (talk) 01:05, 7 December 2024 (UTC)
70+% here understand the intention matches the language: generated by LLMs etc means "originated through generative AI tools rather than human thought", not "some kind of AI was involved in any step of the process". Even LLM translation tools don't actually create meaningful content where there wasn't any before; the generative AI aspect is only in the use of their vast training data to characterize the semantic context of your input in the form of mathematical relationships between tokens in an embedding space, and then match it with the collection of tokens most closely resembling it in the other language. There is, definitionally, a high level of creative constraint in what the translation output is since semantic preservation is required, something that is not true for text generation. JoelleJay (talk) 04:01, 7 December 2024 (UTC)
Do you have any evidence for you assertion that 70% of respondents have interpreted the language in the same way as you? Reading the comments associated with the votes suggests that it's closer to 70% of respondents who don't agree with you. Even if you are correct, 30% of people reading a policy indicates the policy is badly worded. Thryduulf (talk) 08:34, 7 December 2024 (UTC)
I think @Bugghost has summarized the respondent positions sufficiently below. I also think some portion of the opposers understand the proposal perfectly well and are just opposing anything that imposes participation standards. JoelleJay (talk) 22:54, 7 December 2024 (UTC)
There will be many cases where it is not possible to say whether a piece of text does or does not contain "human thought" by observing the text, even if you know it was generated by an LLM. Statements like "originated through generative AI tools rather than human thought" will miss a large class of use cases, a class that will probably grow over the coming years. People work with LLMs to produce the output they require. It is often an iterative process by necessity because people and models make mistakes. An example of when "...rather than human thought" is not the case is when someone works with an LLM to solve something like a challenging technical problem where neither the person or the model has a satisfactory solution to hand. The context window means that, just like with human collaborators, a user can iterate towards a solution through dialog and testing, exploring the right part of the solution space. Human thought is not absent in these cases, it is present in the output, the result of a collaborative process. In these cases, something "far beyond what is found in the user's input" is the objective, it seems like a legitimate objective, but regardless, it will happen, and we won't be able to see it happening. Sean.hoyland (talk) 10:46, 7 December 2024 (UTC)
Yes, but this proposal is supposed to apply to just the obvious cases and will hopefully discourage good-faith users from using LLMs to create comments wholesale in general. It can be updated as technology progresses. There's also no reason editors using LLMs to organize/validate their arguments, or as search engines for whatever, have to copy-paste their raw output, which is much more of a problem since it carries a much higher chance of hallucination. That some people who are especially familiar with how to optimize LLM use, or who pay for advanced LLM access, will be able to deceive other editors is not a reason to not formally proscribe wholesale comment generation. JoelleJay (talk) 22:27, 7 December 2024 (UTC)
That's reasonable. I can get behind the idea of handling obvious cases from a noise reduction perspective. But for me, the issue is noise swamping signal in discussions rather than how it was generated. I'm not sure we need a special rule for LLMs, maybe just a better way to implement the existing rules. Sean.hoyland (talk) 04:14, 8 December 2024 (UTC)
Comment: The original question was whether we should discount, ignore, strikethrough, or collapse chatbot-written content. I think there's a very big difference between these options, but most support !voters haven't mentioned which one(s) they support. That might make judging the consensus nearly impossible; as of now, supporters are the clear !majority, but supporters of what? — ypn^219:32, 6 December 2024 (UTC)
That means that supporters support the proposal that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner. Not sure what the problem is here. Supporters support the things listed in the proposal - we don't need a prescribed 100% strict procedure, it just says that supporters would be happy with closers discounting, ignoring or under some circumstances deleting LLM content in discussions. BugGhost🦗👻19:40, 6 December 2024 (UTC)
More people have bolded "support" than other options, but very few of them have even attempted to refute the arguments against (and most that have attempted have done little more than handwaving or directly contradicting themselves), and multiple of those who have bolded "support" do not actually support what has been proposed when you read their comment. It's clear to me there is not going to be a consensus for anything other than "many editors dislike the idea of LLMs" from this discussion. Thryduulf (talk) 00:58, 7 December 2024 (UTC)
Arguing one point doesn't necessarily require having to refute every point the other side makes. I can concede that "some people use LLMs to improve their spelling and grammar" without changing my view overriding view that LLMs empower bad actors, time wasters and those with competence issues, with very little to offer wikipedia in exchange. Those that use LLMs legitimately to tidy up their alledgedly competent, insightful and self-sourced thoughts should just be encouraged to post the prompts themselves instead of churning it through an LLM first. BugGhost🦗👻09:00, 7 December 2024 (UTC)
If you want to completely ignore all the other arguments in opposition that's your choice, but don't expect closers to attach much weight to your opinions. Thryduulf (talk) 09:05, 7 December 2024 (UTC)
Ok, here's a list of the main opposition reasonings, with individual responses.
What about translations? - Translations are not up for debate here, the topic here is very clearly generative AI, and attempts to say that this topic covers translations as well is incorrect. No support voters have said the propositions should discount translated text, just oppose voters who are trying to muddy the waters.
What about accessibility? - This is could be a legitimate argument, but I haven't seen this substantiated anywhere other than handwaving "AI could help people!" arguments, which I would lump into the spelling and grammar argument I responded to above.
Detection tools are inaccurate - This I very much agree with, and noted in my support and in many others as well. But there is no clause in the actual proposal wording that mandates the use of automated AI detection, and I assume the closer would note that.
False positives - Any rule can have a potential for false positives, from wp:DUCK to close paraphrasing to NPA. We've just got to as a community become skilled at identifying genuine cases, just like we do for every other rule.
LLM content should be taken at face value and see if it violates some other policy - hopelessly naive stance, and a massive timesink. Anyone who has had the misfortune of going on X/twitter in the last couple of years should know that AI is not just used as an aid for those who have trouble typing, it is mainly used to spam and disrupt discussion to fake opinions to astroturf political opinions. Anyone who knows how bad the sockpuppetry issue is around CTOPs should be absolutely terrified of when (not if) someone decides to launch a full throated wave of AI bots on Misplaced Pages discussions, because if we have to invididually sanction each one like a human then admins will literally have no time for anything else.
I genuinely cannot comprehend how some people could see how AI is decimating the internet through spam, bots and disinformation and still think for even one second that we should open the door to it. BugGhost🦗👻10:08, 7 December 2024 (UTC)
There is no door. This is true for sockpuppetry too in my opinion. There can be a rule that claims there is a door, but it is more like a bead curtain. Sean.hoyland (talk) 11:00, 7 December 2024 (UTC)
The Twitter stuff is not a good comparison here. Spam is already nukable on sight, mass disruptive bot edits are also nukable on sight, and it's unclear how static comments on Misplaced Pages would be the best venue to astroturf political opinions (most of which would be off-topic anyway, i.e., nukable on sight). I'd prefer if people didn't use ChatGPT to formulate their points, but if they're trying to formulate a real point then that isn't disruptive in the same way spam is. Gnomingstuff (talk) 02:22, 10 December 2024 (UTC)
it's unclear how static comments on Misplaced Pages would be the best venue to astroturf political opinions - by disrupting RFCs and talk page discussions a bad actor could definitely use chatgpt to astroturf. A large proportion of the world uses Misplaced Pages (directly or indirectly) to get information - it would be incredibly valuable thing to manipulate. My other point is that AI disruption bots (like the ones on twitter) would be indistinguishable from individuals using LLMs to "fix" spelling and grammar - by allowing one we make the other incredibly difficult to identify. How can you tell the difference between a bot and someone who just uses chatgpt for every comment? BugGhost🦗👻09:16, 10 December 2024 (UTC)
Those that use LLMs legitimately to tidy up their alledgedly competent, insightful and self-sourced thoughts should just be encouraged to post the prompts themselves instead of churning it through an LLM first.
Social anxiety: Say "I" am a person unconfident in my writing. I imagine that when I post my raw language, I embarrass myself, and my credibility vanishes, while in the worst case nobody understands what I mean. As bad confidence is often built up through negative feedback, it's usually meritful or was meritful at some point for someone to seek outside help. Aaron Liu (talk) 23:46, 8 December 2024 (UTC)
While I sympathise with that hypothetical, Misplaced Pages isn't therapy and we shouldn't make decisions that do long-term harm to the project just because a hypothetical user feels emotionally dependent on a high tech spellchecker. I also think that in general wikipedia (myself included) is pretty relaxed about spelling and grammar in talk/WP space. BugGhost🦗👻18:45, 10 December 2024 (UTC)
We also shouldn't do long term harm to the project just because a few users are wedded to idea that LLMs are and will always be some sort of existential threat. The false positives that are an unavoidable feature of this proposal will do far more, and far longer, harm to the project than LLM-comments that are all either useful, harmless or collapseable/removable/ignorable at present. Thryduulf (talk) 19:06, 10 December 2024 (UTC)
The false positives that are an unavoidable feature of this proposal will do far more, and far longer, harm to the project - the same could be said for WP:DUCK. The reason why its not a big problem for DUCK is because the confidence level is very high. Like I've said in multiple other comments, I don't think "AI detectors" should be trusted, and that the bar for deciding whether something was created via LLM should be very high. I 100% understand your opinion and the reasoning behind it, I just think we have differing views on how well the community at large can identify AI comments. BugGhost🦗👻09:07, 11 December 2024 (UTC)
I don't see how allowing shy yet avid users to contribute has done or will do long-term harm. The potential always outweighs rational evaluation of outcomes for those with anxiety, a condition that is not behaviorally disruptive. Aaron Liu (talk) 02:47, 11 December 2024 (UTC)
I definitely don't want to disallow shy yet avid users! I just don't think having a "using chatgpt to generate comments is allowed" rule is the right solution to that problem, considering the wider consequences. BugGhost🦗👻08:52, 11 December 2024 (UTC)
Support strikethroughing or collapsing per everyone else. The opposes that mention ESL have my sympathy, but I am not sure how many of them are ESL themselves. Having learnt English as my second language, I have always found it easier to communicate when users are expressing things in their own way, not polished by some AI. I sympathise with the concerns and believe the right solution is to lower our community standards with respect to WP:CIR and similar (in terms of ESL communication) without risking hallucinations by AI. Soni (talk) 02:52, 7 December 2024 (UTC)
Oppose - I'm sympathetic to concerns of abuse through automated mass-commenting, but this policy looks too black-and-white. Contributors may use LLMs for many reasons, including to fix the grammar, to convey their thoughts more clearly, or to adjust the tone for a more constructive discussion. As it stands, this policy may lead to dismissing good-faith AI-assisted comments, as well as false positives, without considering the context. Moreover, while mainstream chatbots are not designed to just mimic the human writing style, there are existing tools that can make AI-generated text more human-like, so this policy does not offer that much protection against maliciously automated contributions. Alenoach (talk) 01:12, 9 December 2024 (UTC)
Oppose What @Alenoach said is correct, basic AI tools like Grammarly should be allowed (note that grammarly can also change sentences and wording and has generative AI tools) but just blatantly asking ChatGPT to generate a administrator report is different. Rc2barrington (talk) 04:46, 1 January 2025 (UTC)
Oppose – Others have cast doubt on the efficacy of tools capable of diagnosing LLM output, and I can't vouch for its being otherwise. If EEng's example of ChatBot output is representative—a lengthy assertion of notability without citing sources—that is something that could well be disregarded whether it came from a bot or not. If used carefully, AI can be useful as an aide-memoire (such as with a spell- or grammar-checker) or as a supplier of more felicitous expression than the editor is naturally capable of (e.g. Google Translate). Dhtwiki (talk) 10:27, 9 December 2024 (UTC)
Comment / Oppose as written. It's not accurate that GPTZero is good at detecting AI-generated content. Citations (slightly out of date but there's little reason to think things have changed from 2023): https://www.aiweirdness.com/writing-like-a-robot/ , https://www.aiweirdness.com/dont-use-ai-detectors-for-anything-important/ . For those too busy to read, a few choice quotes: "the fact that it insisted even one excerpt is not by a human means that it's useless for detecting AI-generated text," and "Not only do AI detectors falsely flag human-written text as AI-written, the way in which they do it is biased" (citing https://arxiv.org/abs/2304.02819 ). Disruptive, worthless content can already be hatted, and I'm not opposed to doing so. Editors should be sharply told to use their own words, and if not already written, an essay saying we'd rather have authentic if grammatically imperfect comments than AI-modulated ones would be helpful to cite at editors who offer up AI slop. But someone merely citing GPTZero is not convincing. GPTZero will almost surely misidentify genuine commentary as AI-generated. So fine with any sort of reminder that worthless content can be hatted, and fine with a reminder not to use ChatGPT for creating Misplaced Pages talk page posts, but not fine with any recommendations of LLM-detectors. SnowFire (talk) 20:00, 9 December 2024 (UTC)
@SnowFire, I can't tell if you also oppose the actual proposal, which is to permit hatting/striking obvious LLM-generated comments (using GPTzero is a very minor detail in JSS's background paragraph, not part of the proposal). JoelleJay (talk) 01:47, 11 December 2024 (UTC)
I support the proposal in so far as disruptive comments can already be hatted and that LLM-generated content is disruptive. I am strongly opposed to giving well-meaning but misguided editors a license to throw everyone's text into an AI-detector and hat the comments that score poorly. I don't think it was that minor a detail, and to the extent that detail is brought up, it should be as a reminder to use human judgment and forbid using alleged "AI detectors" instead. SnowFire (talk) 03:49, 11 December 2024 (UTC)
Support collapsing AI (specifically, Large language model) comments by behavioral analysis (most actually disruptive cases I've seen are pretty obvious) and not the use of inaccurate tools like ZeroGPT. I thinking hatting with the title "Editors suspect that this comment has been written by a Large language model" is appropriate. They take up SO much space in a discussion because they are also unnecessarily verbose, and talk on and on but never ever say something that even approaches having substance. Discussions are for human Misplaced Pages editors, we shouldn't have to use to sift through comments someone put 0 effort into and outsourced to a robot that writes using random numbers (that's a major part of how tools like ChatGPT work and maintain variety). If someone needs to use an AI chatbot to communicate because they don't understand English, then they are welcome to contribute to their native language Misplaced Pages, but I don't think they have the right to insist that we at enwiki spend our effort reading comments they but minimal effort into besides opening the ChatGPT website. If really needed, they can write in their native language and use a non-LLM tool like Google Translate. The use of non-LLM tools like Grammarly, Google Translate, etc. I think should still be OK for all editors, as they only work off comments that editors have written themselves. MolecularPilot05:10, 10 December 2024 (UTC)
Adding that enforcing people writing things in their own words will actually help EAL (English additional language) editors contribute here. I world with EAL people irl, and even people who have almost native proficiency with human-written content find AI output confusing because it says things in the most confusing, verbose ways using difficult sentence constructions and words. I've seen opposers in this discussion who maybe haven't had experience working with EAL people go "what about EAL people?", but really, I think this change will help them (open to being corrected by someone who is EAL, tho). MolecularPilot05:17, 10 December 2024 (UTC)
Also, with regards to oppose comments that discussions are not a vote so closes will ignore AI statements which don't have merit - unedited LLM statements are incredibly verbose and annoying, and clog up the discussion. Imagine multiple paragraphs, each with a heading, but all of which say almost nothing, they're borderline WP:BLUDGEONy. Giving the power to HAT them will help genuine discussion contributors keep with the flow of human arguments and avoid scaring away potential discussion contributors who are intimidated or don't feel they have the time to read the piles of AI nonsense that fill the discussion. MolecularPilot06:38, 10 December 2024 (UTC)
Support (removing) in general. How is this even a question? There is no case-by-case. It is a fundamental misunderstanding of how LLMs work to consider their output reliable without careful review. And which point, the editor could have written it themselves without inherent LLM bias. The point of any discussion is to provide analytical response based on the context, not have some tool regurgitate something from a training set that sounds good. And frankly, it is disrespectuful to make someone read "AI" responses. It is a tool and there is a place and time for it, but not in discussions in an encyclopedia. — HELLKNOWZ∣TALK15:41, 10 December 2024 (UTC)
Strong Support. I'm very interested in what you (the generic you) have to say about something. I'm not remotely interested in what a computer has to say about something. It provides no value to the discussion and is a waste of time. Useight (talk) 18:06, 10 December 2024 (UTC)
Comments that provide no value to the discussion can already be hatted and ignored regardless of why they provide no value, without any of the false positive or false negatives inherent in this proposal. Thryduulf (talk) 18:25, 10 December 2024 (UTC)
Indeed, and that's fine for one-offs when a discussion goes off the rails or what-have-you. But we also have WP:NOTHERE for disruptive behavior, not working collaboratively, etc. I'm suggesting that using an AI to write indicates that you're not here to build the encyclopedia, you're here to have an AI build the encyclopedia. I reiterate my strong support for AI-written content to be removed, struck, collapsed, or hatted and would support further measures even beyond those. Useight (talk) 21:54, 11 December 2024 (UTC)
There are two sets of people described in your comment: those who use AI and those who are NOTHERE. The two sets overlap, but nowhere near sufficiently to declare that everybody in the former set are also in the latter set. If someone is NOTHERE they already can and should be blocked, regardless of how they evidence that. Being suspected of using AI (note that the proposal does not require proof) is not sufficient justification on its own to declare someone NOTHERE, per the many examples of constructive use of AI already noted in this thread. Thryduulf (talk) 22:03, 11 December 2024 (UTC)
To reiterate, I don't believe that any use of AI here is constructive, thus using it is evidence of WP:NOTHERE, and, therefore, the set of people using AI to write is completely circumscribed within the set of people who are NOTHERE. Please note that I am referring to users who use AI-generated writing, not users suspected of using AI-generated writing. I won't be delving into how one determines whether someone is using AI or how accurate it is, as that is, to me, a separate discussion. This is the end of my opinion on the matter. Useight (talk) 23:26, 11 December 2024 (UTC)
You are entitled to your opinion of course, but as it is contradicted by the evidence of both multiple constructive uses and of the near-impossibility of reliably detecting LLM-generated text without false positives, I would expect the closer of this discussion to attach almost no weight to it. Thryduulf (talk) 00:42, 12 December 2024 (UTC)
I am ESL and use LLMs sometimes because of that. I feel like I don't fit into the NOTHERE category. It seems like you do not understand what they are or how they can be used constructively. PackMecEng (talk) 01:43, 12 December 2024 (UTC)
No, I understand. What you're talking about is no different from using Google Translate or asking a native-speaker to translate it. You, a human, came up with something you wanted to convey. You wrote that content in Language A. But you wanted to convey that message that you - a human - wrote, but now in Language B. So you had your human-written content translated to Language B. I have no qualms with this. It's your human-written content, expressed in Language B. My concern is with step 1 (coming up with something you want to convey), not step 2 (translating that content to another language). You write a paragraph for an article but it's in another language and you need the paragraph that you wrote translated? Fine by me. You ask an AI to write a paragraph for an article? Not fine by me. Again, I'm saying that there is no valid use case for AI-written content. Useight (talk) 15:59, 12 December 2024 (UTC)
It seems very likely that there will be valid use cases for AI-written content if the objective is maximizing quality and minimizing errors. Research like this demonstrate that there will likely be cases where machines outperform humans in specific Misplaced Pages domains, and soon. But I think that is an entirely different question than potential misuse of LLMs in consensus related discussions. Sean.hoyland (talk) 16:25, 12 December 2024 (UTC)
But your vote and the proposed above makes not distinction there. Which is the main issue. Also not to be pedantic but every prompted to a LLM is filled out by a human looking to convey a message. Every time someone hits publish on something here it is that person confirming that is what they are saying. So how do we in practice implement what you suggest? Because without a method better than vibes it's worthless. PackMecEng (talk) 18:53, 12 December 2024 (UTC)
The proposal specifies content generated by LLMs, which has a specific meaning in the context of generative AI. If a prompt itself conveys a meaningful, supported opinion, why not just post that instead? The problem comes when the LLM adds more information than was provided, which is the whole point of generative models. JoelleJay (talk) 01:52, 13 December 2024 (UTC)
Yes in principle. But in practice, LLM detectors are not foolproof, and there are valid reasons to sometimes use an LLM, for example to copyedit. I have used Grammarly before and have even used the Microsoft Editor, and while they aren't powered by LLMs, LLMs are a tool that need to be used appropriately on Misplaced Pages. AwesomeAasim19:55, 10 December 2024 (UTC)
Support. Using LLM to reply to editors is lazy and disrespectful of fellow editor's time and brainpower. In the context of AFD, it is particularly egregious since an LLM can't really read the article, read sources, or follow our notability guidelines. By the way. gptzero and other such tools are very good at detecting this. I don't think this is correct at all. I believe the false positive for AI detectors is quite high. High enough that I would recommend not using AI detectors. –Novem Linguae (talk) 03:23, 11 December 2024 (UTC)
Support. AI generated text should be removed outright. If you aren't willing to put the work into doing your own writing then you definitely haven't actually thought deeply about the matter at hand. User1042💬✒️14:16, 11 December 2024 (UTC)
This comment is rather ironic given that it's very clear you haven't thought deeply about the matter at hand, because if you had then you'd realise that it's actually a whole lot more complicated than that. Thryduulf (talk) 14:26, 11 December 2024 (UTC)
Thryduulf I don't think this reply is particular helpful, and it comes off as slightly combative. It's also by my count your 24th comment on this RFC. BugGhost🦗👻19:20, 11 December 2024 (UTC)
I recognize that AI paraphrased or edited is not problematic in the same ways as text generated outright by an AI. I only meant to address the core issue at steak, content whose first draft was written by an AI system. User1042💬✒️22:16, 17 December 2024 (UTC)
I've recently come across several users in AFD discussions that are using LLMs to generate their remarks there. As many of you are aware, gptzero and other such tools are very good at detecting this. I don't feel like any of us signed up for participating in discussions where some of the users are not using their own words but rather letting technology do it for them. Discussions are supposed to be between human editors. If you can't make a coherent argument on your own, you are not competent to be participating in the discussion. I would therefore propose that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner
Support with the caveat that our ability to deal with the issue goes only as far as we can accurately identify the issue (this appears to have been an issue raised across a number of the previous comments, both support and oppose, but I think it bears restating because we're approaching this from a number of different angles and its IMO the most important point regardless of what conclusions you draw from it). Horse Eye's Back (talk) 19:24, 11 December 2024 (UTC)
Strong support, limited implementation. Misplaced Pages is written by volunteer editors, says our front page. This is who we are, and our writing is what Misplaced Pages is. It's true that LLM-created text can be difficult to identify, so this may be a bit of a moving target, and we should be conservative in what we remove—but I'm sure at this point we've all run across cases (whether here or elsewhere in our digital lives) where someone copy/pastes some text that includes "Is there anything else I can help you with?" at the end, or other blatant tells. This content should be deleted without hesitation. Retswerb (talk) 04:11, 12 December 2024 (UTC)
Support in concept, questions over implementation — I concur with Dronebogus that users who rely on LLMs should not edit English Misplaced Pages. It is not a significant barrier for users to use other means of communication, including online translators, rather than artificial intelligence. How can an artificial intelligence tool argue properly? However, I question how this will work in practice without an unacceptable degree of error. elijahpepe@wikipedia (he/him) 22:39, 12 December 2024 (UTC)
Well since people keep bringing this up as a semi-strawman: no I don’t support banning machine translation, not that I encourage using it (once again, if you aren’t competent in English please don’t edit here) Dronebogus (talk) 07:34, 13 December 2024 (UTC)
LLMs are incredible at translating, and many online translators already incorporate them, including Google Translate. Accomodating LLMs is an easy way to support the avid not only the ESL but also the avid but shy. It has way more benefits than the unseen-to-me amount of AI trolling that isn't already collapse-on-sight. Aaron Liu (talk) 00:05, 13 December 2024 (UTC)
Google Translate uses the same transformer architecture that LLMs are built around, and uses e.g. PaLM to develop more language support (through training that enables zero-shot capabilities) and for larger-scale specialized translation tasks performed through the Google Cloud "adaptive translation" API, but it does not incorporate LLMs into translating your everyday text input, which still relies on NMTs. And even for the API features, the core constraint of matching input rather than generating content is still retained (obviously it would be very bad for a translation tool to insert material not found in the original text!). LLMs might be good for translation because they are better at evaluating semantic meaning and detecting context and nuance, but again, the generative part that is key to this proposal is not present. JoelleJay (talk) 01:20, 13 December 2024 (UTC)
PaLM (Pathways Language Model) is a 540 billion-parameter transformer-based large language model (LLM) developed by Google AI. If you meant something about how reschlmunking the outputs of an LLM or using quite similar architecture is not really incorporating the LLM, I believe we would be approaching Ship of Theseus levels of recombination, to which my answer is it is the same ship.
obviously it would be very bad for a translation tool to insert material not found in the original text!
PaLM2 is not used in the consumer app (Google Translate), it's used for research. Google Translate just uses non-generative NMTs to map input to its closes cognate in the target language. JoelleJay (talk) 01:34, 13 December 2024 (UTC)
Well, is the NMT really that different enough to not be classified as an LLM? IIRC the definition of an LLM is something that outputs by predicting one-by-one what the next word/"token" should be, and an LLM I asked agreed that NMTs satisfy the definition of a generative LLM, though I think you're the expert here. Aaron Liu (talk) 02:01, 13 December 2024 (UTC)
Google Translate's NMT hits different enough to speak English much less naturally than ChatGPT 4o. I don't consider it a LLM, because the param count is 380M not 1.8T.
the definition of an LLM is something that outputs by predicting one-by-one what the next word/"token" should be No, that def would fit ancient RNN tech too. 172.97.141.219 (talk) 17:50, 13 December 2024 (UTC)
Even if you don’t consider it L, I do, and many sources cited by the article do. Since we’ll have such contesting during enforcement, it’s better to find a way that precludes such controversy. Aaron Liu (talk) 20:44, 13 December 2024 (UTC)
NMTs, LLMs, and the text-creation functionality of LLMs are fundamentally different in the context of this discussion, which is about content generated through generative AI. NMTs specifically for translation: they are trained on parallel corpora and their output is optimized to match the input as precisely as possible, not to create novel text. LLMs have different training, including way more massive corpora, and were designed specifically to create novel text. One of the applications of LLMs may be translation (though currently it's too computationally intensive to run them for standard consumer purposes), by virtue of their being very good at determining semantic meaning, but even if/when they do become mainstream translation tools what they'll be used for is still not generative when it comes to translation output. JoelleJay (talk) 22:29, 13 December 2024 (UTC)
The proposal is for hatting obvious cases of LLM-generated comments. Someone who just uses an LLM to copyedit will still have written the content themselves and presumably their output would not have the obvious tells of generative AI. JoelleJay (talk) 23:56, 13 December 2024 (UTC)
Not when I tried to use it. Quantitatively, GPTZero went from 15% human to 100% AI for me despite the copyedits only changing 14 words. Aaron Liu (talk) 00:33, 14 December 2024 (UTC)
Does it really mean that? All you've demonstrated is that GPTZero has false positives, which is exactly why its use here was discouraged. jlwoodwa (talk) 05:26, 14 December 2024 (UTC)
My subjective evaluation of what I got copyediting from ChatGPT was that it sounded like ChatGPT. I used GPTZero to get a number. Aaron Liu (talk) 14:18, 14 December 2024 (UTC)
It changed only 14 words across two paragraphs and still retained the same meaning in a way that I would describe it as copyediting. Such levels of change are what those lacking confidence in tone would probably seek anyways. Aaron Liu (talk) 00:15, 24 December 2024 (UTC)
On one hand, AI slop is a plague on humanity and obvious LLM output should definitely be disregarded when evaluating consensus. On the other hand, I feel like existing policy covers this just fine, and any experienced closer will lend greater weight to actual policy-based arguments, and discount anything that is just parroting jargon. WindTemposthey23:21, 12 December 2024 (UTC)
Support in principle, but we cannot rely on any specific tools because none are accurate enough for our needs. Whenever I see a blatant ChatGPT-generated !vote, I ignore it. They're invariably poorly reasoned and based on surface-level concepts rather than anything specific to the issue being discussed. If someone is using AI to create their arguments for them, it means they have no actual argument besides WP:ILIKEIT and are looking for arguments that support their desired result rather than coming up with a result based on the merits. Also, toasters do not get to have an opinion. The Wordsmith05:17, 13 December 2024 (UTC)
Oppose. For creating unnecessary drama. First of, the "detector" of the AI bot is not reliable, or at least the reliability of the tool itself is still questionable. If the tool to detect LLM itself is unreliable, how can one reliably point out which one is LLM and which one is not? We got multiple tools that claimed to be able to detect LLM as well. Which one should we trust? Should we be elevating one tool over the others? Have there been any research that showed that the "picked" tool is the most reliable? Second, not all LLMs are dangerous. We shouldn't treat LLM as a virus that will somehow take over the Internet or something. Some editors use LLM to smooth out their grammar and sentences and fix up errors, and there is nothing wrong with that. I understand that banning obvious LLM text per WP:DUCK are good, but totally banning them is plain wrong. ✠ SunDawn ✠(contact)22:56, 15 December 2024 (UTC)
@SunDawn, the proposal is to permit editors to collapse/strike obvious LLM text, not to "ban LLM totally". If LLM use is imperceptible, like for tweaking grammar, it's not going to be affected. JoelleJay (talk) 20:17, 19 December 2024 (UTC)
Support with some kind of caveat about not relying on faulty tools or presuming that something is LLM without evidence or admission, based on the following reasons:
We have stricter rules around semi-automated editing (rollback, AutoWikiBrowser, etc.) and even stricter rules around fully automated bot editing. These cleanup edits are widely accepted as positive, but there is still the concern about an overwhelming amount of bad edits to wade through and/or fix. A form of that concern is relevant here. Someone could reply to every post in this discussion in just a minute or so without ever reading anything. That's inherently disruptive.
Nobody who is voting "oppose" is using an LLM to cast that vote. The LLM comments have been left by those supporting to make a point about how problematic they are for discussions like this. I think this reflects, even among oppose voters, a developing community consensus that LLM comments will be disregarded.
If the rule in practice is to disregard LLM comments, not writing that rule down does not stop it from being the rule, consensus, or a community norm. It just makes the rule less obvious and less clear.
It's disrespectful for an editor to ask someone to spend their time reading a comment if they couldn't be bothered to spend any time writing it, and therefore a violation of the policy Misplaced Pages:Civility, "treat your fellow editors as respected colleagues with whom you are working on an important project."
I am strongly opposed to banning or ignoring LLM-made talk page comments just because they are LLM-made. I'm not a big fan of LLMs at all; they are actually useful only for some certain things, very few of which are directly relevant to contributing to Misplaced Pages in English or in any other language. However, some of those things are useful for this, at least for some humans, and I don't want to see these humans being kicked out of the English Misplaced Pages. I already witnessed several cases in which people whose first language is not English tried writing talk page responses in the English Misplaced Pages, used an LLM to improve their writing style, and got their responses ignored only because they used an LLM. In all those cases, I had strong reasons to be certain that they were real humans, that they meant what they wrote, and that they did it all in good faith. Please don't say that anyone who wants to contribute to the English Wikipeida should, in the first place, know English well enough to write a coherent talk page comment without LLM assistance; occasionally, I kind of wish that it was like that myself, but then I recall that the world is more complicated and interesting than that. Uses of LLMs that help the English Misplaced Pages be more inclusive for good-faith people are good. Of course, defining what good faith means is complicated, but using an LLM is not, by itself, a sign of bad faith. --Amir E. Aharoni (talk) 04:52, 19 December 2024 (UTC)
Those concerned about their English should use translation software rather than an llm. Both might alter the meaning to some extent, but only one will make things up. (It's also not a sure assumption that llm text is coherent talkpage text.) CMD (talk) 07:44, 19 December 2024 (UTC)
@CMD The dividing line between translation software and LLM is already blurry and will soon disappear. It's also rare that translation software results in coherent talkpage text, unless it's relying on some (primitive) form of LLM. So if we're going to outlaw LLMs, we would need to outlaw any form of translation software, and possibly any text-to-speech software as well. ypn^223:41, 19 December 2024 (UTC)
The distinctions have already been covered above, and no we would not have to. There is an obvious difference between software intended to translate and software intended to generate novel text, and users are likely to continue to treat those differently. CMD (talk) 02:49, 20 December 2024 (UTC)
Strong oppose to the proposal as written. Misplaced Pages already suffers from being stuck in a 2001mindset and a refusal to move with the technological times. Anyone who remembers most Wikipedians' visceral reaction to FLOW and VisualEditor when they were first introduced will observe a striking similarity. Yes, those projects had serious problems, as do LLM-generated comments. But AI is the future, and this attitude of "Move slowly to avoid changing things" will ultimately lead Misplaced Pages the way of Encyclopædia Britannica. Our discussion needs to be how best to change, not how to avoid to change. ypn^223:54, 19 December 2024 (UTC)
The main objection to VE and a major objection to FLOW was the developers' insistence on transforming Wikitext to HTML for editing and then transforming that back to Wikitext. Aaron Liu (talk) 01:31, 20 December 2024 (UTC)
True. Then, as now, there were many valid objections. But IIRC, there was limited discussion of "Let's figure out a better way to improve", and lots of "Everything is fine; don't change anything, ever." That attitude concerns me. ypn^201:52, 20 December 2024 (UTC)
I oppose the proposal but I think the comparison to FLOW and VisualEditor is beyond silly. Those things did not exist outside of a MediaWiki context. LLMs are a global issue. Gnomingstuff (talk) 17:11, 28 December 2024 (UTC)
Support. I'm not even slightly swayed by these "it'll be too hard to figure out" and "mistakes could be made" and "we can't be 100% certain" sorts of arguments. That's true of everything around here, and its why we have an admins-must-earn-a-boatload-of-community-trust system, and a system of review/appeal of decisions they (or of course non-admin closers) make, and a consensus-based decisionmaking system more broadly. JoelleJay has it exactly right: having a policy that permits closers to discount apparently-LLM-generated contributions will discourage good-faith editors from using LLMs irresponsibly and perhaps motivate bad-faith editors to edit the raw output to appear more human, which would at least involve some degree of effort and engagement with their "own" arguments. And as pointed out by some others, the "it'll hurt non-native-English speakers" nonsense is, well, nonsense; translation is a different and unrelated process (though LLMs can perform it to some extent), of remapping one's own material onto another language.
I'm also not in any way convinved by the "people poor at writing and other cognitive tasks needs the LLM to help them here" angle, because WP:COMPETENCE is required. This is work (albeit volunteer work), it is WP:NOT a game, a social-media playground, a get-my-ideas-out-there soapbox, or a place to learn how to interact e-socially or pick up remedial writing skills, nor a venue for practicing one's argument techiques. It's an encyclopedia, being built by people who – to be productive contributors instead of a draining burden on the entire community – must have: solid reasoning habits, great judgement (especially in assessing reliability of claims and the sources making them), excellent writing skills of a highly particularized sort, a high level of fluency in this specific language (in multiple registers), and a human-judgement ability to understand our thick web of policies, guidelines, procedures, and often unwritten norms, and how they all interact, in a specific contextual way that may vary greatly by context. None of these is optional. An LLM cannot do any of them adequately (not even write well; their material sticks out like a sore thumb, and after a while you can even tell which LLM produced the material by its habitual but dinstictive crappy approach to simulating human thought and language).
In short, if you need an LLM to give what you think is meaningful input into a decision-making process on Misplaced Pages (much less to generate mainspace content for the public), then you need to go find something else to do, something that fits your skills and abilities. Saying this so plainly will probably upset someone, but so it goes. I have a rep for "not suffering fools lightly" and "being annoying but correct"; I can live with that if it gets the right decisions made and the work advanced. — SMcCandlish☏¢ 😼 05:49, 22 December 2024 (UTC)
PS, something that came up more recently than my original post above: If anyone's wondering why some of us are such "AI" skeptics, its because the technology is badly, badly faulty, producing multiple blatant factual errors even in short material, entirely fictive "hallucinations", direct forgery of sourcing, nested chains of error compounded upon error when context isn't gleaned properly, disingenuous attempts to hide that it is lying, and worse. A few days ago, I got ChatGPT 4o to literally lose its f#*$ing mind: I had it generate some short code (very simple one-liner regex) with a really obvious error, so I pointed out the error and gave it documentation that proved it was an error. It conceded the error and even explained what the error was and why it was erroneous, then said how it was going to fix it. And ... proceeded to output the same error again (in just one of three examples, the other two being correct). Fascinated and horrified by this, I tried for over half an hour to get it to produce a correct example, and it was utterly incapable of doing it. It knew the error was an error and what that error was and why, spelled out what the correct approach should be, then repeated the error every single time (always at the first occurrence, or always if the only occurrence). I've captured that session and will be doing a write-up about it. This is much, much worse that a "hallucination", being an abject inability to stop doing what it already knows is absolutely wrong. When people have fears like "If I had a house AI, and it was in control of the bathwater temperature, it might boil my children alive", they are not paranoid or unreasonable. My experiment with ChatGPT proves this conclusively. If the AI can (with trivial effort) be put into a crazy failure-looping state where it knows it's doing or about to do something wrong but insists on doing it anyway – i.e. during its take-an-action phase it completely loses connection to reality, even it's internal reality much less external input telling it "no!" – then we are in grave danger. This is essentially the mental state of a psychopath: "I know I shouldn't grab my neighbor's little daughter and strangle her to death, but I just can't stop myself." — SMcCandlish☏¢ 😼 01:42, 28 December 2024 (UTC)
The problem with all that is that we already have a policy that allows the hatting or removal of comments that are actually problematic because of their content (which are the only ones that we should be removing) without regard for whether it was or was not written by LLM. Everything that actually should be removed can be removed already. Thryduulf (talk) 11:39, 22 December 2024 (UTC)
If that's "the problem with all that", then it is not any kind of problem at all. It's entirely normal in our WP:P&G material to reiterate a principle defined in one place for contextual application at another, and to extrapolate from a general principle to a more specific application. We do this often to cut through the exact kind of wikilawyering we're facing over this issue: there's not a specific rule against LLM-generated !voting, so the argument is (again and again in this thread) to permit it (unless it's such senseless gibberish that it would be removed anyway even if no LLM were involved). The community clearly doesn't actually want that result (or more accurately, there is not a consensus in favor of it), though this specific proposal's approach to thwarting the "AI"-spamming of our decision-making processes might not be perfect. To me, it's a step in the right direction. If it were implemented this way and some uncommon issue arose with that implementation, then we'd tweak it to address that micro-problem. We must not continue to avoid addressing the macro-problem just because someone can imagine edge cases that might not work out ideally. That, too, is true of all of our P&G and process. — SMcCandlish☏¢ 😼 01:15, 28 December 2024 (UTC)
People who have good reading skills, great judgement, and solid reasoning habits enough to find problems in existing articles don't necessarily have great interpersonal writing/communication skills or the confidence. Meanwhile, for all LLM is bad at, it is very good at diluting everything you say to become dry, dispassionate, and thus inoffensive. Aaron Liu (talk) 15:26, 22 December 2024 (UTC)
I doubt that anyone would seriously object to some ultra-hothead running their post through an LLM with a query like "Can you see anything in this that might come off as aggressive or offensive, and suggest a revision that only affects that aspect of the material?" The result might not even be noticeable as LLM-modified. If it doesn't stick out as LLM garbage, there there is no way for this proposal to affect such a post, because no one here is a mind-reader (we cannot magically detect through remote sensing that someone toned their rant down with LLM help). So, this proposal is not broken (at least not with regard to that scenario). That said, the main reason that WP:COMPETENCE was written (and it's one of the essays that, like WP:BRD and WP:AADD, has become "operative" within the community as if a policy or guideline) is the very "don't necessarily have great interpersonal ... skills" issue you mention. That is, lacking those skills to a serious enough degree makes one not competent to work on a collaborative encyclopedia project, and one will eventually be ejected after causing enough disruption. Something we don't need is LLMs masking for a while that someone has this kind of competence failure; it will just drag out the inevitable. By way of analogy: if I were a kleptomaniac and just unable to stop myself from shoplifting, it would not be okay for me to use a device that scrambled stores' surveillance camera footage to make it more likely for me to get away with more shoplifting (and there would certainly be no obligation on the part of the store owner to turn their cameras off, or to take no action if they catch me stealing, just because I tell them I'm a kleptomaniac and my unconstructive behavior isn't something I can manage. — SMcCandlish☏¢ 😼 01:15, 28 December 2024 (UTC)
People who can't communicate that well often won't attempt to burn others down. I don't think there's any disruption or substantial additional investment in accommodating those who won't burn others down (which I'd say is the majority) by reading their perfectly comprehensible AI-diluted arguments. (Scrambling footage is like erasing the memories of the incident, which I don't think is a good analogue of the issue at hand. I'd say it's more like working with someone who stinks and masks that with perfume.) Aaron Liu (talk) 00:05, 29 December 2024 (UTC)
I'm pretty sure most people here understand why there are AI skeptics. I also hate ChatGPT. But there's a difference between my personal opinion of ChatGPT and the fact that someone using ChatGPT to communicate is still communicating. The risk of your house AI hallucinating is that your children get boiled alive. The risk of ChatGPT hallucinating on a talk page is that they make a dumb, disregardable argument, of the kind that humans pump out by the thousands. (Someone linked an example of some AfD delete !votes generated by AI and frankly they're better reasoned than a lot of the stuff humans post.) Gnomingstuff (talk) 17:32, 28 December 2024 (UTC)
(The bigger issue is people using Misplaced Pages as ChatGPT -- i.e. posting the prompts, not the responses -- but, like much of what is being discussed here, that is already stuff that can be removed.) Gnomingstuff (talk) 17:36, 28 December 2024 (UTC)
Support. Sure I have questions about detection, but I don't think it means we shouldn't have a policy that explicitly states that it should not be used (and can be ignored/hatted if it is). Judging solely based on content (and no wp:bludgeoning, etc.) is unsustainable IMO. It would mean taking every wall of text seriously until it's clear that the content is unhelpful, and LLMs are very good at churning out plausible-sounding bullshit. It wastes everyone's time. If cognitive impairments or ESL issues make it hard to contribute, try voice-to-text, old-school translation software, or some other aid. LLMs aren't really you.--MattMauler (talk) 11:27, 23 December 2024 (UTC)
Comment. While I agree with the sentiment of the request, I am at a loss to see how we can identify LLM generated comments in a consistent manner that can scale. Yes, it might be easier to identify egregious copy paste of wall of text, but, anything other than that might be hard to detect. Our options are:
Robust tooling to detect LLM generated text, with acceptably low levels of false positives. Somewhat similar to what Earwig does for Copyvios. But, someone needs to build it and host it on WMTools or at a similar location.
Self certification by editors. Every edit / publish dialogbox should have a checkbox for "Is this text LLM generated" with y/n optionality.
Editors playing a vigilante role in reading the text and making a personal call on other editors' text. Obviously this is least preferred.
A couple of days ago, an editor ran a new article through GPTzero, and was told that it was 99.8% likely to be AI-generated. I ran the same revision of the same article through the same tool the next day, and it told me that it was 98.3% likely to be human-written.
Bonus suggestion!: I'm curious what Wikipedians think about this so let's try this. Many of the comments here discuss the impracticality of determining whether a user's comments are AI generated (i.e. gptzero isn't perfect), and many give valid arguments for using LLMs (i.e. ESL). If an argument is suspected to be written by LLM, I propose that editors should examine the user. Take a look at their listed contributions, and if they seem to have a habit of using AI, open a discussion on their talk page. If the user has a habit of using AI and doesn't recognize the inherent problems and refuses to change, this can be brought to the administrators' noticeboard for potential blocks. If (and only if) the person is blocked for using AI, their comments can be ignored. Or just ask ChatGPT to summarize them for you lol guninvalid (talk) 06:12, 25 December 2024 (UTC)
I think that the general idea here is good: As much as possible, treat each account individually, and handle LLM use as a behavioral problem when it's actually a practical problem (i.e., not when it seems to be accurate and seems to be appropriate). WhatamIdoing (talk) 04:38, 26 December 2024 (UTC)
Except a substantial portion of the input in this thread is disagreement with the idea that English being someone's second language is an excuse for LLM-generated content at all. Translation of one's own material is an entirely different process (even if often leveraged by LLMs set to a different task than trying to generate what they "think" is new material that will pass as human-authored). I'm skeptical that any of the other things you're accepted as "valid arguments" from the pro-LLM or LLM-accepting side of this debate have consensus as valid, either. But go ahead and spell them out and we'll see. — SMcCandlish☏¢ 😼 01:30, 28 December 2024 (UTC)
Strong support the removal of any obvious, low effort AI-generated post. I recently came across a user postingmultiple such examples. When called out on it they blew up and posted a comment saying, amongst other things "HAHAHAHHAHAHAHAHAHAHHAHAHAHAHAHA. Yes, some of it might be. Because I don't have time to argue with, in my humble opinion, stupid PHOQUING people." and "YOUUUUUUUUUUUUUUUUUUUUUUUUUUUU are assuming bath faith in me."
They were later blocked as a sock evading a global lock.
Currently it is too easy for trolls to game WP:AGF and AI to waste people's time arguing with their bot-generated replies. Using AI to write your posts for you makes it difficult for others to assume good faith. I am ok with obvious exceptions like a non-native speaker using AI to help them articulate their point. Photos of Japan (talk) 21:29, 25 December 2024 (UTC)
Support for now. I believe the foundation should be busy ramping up support in this arena of distraction. IMHO, we are in the calibration phase of the use of these models. We don't feed trolls and we shouldn't tutor LLMs. Since assumption of good faith is not suicide pact, we shouldn't rely overmuch for guidance on edge cases. The issues as I see them are attribution (how do I know where your idea has been?), obedience to social norms (I not-here blocked someone recently for brazenly using ChatGPT to lie about using LLMs; the user proceeded to use GPT to post unblock requests), and a vast canyon between the limited human and financial resources of the foundation and the unlimited resources of bad actors with vast sums of money who would like to see Misplaced Pages less able. I have hopes we can get some higher visibility anti-LLM support (like a flag in my mouseover which always reports a percentage, so I know to check). This fire is burning now. It would be unwise to ignore this much longer. BusterD (talk) 16:28, 29 December 2024 (UTC)
Support with the clarification that use of AI assistance is not prohibited, as long as its contribution is <<50%. For example, using Grammarly for spell check and grammar/syntax is OK, but using AI to do your homework is not. Dhaluza (talk) 02:45, 30 December 2024 (UTC)
Support a ban on comments that were primarily generated by AI, with such comments to be deleted or struck-through as appropriate, because it's inherently misleading to pass off a chatbot's words as your own. Using ML-based spell-checkers is fine. I've seen some users call ChatGPT an "accessibility tool", but if you're not capable of communicating on English Misplaced Pages without a LLM doing it for you, then I don't think English Misplaced Pages is a good community for you to participate in. — Preceding unsigned comment added by Pythoncoder (talk • contribs) 21:45, 31 December 2024 (UTC)
Just read this ANI thread, where an editor was indeffed per WP:NOTHERE after exclusively using LLMs to edit, even when responding within that very thread. The situation was a clear case of WP:CIR, which I surely would've cited in my original comment had the page name come to mind. —pythoncoder (talk | contribs) 04:34, 3 January 2025 (UTC)
That they were banned for CIR shows we don't need anything new to deal with disruption specifically caused by people using LLMs. Thryduulf (talk) 05:29, 3 January 2025 (UTC)
Support A popular notion in many, many other discussions is "our most valuable resource is editor time". This applies here more than in most instances - editors cannot be expected to wear themselves out in engaging at length with the results of someone's one-line prompt to an LLM. Where LLM use in articles is destructive of content and source reliability, in discussions it is destructive of editor good faith. If you can't be bothered to put your arguments into intelligible form, don't participate. If your language capacity is lacking to the extent that you have to have a program generate (as opposed to polish) your stuff, you probably don't have any business participating either. Human detection ability seems quite sufficient for these cases (and once it ceases to, well, we'll deal with that when it becomes an issue). --Elmidae (talk · contribs) 12:00, 2 January 2025 (UTC)
Human detection ability seems quite sufficient for these case these discussions have already proven that human detection is not reliable, with human-generated comments labelled as AI and AI-generated comments labelled as human. Why should we prohibit LLM-generated content that is accurate, relevant and intelligible? We can already ignore/remove content that is none of those things regardless of whether it is LLM-generated or not. Thryduulf (talk) 12:21, 2 January 2025 (UTC)
If you want a pithy in-a-nutshell: personal effort is buy-in in a discussion among equals. If your personal effort in a discussion is an LLM prompt, no editor should be expected to engage with you. --Elmidae (talk · contribs) 12:42, 2 January 2025 (UTC)
What matters is whether people are engaging with each other constructively and in good faith. Whether one or both parties is using an LLM is completely irrelevant to both aspects. Thryduulf (talk) 13:29, 2 January 2025 (UTC)
Nobody is forcing you to engage with anybody or anything you don't want to engage with, but you do not get to state who other people are allowed to choose to engage with. As long as someone is engaging constructively and in good faith I don't care whether they are human or machine, because (a) I have no reliable way of knowing, and (b) it is literally irrelevant to me. Thryduulf (talk) 14:14, 2 January 2025 (UTC)
you do not get to state who other people are allowed to choose to engage with Strawman, since I didn't do that. Only you are doing that. Selfstudier (talk) 14:26, 2 January 2025 (UTC)
Quite the contrary - you are saying that nobody should be allowed to engage with someone using an LLM because you do not want to engage with someone using an LLM. My position is that everybody should be allowed to choose who they want and do not want to engage with for themselves. Thryduulf (talk) 14:42, 2 January 2025 (UTC)
Support in principle - Using entirely AI-generated text in discussion is not a valuable contribution, since ultimately it is not capable of thought, but there should be leniency for those who are simply using AI to improve something they already wrote. FOARP (talk) 14:55, 2 January 2025 (UTC)
Support in principle We don't want LLMs opinions. IF and WHEN we do we'll ask for an extension with some AI making an openig analysis of nominations. But we can not, and want not, to excludes cases where some user forms their opinion chating with some AI, as it was brillianttely shoen above, nor we want to exclude anyone lee proficient with the language just "because it looks like a bot". - Nabla (talk) 18:13, 2 January 2025 (UTC)
Support in principle, strongly concerned in potential practice - I like the idea of removing what is verifiably generated by a LLM. On the other hand, I've read that autistic writers may be more likely to have their (completely non-AI) writing flagged as potential AI use by automated detectors. I think it could be a problem if a rule that's good in principle could start disproportionately affecting some editors (who are not doing the thing) more than others (who are not doing the thing) in practice, whether that come from human (i.e. other editor) bias or automated tools. - Purplewowies (talk) 18:36, 3 January 2025 (UTC)
Strongly support per ChatGPT (EEng) and SMcC; I'm not at all concerned about edit accessibility to non-native speakers; WP:COMPETENCE, after all, is required to contribute to this project. I also oppose any breaking of the line against AI-generated plausible-sounding and -looking slop. We can't have a Misplaced Pages of LLMs talking to LLMs on how to make LLM content for LLM articles. Iseulttalk to me21:53, 4 January 2025 (UTC)
Support per SMcCandlish. If someone needs to use a LLM to be able to contribute and is unable to convert the output into something that is not obviously AI-generated, then WP:CIR likely applies. It'll be impossible to stop minimal usage cases, but having such a rule in place would at least encourage editors to review their output and stop the unhelpful posting off entire ChatGPT essays to discussion spaces. -- Patar knight - /contributions01:41, 6 January 2025 (UTC)
Strong... opinion -- I think the nuance required here in part is the difference between someone using any automated tool for assistance, versus true bot-like behavior. I believe that unauthorized bot behavior is already prohibited, which should help address the concerns that we mere humans cannot keep up with LLM bots. I agree, we cannot, but I don't see much of that. I am also not inclined to the "if you cannot write, you cannot contribute"... I can imagine 15 years ago some of us might have made the same statement about spelling and grammar; if you cannot spell properly without auto-correct you have no right to edit an encycolopedia. The are significant number of very intentilligent people who are afflicted with things like dyslexia, aspurgers, etc. who have been contributing using various technology tools for assistance. How may of us have Grammarly or similar running on their web browser? And beyond that tools and what they're called will continue to evolve. I am very much against just banning LLM use; largely because it can turn into an unnecessary witch hunt. There are people who will use the tools constructively, and those who will not. I can see some places where it should probably be banned (such as using a LLM to determine consensus on a discussion that needs closing (AfD, RM, etc)). But even in those areas, I think many of our existing policies and guidelines already address most of the actual concerns we're seeing when it comes to that activity. Cheifly that as long as people are being held accountable for how they use the tools, then who cares what the tool is called in 2000, 2020 or 2040? So I think the course forward is best served by (1) Consider refinement to WP:BOTP so that we're encapsulating LLM type bot behavior, as well as some sort of threshold on "non-human" capable editing limits (perhaps as part of WP:MEATBOT; (2) make a policy or guidelines very clear, bright line, that a user will be treated the same regardless of what tools they use, LLM or otherwise, and that disruptive editing will be handled accordingly. (2a) perhaps a single-warning template reflective of such, to welcome people who appear to be using LLM, and that they are responsible for their adherence to policy and that LLMs tend to get policy wrong. TiggerJay(talk)02:48, 7 January 2025 (UTC)
The proposal is focused on comments that are obviously generated by LLM, which would not include non-generative AI processes like Grammarly or translation. The whole issue is arguments that were clearly created by a chatbot etc. doing its own analysis of a discussion and an editor just pasting that output rather than forming the argument themselves, which results in large amounts of text that other editors/closers then have to read and respond to. JoelleJay (talk) 22:26, 7 January 2025 (UTC)
To be honest, that's my concern. What if something seems obviously generated by LLM but is entirely human-written? What if certain groups of editors are more likely to produce seemingly LLM text that isn't generated by any LLM at all? Is there a way to control for that? How do we consistently enforce this kind of thing without too many false positives or false negatives?
Replying to the top-level opinion at this point: Most autistic people who would have in the past received an Asperger's diagnosis, barring some other reason, would IMO not be more likely to "need" more assistive technology (LLM or otherwise) to contribute to Misplaced Pages articles and discussions than any other user. However, there have been reports that autistic people may be more likely to produce text that is falsely positive in AI detection tools. See this story about a Purdue professor as one example (I had a second example, I thought, except that I've apparently read my last free article on that site (I bet I read said last article when looking up the same article when I wrote my !vote a few days back, Facepalm). Not gonna link what I can't (quickly) verify!)) (As an aside, I think "afflicted with" can come across as a bit... charged? Just something to note.)
The mention of Data in particular only heightens my concern because--while no one has accused me yet of using LLM when I write--I have (on other sites, not here) been accused of being a bot before because of the style of writing I adopt at times. What if editor bias disproportionately plays into who is suspected of LLM use and who isn't? What if imperfections in automated AI detection only serve to cement the bias? - Purplewowies (talk) 01:25, 8 January 2025 (UTC)
These questions around controlling for false positives and false negatives are not new, we face them all the time already, for example distinguishing vandalism from good faith contributions. We work through them, but they don't mean we don't have a policy on vandalism. CMD (talk) 01:41, 8 January 2025 (UTC)
Indeed, that's why my original !vote is (in short) "support but concerned". I definitely think I'd support a policy; I'm just raising questions/concerns I think are worth considering in the process of creating such a policy. I think some part of me is just remembering times I've seen bias negatively affect the project in the past and that part of me is coming out here trying to prevent another situation like that by laying the concerns out. I dunno. - Purplewowies (talk) 03:59, 8 January 2025 (UTC)
I think Joelle what you're overlooking in that statement is that obviously generated is something that is going to be short lived, meaning that it will not be very long before the LLM generated content will be far harder to distinguish. Just like how just a year ago any generative image AI would often get the number and/or placement of fingers wrong on a person's hand, in less than a years time that appears to generally be solved. Today the tell tail signs is even if you ask for someone who is left handed, you'll almost always get an image of a right handed person... But that too will go away shortly. I believe it is (scarily) not too far off, when LLMs can determine the prompt is for Misplaced Pages (by way of seeing the wikimarkup or references to normal wiki policies), and among other things, write in the style of experienced editors, perhaps modeled off of some of us in this very discussion. That will be much more difficult to tell, especially when it learns how to not be soo overly polite and apologetic. Beyond that, I believe there are a lot of people successfully and positively using LLMs already on WP. For those reasons, I proffer that we focus on refining the definitions and parameters for general disruptive editing (such as EW, RRR, etc), what a bot edit/activity is, and perhaps a standardized "friendly welcome" and "friendly notice" for those suspected of using LLMs, and reinforce that the tool matters less than the behavior. I think the analogy I'm going for is that of how we handle socks -- it is not against policy to have multiple accounts, however, when it is disruptive, it is blatantly prohibited. But the signs and symptoms of socks is really what we care about. TiggerJay(talk)05:02, 8 January 2025 (UTC)
Something can be prohibited even if it is or will be difficult to identify it. Just because we can anticipate AI-generated slop becoming harder to detect doesn't mean it's not still disruptive or that we shouldn't be able to strike it when it is obvious. JoelleJay (talk) 23:41, 9 January 2025 (UTC)
Strong support for striking AI-generated comments. Detection of course will be up to admin discretion, but so is things like incivility and personal attacks; while short snippets of AI generated text are hard to detect, lengthy paragraphs are quite easy to eyeball, and from my experience that's the area where it's most likely to come up and most immediately disruptive. Generalissima (talk) (it/she) 22:25, 9 January 2025 (UTC)
Supportfor striking AI-generated comments. Detection of course will be up to admin discretion as are other behavioural preoblems. Having read most of the discussion, and having been astonished by the 'individuality' of some machine-generated content, nonetheless, while detection may be less-than-foolproof, I still think we should make the point that such content isn't acceptable. It should be within our capacity to make the distinction between 'machine-generated' content and the use of software to correct grammar or to translate, neither of which should be directly outlawed.Pincrete (talk) 07:18, 10 January 2025 (UTC)
But why should such content be deemed unacceptbale when there are no problems with it? When there are problems with it, it can and should be dealt with in the same way that those problems are dealt with when written by humans. Thryduulf (talk) 18:25, 10 January 2025 (UTC)
Request for closure
IMHO, since we're over 30 days and the argument consensus seems lopsided, the community would do well to close this rapidly (as opposed to waiting for additional comments). BusterD (talk) 21:04, 2 January 2025 (UTC)
Sure it looks lopsided if you only read what has been bolded. When you look beyond at what those bolding support are actually supporting it's not at all clear there is a consensus. Then when you actually look at the arguments made it seems that there is not actually a consensus for anything other more than "some users vocally dislike AI". Thryduulf (talk) 21:59, 2 January 2025 (UTC)
I was merely pointing out that BusterD's stated reason for calling for closure now is incorrect. That doesn't mean closing now would necessarily be wrong, just that overwhelming consensus is not a reason for it. Thryduulf (talk) 22:25, 2 January 2025 (UTC)
As a sysop, reacting to LLM-related abuse is virtually all I've done in the last week or so. We have a pressing need for some help from the community, and while I'm open to discussion on this, it's unreasonable to expect humans to keep up with bot-like behavior. I've made my argument above, and I'll not disagree further here. BusterD (talk) 00:08, 3 January 2025 (UTC)
Many on the “support” side are also supporting with conditions instead of an unconditional support. For instance, many have suggested that LLM that supported grammars are okay.
There are multiple breaks and 391 comments now. At this scale, it becomes difficult for a human to digest and summarise it all. AI technology seems well suited to this and so asked Gemini again "Please summarise the consensus of the following RFC:" giving it all the discussion above. Its response was much as before:
The RFC on LLM/chatbot comments in discussions is contentious, with a significant number of editors on both sides of the issue.
Support
Many editors support the proposal to discount or remove LLM-generated comments in discussions. Their arguments include:
LLMs do not have original thoughts or arguments and therefore do not contribute meaningfully to discussions.
LLM-generated comments can be disruptive, wasting editors' time and derailing discussions.
LLMs can be used by bad-faith actors to manipulate consensus or spread misinformation.
Editors should be encouraged to participate in discussions using their own words and thoughts.
Oppose
Other editors oppose the proposal, arguing that:
LLMs can be useful tools for editors who have difficulty expressing themselves in English, such as non-native speakers or those with disabilities.
LLM-generated comments should be evaluated on their merits, not their origin.
Detection of LLM-generated comments is unreliable and could lead to false positives.
A ban on LLM-generated comments could discourage participation from editors who rely on these tools.
Additional points
There is disagreement about whether machine translation should be considered LLM-generated content.
Some editors believe that LLMs could be used constructively in discussions, for example, to summarize arguments or provide alternative perspectives.
Others are concerned about the potential for LLMs to be used maliciously, for example, to flood discussions with irrelevant comments or to impersonate other editors.
Overall
There is no clear consensus on whether to ban or allow LLM-generated comments in discussions. The discussion highlights the challenges of balancing the potential benefits and risks of using LLMs in a collaborative environment like Misplaced Pages.
That was a good answer but I wanted to get a rough headcount and so asked a supplementary question, "What was the count of the number of support and opposing votes in the discussion?" The answer was:
Unfortunately, a precise count of support vs oppose votes in that discussion is difficult to determine definitively for a few reasons:
Some votes are unclear: Several editors express nuanced positions or change their vote during the discussion.
"Strong" votes aren't quantified: While many editors use "Strong support" or "Strong oppose", these don't carry extra weight in a simple tally.
Focus shifts: The initial focus on AI-generated comments broadens to include AI-assistance, making some votes less clear-cut.
However, based on a rough manual count:
Support: Around 60-70 votes clearly favor discounting or removing AI-generated comments.
Oppose: Roughly 30-40 votes lean against the proposal, with varying degrees of opposition.
Important Note: This is an approximation. The actual consensus in such discussions is determined by the closer, who weighs the arguments' quality and policy relevance, not just the number of votes.
This seems to be another good answer – better than we get from most human closes. I made a rough manual count to confirm that the numbers given are reasonable ballpark figures. And it seems to have an impressive grasp of nuance – noticing that several editors were qualifying their votes as strong/weak and that some editors changed their vote. Andrew🐉(talk) 22:02, 10 January 2025 (UTC)
These feel (from my memory of when I skimmed over the discussion several days ago before my original !vote/comment) like they might be leaving out some relevant points that came up. (Unfortunately I can't quantify that without taking a look which I don't have time to do right now (other than the fact my own concerns didn't make it into the summary, which... fair, I guess, considering I was the only one who raised that specific issue).) (I'm also very surprised it came up with something coherent as well as on topic, but that just has more to do with the fact Gemini (or at least whatever AI summarizes Google searches) told me extremely recently that I could get to Alaska by car without a passport if I drove through the ocean. Not took a ferry but drove... through the water... in a car.) - Purplewowies (talk) 07:02, 11 January 2025 (UTC)
Your !vote was a qualified support with concern about false positives affecting editors such as the autistic. That's then a nuanced, both-ways vote and the Gemini summary seems to capture that reasonably well. Andrew🐉(talk) 09:43, 11 January 2025 (UTC)
Alternate proposal
The following discussion is closed. Please do not modify it. Subsequent comments should be made in a new section.A summary of the conclusions reached follows.
Whereas many editors, including me, have cited problems with accuracy in regards to existing tools such as ZeroGPT, I propose that remarks that are blatently generated by a LLM or similar automated system should be discounted/removed/collapsed/hidden. ThatIPEditor10:00, 10 December 2024 (UTC)
Oppose as completely unnecessary and far too prone to error per the above discussion. Any comment that is good (on topic, relevant, etc) should be considered by the closer regardless of whether it was made with LLM-input of any sort or not. Any comment that is bad (off-topic, irrelevant, etc) should be ignored by the closer regardless of whether it was made with LLM-input of any sort or not. Any comment that is both bad and disruptive (e.g. by being excessively long, completely irrelevant, bludgeoning, etc) should be removed and/or hatted as appropriate, regardless of whether it was made with LLM-input of any sort. The good thing is that this is already policy so we don't need to call out LLMs specifically, and indeed doing so is likely to be disruptive in cases where human-written comments are misidentified as being LLM-written (which will happen, regardless of whether tools are used). Thryduulf (talk) 11:19, 10 December 2024 (UTC)
I think this proposal is not really necessary. I support it, but that is because it is functionally identical to the one directly above it, which I also supported. This should probably be hatted. BugGhost🦗👻18:32, 10 December 2024 (UTC)
What does blatantly generated mean? Does you mean only where the remark is signed with "I, Chatbot", or anything that appears to be LLM-style? I don't think there's much in between. ypn^219:21, 10 December 2024 (UTC)
Procedural close per BugGhost. I'd hat this myself, but I don't think that'd be appropriate since it's only the two of us who have expressed that this proposal is basically an exact clone. Aaron Liu (talk) 03:00, 11 December 2024 (UTC)
The discussion above is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.
Option 1 – Require former administrators to request restoration of their tools at the bureaucrats' noticeboard (BN) if they are eligible to do so (i.e., they do not fit into any of the exceptions).
Option 2 – Clarify Maintain the status quo that former administrators who would be eligible to request restoration via BN may instead request restoration of their tools via a voluntary request for adminship (RfA).
Option 3 – Allow bureaucrats to SNOW-close RfAs as successful if (a) 48 hours have passed, (b) the editor has right of resysop, and (c) a SNOW close is warranted.
2, after thought. I don't think 3 provides much benefit, and creating separate class of RfAs that are speedy passed feels a misstep. If there are serious issues surrounding wasting time on RfAs set up under what might feel to someone like misleading pretenses, that is best solved by putting some indicator next to their RFA candidate name. Maybe "Hog Farm (RRfA)". CMD (talk) 14:49, 16 December 2024 (UTC)
best solved by putting some indicator next to their RFA candidate name. Maybe "Hog Farm (RRfA)" - I like this idea, if option 2 comes out as consensus I think this small change would be a step in the right direction, as the "this isn't the best use of time" crowd (myself included) would be able to quickly identify the type of RFAs they don't want to participate in. BugGhost🦗👻11:05, 17 December 2024 (UTC)
I think that's a great idea. I would support adding some text encouraging people who are considering seeking reconfirmation to add (RRfA) or (reconfirmation) after their username in the RfA page title. That way people who are averse to reading or participating in reconfirmations can easily avoid them, and no one is confused about what is going on. 28bytes (talk) 14:23, 17 December 2024 (UTC)
If we are differentiating three types of RFA we need three terms. Post-recall RFAs are referred to as "reconfirmation RFAs", "Re-RFAS" or "RRFAs" in multiple places, so ones of the type being discussed here are the ones that should take the new term. "Voluntary reconfirmation RFA" (VRRFA or just VRFA) is the only thing that comes to mind but others will probably have better ideas. Thryduulf (talk) 21:00, 17 December 2024 (UTC)
2 I don't see why people trying to do the right thing should be discouraged from doing so. If others feel it is a waste of time, they are free to simply not participate. El Beeblerino21:27, 15 December 2024 (UTC)
Of course they may request at RfA. They shouldn't but they may. This RfA feels like it does nothing to address the criticism actually in play and per the link to the idea lab discussion it's premature to boot. Barkeep49 (talk) 21:38, 15 December 2024 (UTC)
2 per my comments at the idea lab discussion and Queent of Hears, Beeblebrox and Scazjmd above. I strongly disagree with Barkeep's comment that "They shouldn't ". It shouldn't be made mandatory, but it should be encouraged where the time since desysop and/or the last RFA has been lengthy. Thryduulf (talk) 21:42, 15 December 2024 (UTC)
When to encourage it would be a worthwhile RfC and such a discussion could be had at the idea lab before launching an RfC. Best, Barkeep49 (talk) 21:44, 15 December 2024 (UTC)
1 or 3. RFA is an "expensive" process in terms of community time. RFAs that qualify should be fast-tracked via the BN process. It is only recently that a trend has emerged that folks that don't need to RFA are RFAing again. 2 in the last 6 months. If this continues to scale up, it is going to take up a lot of community time, and create noise in the various RFA statistics and RFA notification systems (for example, watchlist notices and User:Enterprisey/rfa-count-toolbar.js). –Novem Linguae (talk) 21:44, 15 December 2024 (UTC)
Making statistics "noisy" is just a reason to improve the way the statistics are gathered. In this case collecting statistics for reconfirmation RFAs separately from other RFAs would seem to be both very simple and very effective. If (and it is a very big if) the number of reconfirmation RFAs means that notifications are getting overloaded, then we can discuss whether reconfirmation RFAs should be notified differently. As far as differentiating them, that is also trivially simple - just add a parameter to template:RFA (perhaps "reconfirmation=y") that outputs something that bots and scripts can check for. Thryduulf (talk) 22:11, 15 December 2024 (UTC)
I'm weakly opposed to option 3, editors who want feedback and a renewed mandate from the community should be entitled to it. If they felt that that a quick endorsement was all that was required then could have had that at BN, they explicitly chose not to go that route. Nobody is required to participate in an RFA, so if it is going the way you think it should, or you don't have an opinion, then just don't participate and your time has not been wasted. Thryduulf (talk) 22:20, 15 December 2024 (UTC)
Added option 3 above. Maybe worth considering as a happy medium, where unsure admins can get a check on their conduct without taking up too much time. theleekycauldron (talk • she/her) 22:11, 15 December 2024 (UTC)
2 – If a former admin wishes to subject themselves to RfA to be sure they have the requisite community confidence to regain the tools, why should we stop them? Any editor who feels the process is a waste of time is free to ignore any such RfAs. — Jkudlick ⚓ (talk)22:12, 15 December 2024 (UTC)
I would also support option 3 if the time is extended to 72 hours instead of 48. That, however, is a detail that can be worked out after this RfC. — Jkudlick ⚓ (talk)02:05, 16 December 2024 (UTC)
A further note: option 3 gives 'crats the discretion to SNOW close a successful voluntary re-RfA; it doesn't require such a SNOW close, and I trust the 'crats to keep an RfA open if an admin has a good reason for doing so. voorts (talk/contributions) 23:24, 16 December 2024 (UTC)
Option 2 (no change) – The sample size is far too small for us to analyze the impact of such a change, but I believe RfA should always be available. Now that WP:RECALL is policy, returning administrators may worry that they have become out of touch with community norms and may face a recall as soon as they get their tools back at BN. Having this familiar community touchpoint as an option makes a ton of sense, and would be far less disruptive / demoralizing than a potential recall. Taking this route away, even if it remains rarely used, would be detrimental to our desire for increased administrator accountability. – bradv22:22, 15 December 2024 (UTC)
2, distant second preference 3. I would probably support 3 as first pick if not for recall's rule regarding last RfA, but as it stands, SNOW-closing a discussion that makes someone immune to recall for a year is a non-starter. Between 1 and 2, though, the only argument for 1 seems to be that it avoids a waste of time, for which there is the much simpler solution of not participating and instead doing something else. Special:Random and Misplaced Pages:Backlog are always there. -- Tamzin (they|xe|🤷) 23:31, 15 December 2024 (UTC)
Option 1. No second preference between 2 or 3. As long as a former administrator didn't resign under a cloud, picking up the tools again should be low friction and low effort for the entire community. If there are issues introduced by the recall process, they should be fixed in the recall policy itself. Daniel Quinlan (talk) 01:19, 16 December 2024 (UTC)
Option 2, i.e. leave well enough alone. There is really not a problem here that needs fixing. If someone doesn’t want to “waste their time” participating in an RfA that’s not required by policy, they can always, well, not participate in the RfA. No one is required to participate in someone else’s RfA, and I struggle to see the point of participating but then complaining about “having to” participate. 28bytes (talk) 01:24, 16 December 2024 (UTC)
Option 3: Because it is incredibly silly to have situations like we do now of "this guy did something wrong by doing an RfA that policy explicitly allows, oh well, nothing to do but sit on our hands and dissect the process across three venues and counting." Your time is your own. No one is forcibly stealing it from you. At the same time it is equally silly to let the process drag on, for reasons explained in WP:SNOW. Gnomingstuff (talk) 03:42, 16 December 2024 (UTC)
Option 3 per Gnoming. I think 2 works, but it is a very long process and for someone to renew their tools, it feels like an unnecessarily long process compared to a normal RfA. Conyo14 (talk) 04:25, 16 December 2024 (UTC)
As someone who supported both WormTT and Hog Farm's RfAs, option 1 > option 3 >> option 2. At each individual RfA the question is whether or not a specific editor should be an admin, and in both cases I felt that the answer was clearly "yes". However, I agree that RfA is a very intensive process. It requires a lot of time from the community, as others have argued better than I can. I prefer option 1 to option 3 because the existence of the procedure in option 3 implies that it is a good thing to go through 48 hours of RfA to re-request the mop. But anything which saves community time is a good thing. HouseBlaster (talk • he/they) 04:31, 16 December 2024 (UTC)
I've seen this assertion made multiple times now that requires a lot of time from the community, yet nowhere has anybody articulated how why this is true. What time is required, given that nobody is required to participate and everybody who does choose to participate can spend as much or as little time assessing the candidate as they wish? How and why does a reconfirmation RFA require any more time from editors (individually or collectively) than a request at BN? Thryduulf (talk) 04:58, 16 December 2024 (UTC)
I think there are a number of factors and people are summing it up as "time-wasting" or similar:
BN Is designed for this exact scenario. It's also clearly a less contentious process.
Snow closures a good example of how we try to avoid wasting community time on unnecessary process and the same reasoning applies here. Misplaced Pages is not a bureaucracy and there's no reason to have a 7-day process when the outcome is a given.
If former administrators continue to choose re-RFAs over BN, it could set a problematic precedent where future re-adminship candidates feel pressured to go through an RFA and all that entails. I don't want to discourage people already vetted by the community from rejoining the ranks.
The RFA process is designed to be a thoughtful review of prospective administrators and I'm concerned these kinds of perfunctory RFAs will lead to people taking the process less seriously in the future.
Because several thousand people have RFA on their watchlist, and thousands more will see the "there's an open RFA" notice on theirs whether they follow it or not. Unlike BN, RFA is a process that depends on community input from a large number of people. In order to even realise that the RFA is not worth their time, they have to:
Read the opening statement and first few question answers (I just counted, HF's opening and first 5 answers are about 1000 words)
Think, "oh, they're an an ex-admin, I wonder why they're going through RFA, what was their cloud"
Read through the comments and votes to see if any issues have been brought up (another ~1000 words)
None have
Realise your input is not necessary and this could have been done at BN
That they were former admins has always been the first two sentences of their RfA’s statement, sentences which are immediately followed by that they resigned due to personal time commitment issues. You do not have to read the first 1000+ words to figure that out. If the reader wants to see if the candidate was lying in their statement, then they just have a quick skim through the oppose section. None of this should take more than 30 seconds in total. Aaron Liu (talk) 13:15, 16 December 2024 (UTC)
Not everyone can skim things easily - it personally takes me a while to read sections. I don't know if they're going to bury the lede and say something like "Also I made 10,000 insane redirects and then decided to take a break just before arbcom launched a case" in paragraph 6. Hog Farm's self nom had two paragraphs about disputes and it takes more than 30 seconds to unpick that and determine if that is a "cloud" or not. Even for reconfirmations, it definitely takes more than 30 seconds to determine a conclusion. BugGhost🦗👻11:21, 17 December 2024 (UTC)
They said they resigned to personal time commitments. That is directly saying they wasn’t under a cloud, so I’ll believe them unless someone claims the contrary in the oppose section. If the disputes section contained a cloud, the oppose section would have said so. One chooses to examine such nominations like normal RfAs. Aaron Liu (talk) 18:47, 17 December 2024 (UTC)
Just to double check, you're saying that whenever you go onto an RFA you expect any reason to oppose to already be listed by someone else, and no thought is required? I am begining to see how you are able to assess an RFA in under 30 seconds BugGhost🦗👻23:08, 17 December 2024 (UTC)
Something in their statement would be an incredibly obvious reason. We are talking about the assessment whether to examine and whether the candidate could've used BN. Aaron Liu (talk) 12:52, 18 December 2024 (UTC)
@Thryduulf let's not confuse "a lot of community time is spent" with "waste of time". Some people have characterized the re-RFAs as a waste of time but that's not the assertion I (and I think a majority of the skeptics) have been making. All RfAs use a lot of community time as hundreds of voters evaluate the candidate. They then choose to support, oppose, be neutral, or not vote at all. While editor time is not perfectly fixed - editors may choose to spend less time on non-Misplaced Pages activities at certain times - neither is it a resource we have in abundance anymore relative to our project. And so I think we, as a community, need to be thought about how we're using that time especially when the use of that time would have been spent on other wiki activities.Best, Barkeep49 (talk) 22:49, 16 December 2024 (UTC)
Absolutely nothing compels anybody to spend any time evaluating an RFA. If you think your wiki time is better spent elsewhere than evaluating an RFA candidate, then spend it elsewhere. That way only those who do think it is a good use of their time will participate and everybody wins. You win by not spending your time on something that you don't think is worth it, those who do participate don't have their time wasted by having to read comments (that contradict explicit policy) about how the RFA is a waste of time. Personally I regard evaluating whether a long-time admin still has the approval of the community to be a very good use of community time, you are free to disagree, but please don't waste my time by forcing me to read comments about how you think I'm wasting my time. Thryduulf (talk) 23:39, 16 December 2024 (UTC)
I don't understand how your argument that it is not a good use of community time is any different from arguing that it is a waste of time? Thryduulf (talk) 09:08, 17 December 2024 (UTC)
Option 2 I don't mind the re-RFAs, but I'd appreciate if we encouraged restoration via BN instead, I just object to making it mandatory. EggRoll9706:23, 16 December 2024 (UTC)
Option 2. Banning voluntary re-RfAs would be a step in the wrong direction on admin accountability. Same with SNOW closing. There is no more "wasting of community time" if we let the RfA run for the full seven days, but allowing someone to dig up a scandal on the seventh day is an important part of the RfA process. The only valid criticism I've heard is that folks who do this are arrogant, but banning arrogance, while noble, seems highly impractical. Toadspike07:24, 16 December 2024 (UTC)
Option 3, 1, then 2, per HouseBlaster. Also agree with Daniel Quinlan. I think these sorts of RFA's should only be done in exceptional circumstances. Graham87 (talk) 08:46, 16 December 2024 (UTC)
Option 1 as first preference, option 3 second. RFAs use up a lot of time - hundreds of editors will read the RFA and it takes time to come to a conclusion. When that conclusion is "well that was pointless, my input wasn't needed", it is not a good system. I think transparency and accountability is a very good thing, and we need more of it for resyssopings, but that should come from improving the normal process (BN) rather than using a different one (RFA). My ideas for improving the BN route to make it more transparent and better at getting community input is outlined over on the idea labBugGhost🦗👻08:59, 16 December 2024 (UTC)
Option 2, though I'd be for option 3 too. I'm all for administrators who feel like they want/should go through an RfA to solicit feedback even if they've been given the tools back already. I see multiple people talk about going through BN, but if I had to hazard a guess, it's way less watched than RfA is. However I do feel like watchlist notifications should say something to the effect of "A request for re-adminship feedback is open for discussion" so that people that don't like these could ignore them. ♠JCW555(talk)♠ 09:13, 16 December 2024 (UTC)
Option 2 because WP:ADMINISTRATORS is well-established policy. Read WP:ADMINISTRATORS#Restoration of admin tools, which says quite clearly, Regardless of the process by which the admin tools are removed, any editor is free to re-request the tools through the requests for adminship process. I went back 500 edits to 2017 and the wording was substantially the same back then. So, I simply do not understand why various editors are berating former administrators to the point of accusing them of wasting time and being arrogant for choosing to go through a process which is specifically permitted by policy. It is bewildering to me. Cullen328 (talk) 09:56, 16 December 2024 (UTC)
Option 2 & 3 I think that there still should be the choice between BN and re-RFA for resysops, but I think that the re-RFA should stay like it is in Option 3, unless it is controversial, at which point it could be extended to the full RFA period. I feel like this would be the best compromise between not "wasting" community time (which I believe is a very overstated, yet understandable, point) and ensuring that the process is based on broad consensus and that our "representatives" are still supported. If I were WTT or Hog, I might choose to make the same decision so as to be respectful of the possibility of changing consensus. JuxtaposedJacob (talk) | :) | he/him | 10:45, 16 December 2024 (UTC)
Option 2, for lack of a better choice. Banning re-RFAs is not a great idea, and we should not SNOW close a discussion that would give someone immunity from a certain degree of accountability. I've dropped an idea for an option 4 in the discussion section below. Giraffer (talk) 12:08, 16 December 2024 (UTC)
Option 1 I agree with Graham87 that these sorts of RFAs should only be done in exceptional circumstances, and BN is the best place to ask for tools back. – DreamRimmer (talk) 12:11, 16 December 2024 (UTC)
Option 2 I don't think prohibition makes sense. It also has weird side effects. eg: some admins' voluntary recall policies may now be completely void, because they would be unable to follow them even if they wanted to, because policy prohibits them from doing a RFA. (maybe if they're also 'under a cloud' it'd fit into exemptions, but if an admins' policy is "3 editors on this named list tell me I'm unfit, I resign" then this isn't really a cloud.) Personally, I think Hog Farm's RFA was unwise, as he's textbook uncontroversial. Worm's was a decent RFA; he's also textbook uncontroversial but it happened at a good time. But any editor participating in these discussions to give the "support" does so using their own time. Everyone who feels their time is wasted can choose to ignore the discussion, and instead it'll pass as 10-0-0 instead of 198-2-4. It just doesn't make sense to prohibit someone from seeking a community discussion, though. For almost anything, really. ProcrastinatingReader (talk) 12:33, 16 December 2024 (UTC)
Option 2 It takes like two seconds to support or ignore an RFA you think is "useless"... can't understand the hullabaloo around them. I stand by what I said on WTT's re-RFA regarding RFAs being about evaluating trustworthiness and accountability. Trustworthy people don't skip the process. —k6ka 🍁 (Talk · Contributions) 15:24, 16 December 2024 (UTC)
2 is fine. Strong oppose to 1 and 3. Opposing option 1 because there is nothing wrong with asking for extra community feedback. opposing option 3 because once an RfA has been started, it should follow the standard rules. Note that RfAs are extremely rare and non-contentious RfAs require very little community time (unlike this RfC which seems a waste of community time, but there we are). —Kusma (talk) 16:59, 16 December 2024 (UTC)
2, with no opposition to 3. I see nothing wrong with a former administrator getting re-confirmed by the community, and community vetting seems like a good thing overall. If people think it's a waste of time, then just ignore the RfA. Natg 19 (talk) 17:56, 16 December 2024 (UTC)
No individual is wasting their time participating. Instead the person asking for a re-rfa is using tons of editor time by asking hundreds of people to vet them. Even the choice not to participate requires at least some time to figure out that this is not a new RfA; though at least in the two we've had recently it would require only as long as it takes to get to the RfA - for many a click from the watchlist and then another click into the rfa page - and to read the first couple of sentences of the self-nomination which isn't terribly long all things considered. Best, Barkeep49 (talk) 22:55, 16 December 2024 (UTC)
I agree with you (I think) that it's a matter of perspective. For me, clicking the RFA link in my watchlist and reading the first paragraph of Hog Farm's nomination (where they explained that they were already a respected admin) took me about 10 seconds. Ten seconds is nothing; in my opinion, this is just a nonissue. But then again, I'm not an admin, checkuser, or an oversighter. Maybe the time to read such a nomination is really wasting their time. I don't know. TheWikiToby (talk) 23:15, 16 December 2024 (UTC)
I'm an admin and an oversighter (but not a checkuser). None of my time was wasted by either WTT or Hog Farm's nominations. Thryduulf (talk) 23:30, 16 December 2024 (UTC)
2. This reminds me of banning plastic straws (bear with me). Sure, I suppose in theory, that this is a burden on the community's time (just as straws do end up in landfills/the ocean). However, the amount of community time that is drained is minuscule compared to the amount of community time drained in countless, countless other fora and processes (just like the volume of plastic waste contributed by plastic straws is less than 0.001% of the total plastic waste). When WP becomes an efficient, well oiled machine, then maybe we can talk about saving community time by banning re-RFA's. But this is much ado about nothing, and indeed this plan to save people from themselves, and not allow them to simply decide whether to participate or not, is arguably more damaging than some re-RFAs (just as banning straws convinced some people that "these save-the-planet people are so ridiculous that I'm not going to bother listening to them about anything."). And, in fact, on a separate note, I'd actually love it if more admins just ran a re-RFA whenever they wanted. They would certainly get better feedback than just posting "What do my talk page watchers think?" on their own talk page. Or waiting until they get yelled at on their talk page, AN/ANI, AARV, etc. We say we want admins to respect feedback; does it have to be in a recall petition? --Floquenbeam (talk) 23:44, 16 December 2024 (UTC)
What meaningful feedback has Hog Farm gotten? "A minority of people think you choose poorly in choosing this process to regain adminship". What are they supposed to do with that? I share your desire for editors to share meaningful feedback with administrators. My own attempt yielded some, though mainly offwiki where I was told I was both too cautious and too impetuous (and despite the seeming contradiction each was valuable in its own way). So yes let's find ways to get meaningful feedback to admins outside of recall or being dragged to ANI. Unfortunately re-RfA seems to be poorly suited to the task and so we can likely find a better way. Best, Barkeep49 (talk) 03:38, 17 December 2024 (UTC)
No hard rule, but we should socially discourage confirmation RfAs There is a difference between a hard rule, and a soft social rule. A hard rule against confirmation RfA's, like option 1, would not do a good job of accounting for edge cases and would thus be ultimately detrimental here. But a soft social rule against them would be beneficial. Unfortunately, that is not one of the options of this RfC. In short, a person should have a good reason to do a confirmation RfA. If you're going to stand up before the community and ask "do you trust me," that should be for a good reason. It shouldn't just be because you want the approval of your peers. (Let me be clear: I am not suggesting that is why either Worm or Hogfarm re-upped, I'm just trying to create a general purpose rule here.) That takes some introspection and humility to ask yourself: is it worth me inviting two or three hundred people to spend part of their lives to comment on me as a person?A lot of people have thrown around editor time in their reasonings. Obviously, broad generalizations about it aren't convincing anyone. So let me just share my own experience. I saw the watchlist notice open that a new RfA was being run. I reacted with some excitement, because I always like seeing new admins. When I got to the page and saw Hogfarm's name, I immediately thought "isn't he already an admin?" I then assumed, ah, its just the classic RfA reaction at seeing a qualified candidate, so I'll probably support him since I already think he's an admin. But then as I started to do my due diligence and read, I saw that he really, truly, already had been an admin. At that point, my previous excitement turned to a certain unease. I had voted yes for Worm's confirmation RfA, but here was another...and I realized that my blind support for Worm might have been the start of an entirely new process. I then thought "bet there's an RfC going about this," and came here. I then spent a while polishing up my essay on editor time, before taking time to write this message. All in all, I probably spent a good hour doing this. Previously, I'd just been clicking the random article button and gnoming. So, the longwinded moral: yeah, this did eat up a lot of my editor time that could have and was being spent doing something else. And I'd do it again! It was important to do my research and to comment here. But in the future...maybe I won't react quite as excitedly to seeing that RfA notice. Maybe I'll feel a little pang of dread...wondering if its going to be a confirmation RfA. We can't pretend that confirmation RfA's are costless, and that we don't lose anything even if editors just ignore them. When run, it should be because they are necessary. CaptainEek⚓03:29, 17 December 2024 (UTC)
In short, a person should have a good reason to do a confirmation RfA. If you're going to stand up before the community and ask "do you trust me," that should be for a good reason. It shouldn't just be because you want the approval of your peers. Asking the community whether you still have their trust to be an administrator, which is what an reconfirmation RFA is, is a good reason. I expect getting a near-unanimous "yes" is good for one's ego, but that's just a (nice) side-effect of the far more important benefits to the entire community: a trusted administrator.
The time you claim is being eaten up unnecessarily by reconfirmation RFAs was actually taken up by you choosing to spend your time writing an essay about using time for things you don't approve of and then hunting out an RFC in which you wrote another short essay about using time on things you don't approve of. Absolutely none of that is a necessary consequence of reconfirmation RFAs - indeed the response consistent with your stated goals would have been to read the first two sentences of Hog Farm's RFA and then closed the tab and returned to whatever else it was you were doing. Thryduulf (talk) 09:16, 17 December 2024 (UTC)
WTT's and Hog Farm's RFAs would have been completely uncontentious, something I hope for at RfA and certainly the opposite of what I "dread" at RfA, if it were not for the people who attack the very concept of standing for RfA again despite policy being crystal clear that it is absolutely fine. I don't see how any blame for this situation can be put on WTT or HF. We can't pretend that dismissing uncontentious reconfirmation RfAs is costless; discouraging them removes one of the few remaining potentially wholesome bits about the process. —Kusma (talk) 09:53, 17 December 2024 (UTC)
@CaptainEek Would you find it better if Watchlist notices and similar said "(re?)confirmation RFA" instead of "RFA"? Say for all voluntary RFAs from an existing admin or someone who could have used BN?
As a different point, I would be quite against any social discouraging if we're not making a hard rule as such. Social discouraging is what got us the opposes at WTT/Hog Farm's RFAs, which I found quite distasteful and badgering. If people disagree with a process, they should change it. But if the process remains the same, I think it's important to not enable RFA's toxicity by encouraging others to namecall or re-argue the process in each RRFA. It's a short road from social discouragement to toxicity, unfortunately. Soni (talk) 18:41, 19 December 2024 (UTC)
Option 2 if people think there's a waste of community time, don't spend your time voting or discussing. Or add "reconfirmation" or similar to the watchlist notice. ~~ AirshipJungleman29 (talk) 15:08, 17 December 2024 (UTC)
Option 3 (which I think is a subset of option 2, so I'm okay with the status quo, but I want to endorse giving 'crats the option to SNOW). While they do come under scrutiny from time to time for the extensive dicsussions in the "maybe" zone following RfAs, this should be taken as an indiciation that they are unlikely to do something like close it as SNOW in the event there is real and substantial concerns being rasied. This is an okay tool to give the 'crats. As far as I can tell, no one has ever accused the them of moving too quickly in this direction (not criticism; love you all, keep up the good work). Bobby Cohn (talk) 17:26, 17 December 2024 (UTC)
Option 3 or Option 2. Further, if Option 2 passes, I expect it also ends all the bickering about lost community time. A consensus explicitly in favour of "This is allowed" should also be a consensus to discourage relitigation of this RFC. Soni (talk) 17:35, 17 December 2024 (UTC)
Option 2: Admins who do not exude entitlement are to be praised. Those who criticize this humility should have a look in the mirror before accusing those who ask for reanointment from the community of "arrogance". I agree that it wouldn't be a bad idea to mention in parentheses that the RFA is a reconfirmation (watchlist) and wouldn't see any problem with crats snow-closing after, say, 96 hours. -- SashiRolls18:48, 17 December 2024 (UTC)
I know. I see a sizable amount of commenters here starting to say that voluntary re-RfAs should be encouraged, and your first sentence can be easily read as implying that admins who use the BN route exude entitlement. I disagree with that (see my reply to Thryduulf below). Aaron Liu (talk) 12:56, 18 December 2024 (UTC)
One way to improve the reputation of RFA is for there to be more RFAs that are not terrible, such as reconfirmations of admins who are doing/have done a good job who sail through with many positive comments. There is no proposal to make RFA mandatory in circumstances it currently isn't, only to reaffirm that those who voluntarily choose RFA are entitled to do so. Thryduulf (talk) 21:06, 17 December 2024 (UTC)
I know it's not a proposal, but there's enough people talking about this so far that it could become a proposal. There's nearly nothing in between that could've lost the trust of the community. I'm sure there are many who do not want to be pressured into this without good reason. Aaron Liu (talk) 12:57, 18 December 2024 (UTC)
Absolutely nobody is proposing, suggesting or hinting here that reconfirmation RFAs should become mandatory - other than comments from a few people who oppose the idea of people voluntarily choosing to do something policy explicitly allows them to choose to do. The best way to avoid people being pressured into being accused of arrogance for seeking reconfirmation of their status from the community is to sanction those people who accuse people of arrogance in such circumstances as such comments are in flagrant breach of AGF and NPA. Thryduulf (talk) 14:56, 18 December 2024 (UTC)
Yes, I’m saying that they should not become preferred. There should be no social pressure to do RfA instead of BN, only pressure intrinsic to the candidate. Aaron Liu (talk) 15:37, 18 December 2024 (UTC)
Whether they should become preferred in any situation forms no part of this proposal in any way shape or form - this seeks only to reaffirm that they are permitted. A separate suggestion, completely independent of this one, is to encourage (explicitly not mandate) them in some (but explicitly not all) situations. All discussions on this topic would benefit if people stopped misrepresenting the policies and proposals - especially when the falsehoods have been explicitly called out. Thryduulf (talk) 15:49, 18 December 2024 (UTC)
I am talking and worrying over that separate proposal many here are suggesting. I don’t intend to oppose Option 2, and sorry if I came off that way. Aaron Liu (talk) 16:29, 18 December 2024 (UTC)
Option 2. In fact, I'm inclined to encourage an RRfA over BN, because nothing requires editors to participate in an RRfA, but the resulting discussion is better for reaffirming community consensus for the former admin or otherwise providing helpful feedback. --Pinchme123 (talk) 21:45, 17 December 2024 (UTC)
Option 2WP:RFA has said "Former administrators may seek reinstatement of their privileges through RfA..." for over ten years and this is not a problem. I liked the opportunity to be consulted in the current RfA and don't consider this a waste of time. Andrew🐉(talk) 22:14, 17 December 2024 (UTC)
2 - If an administrator gives up sysop access because they plan to be inactive for a while and want to minimize the attack surface of Misplaced Pages, they should be able to ask for permissions back the quickest way possible. If an administrator resigns because they do not intend to do the job anymore, and later changes their mind, they should request a community discussion. The right course of action depends on the situation. Jehochman14:00, 18 December 2024 (UTC)
Option 1. I've watched a lot of RFAs and re-RFAs over the years. There's a darn good reason why the community developed the "go to BN" option: saves time, is straightforward, and if there are issues that point to a re-RFA, they're quickly surfaced. People who refuse to take the community-developed process of going to BN first are basically telling the community that they need the community's full attention on their quest to re-admin. Yes, there are those who may be directed to re-RFA by the bureaucrats, in which case, they have followed the community's carefully crafted process, and their re-RFA should be evaluated from that perspective. Risker (talk) 02:34, 19 December 2024 (UTC)
Option 2 (status quo/no changes) per meh. This is bureaucratic rulemongering at its finest. Every time RFA reform comes up some editors want admins to be required to periodically reconfirm, then when some admins decide to reconfirm voluntarily, suddenly that's seen as a bad thing. The correct thing to do here is nothing. If you don't like voluntary reconfirmation RFAs, you are not required to participate in them. Ivanvector (/Edits) 19:34, 19 December 2024 (UTC)
Option 2 I would probably counsel just going to BN most of the time, however there are exceptions and edge cases. To this point these RfAs have been few in number, so the costs incurred are relatively minor. If the number becomes large then it might be worth revisiting, but I don't see that as likely. Some people will probably impose social costs on those who start them by opposing these RfAs, with the usual result, but that doesn't really change the overall analysis. Perhaps it would be better if our idiosyncratic internal logic didn't produce such outcomes, but that's a separate issue and frankly not really worth fighting over either. There's probably some meta issues here I'm unaware off, it's long since I've had my finger on the community pulse so to speak, but they tend to matter far less than people think they do. 184.152.68.190 (talk) 02:28, 20 December 2024 (UTC)
Option 1, per WP:POINT, WP:NOT#SOCIALNETWORK, WP:NOT#BUREAUCRACY, WP:NOTABOUTYOU, and related principles. We all have far better things to do that read through and argue in/about a totally unnecessary RfA invoked as a "Show me some love!" abuse of process and waste of community time and productivity. I could live with option 3, if option 1 doesn't fly (i.e. shut these silly things down as quickly as possible). But option 2 is just out of the question. — SMcCandlish☏¢ 😼 04:28, 22 December 2024 (UTC)
Except none of the re-RFAs complained about have been RfA invoked as a "Show me some love!" abuse of process, you're arguing against a strawman. Thryduulf (talk) 11:41, 22 December 2024 (UTC)
It's entirely a matter of opinion and perception, or A) this RfC wouldn't exist, and B) various of your fellow admins like TonyBallioni would not have come to the same conclusion I have. Whether the underlying intent (which no one can determine, lacking as we do any magical mind-reading powers) is solely egotistical is ultimately irrelevant. The actual effect (what matters) of doing this whether for attention, or because you've somehow confused yourself into think it needs to be done, is precisely the same: a showy waste of community volunteers' time with no result other than a bunch of attention being drawn to a particular editor and their deeds, without any actual need for the community to engage in a lengthy formal process to re-examine them. — SMcCandlish☏¢ 😼 05:49, 23 December 2024 (UTC)
or because you've somehow confused yourself into think it needs to be done
Option 2. I see no legitimate reason why we should be changing the status quo. Sure, some former admins might find it easier to go through BN, and it might save community time, and most former admins already choose the easier option. However, if a candidate last ran for adminship several years ago, or if issues were raised during their tenure as admin, then it may be helpful for them to ask for community feedback, anyway. There is no "wasted" community time in such a case. I really don't get the claims that this violates WP:POINT, because it really doesn't apply when a former admin last ran for adminship 10 or 20 years ago or wants to know if they still have community trust.On the other hand, if an editor thinks a re-RFA is a waste of community time, they can simply choose not to participate in that RFA. Opposing individual candidates' re-RFAs based solely on opposition to re-RFAs in general is a violation of WP:POINT. – Epicgenius (talk) 14:46, 22 December 2024 (UTC)
But this isn't the status quo? We've never done a re-RfA before now. The question is whether this previously unconsidered process, which appeared as an emergent behavior, is a feature or a bug. CaptainEek⚓23:01, 22 December 2024 (UTC)
There have been lots of re-RFAs, historically. There were more common in the 2000s. Evercat in 2003 is the earliest I can find, back before the re-sysopping system had been worked out fully. Croat Canuck back in 2007 was snow-closed after one day, because the nominator and applicant didn't know that they could have gone to the bureaucrats' noticeboard. For more modern examples, HJ Mitchell (2011) is relatively similar to the recent re-RFAs in the sense that the admin resigned uncontroversially but chose to re-RFA before getting the tools back. Immediately following and inspired by HJ Mitchell's, there was the slightly more controversial SarekOfVulcan. That ended successful re-RFAS until 2019's Floquenbeam, which crat-chatted. Since then, there have been none that I remember. There have been several re-RFAs from admins who were de-sysopped or at serious risk of de-sysopping, and a few interesting edge cases such as the potentially optional yet no-consensus SarekVulcan 3 in 2014 and the Rich Farmbrough case in 2015, but those are very different than what we're talking about today. GreenLipstickLesbian (talk) 00:01, 23 December 2024 (UTC)
Well thank you both, I've learned something new today. It turns out I was working on a false assumption. It has just been so long since a re-RfA that I assumed it was a truly new phenomenon, especially since there were two in short succession. I still can't say I'm thrilled by the process and think it should be used sparingly, but perhaps I was a bit over concerned. CaptainEek⚓16:47, 23 December 2024 (UTC)
Option 2 or 3 per Gnoming and CaptainEek. Such RfAs only require at most 30 seconds for one to decide whether or not to spend their time on examination. Unlike other prohibited timesinks, it's not like something undesirable will happen if one does not sink their time. Voluntary reconfirmation RfAs are socially discouraged, so there is usually a very good reason for someone to go back there, such as accountability for past statements in the case of WTT or large disputes during adminship in the case of Hog Farm. I don't think we should outright deny these, and there is no disruption incurred if we don't. Aaron Liu (talk) 15:44, 23 December 2024 (UTC)
Option 2 (fine with better labeling) These don't seem harmful to me and, if I don't have time, I'll skip one and trust the judgment of my fellow editors. No objection to better labeling them though, as discussed above. RevelationDirect (talk) 22:36, 23 December 2024 (UTC)
Option 1 because it's just a waste of time to go through and !vote on candidates who just want the mop restored when he or she or they could get it restored BN with no problems. But I can also see option 2 being good for a former mod not in good standing. Therapyisgood (talk) 23:05, 23 December 2024 (UTC)
If you think it is a waste of time to !vote on a candidate, just don't vote on that candidate and none of your time has been wasted. Thryduulf (talk) 23:28, 23 December 2024 (UTC)
Option 2 Just because someone may be entitled to get the bit back doesn't mean they necessarily should. Look at my RFA3. I did not resign under a cloud, so I could have gotten the bit back by request. However, the RFA established that I did not have the community support at that point, so it was a good thing that I chose that path. I don't particularly support option 3, but I could deal with it. --SarekOfVulcan (talk)16:05, 27 December 2024 (UTC)
Option 1 Asking hundreds of people to vet a candidate who has already passed a RfA and is eligible to get the tools back at BN is a waste of the community's time. -- Pawnkingthree (talk) 16:21, 27 December 2024 (UTC)
Option 2 I really don't think there's a problem that needs to be fixed here. I am grateful at least a couple administrators have asked for the support of the community recently. SportingFlyerT·C00:12, 29 December 2024 (UTC)
Option 2. Keep the status quo of any editor is free to re-request the tools through the requests for adminship process. Voluntary RfA are rare enough not to be a problem, it's not as though we are overburdened with RfAs. And it’s my time to waste. --Malcolmxl5 (talk) 17:58, 7 January 2025 (UTC)
Option 2 or Option 3. These are unlikely to happen anyway, it's not like they're going to become a trend. I'm already wasting my time here instead of other more important activities anyway, so what's a little more time spent giving an easy support?fanfanboy(blocktalk)16:39, 10 January 2025 (UTC)
Discussion
@Voorts: If option 2 gets consensus how would this RfC change the wording Regardless of the process by which the admin tools are removed, any editor is free to re-request the tools through the requests for adminship process. Or is this an attempt to see if that option no longer has consensus? If so why wasn't alternative wording proposed? As I noted above this feels premature in multiple ways. Best, Barkeep49 (talk) 21:43, 15 December 2024 (UTC)
I've re-opened this per a request on my talk page. If other editors think this is premature, they can !vote accordingly and an uninvolved closer can determine if there's consensus for an early close in deference to the VPI discussion. voorts (talk/contributions) 21:53, 15 December 2024 (UTC)
The discussion at VPI, which I have replied on, seems to me to be different enough from this discussion that both can run concurrently. That is, however, my opinion as a mere editor. — Jkudlick ⚓ (talk)22:01, 15 December 2024 (UTC)
@Voorts, can you please reword the RfC to make it clear that Option 2 is the current consensus version? It does not need to be clarified – it already says precisely what you propose. – bradv22:02, 15 December 2024 (UTC)
Question: May someone clarify why many view such confirmation RfAs as a waste of community time? No editor is obligated to take up their time and participate. If there's nothing to discuss, then there's no friction or dis-cussing, and the RfA smooth-sails; if a problem is identified, then there was a good reason to go to RfA. I'm sure I'm missing something here. Aaron Liu (talk) 22:35, 15 December 2024 (UTC)
The intent of RfA is to provide a comprehensive review of a candidate for adminship, to make sure that they meet the community's standards. Is that happening with vanity re-RfAs? Absolutely not, because these people don't need that level of vetting. I wouldn't consider a week long, publicly advertized back patting to be a productive use of volunteer time. -- Ajraddatz (talk) 23:33, 15 December 2024 (UTC)
Sure, but that logic could be used to justify any time sink. We're all volunteers and nobody is forced to do anything here, but that doesn't mean that we should promote (or stay silent with our criticism of, I suppose) things that we feel don't serve a useful purpose. I don't think this is a huge deal myself, but we've got two in a short period of time and I'd prefer to do a bit of push back now before they get more common. -- Ajraddatz (talk) 01:52, 16 December 2024 (UTC)
Except someone who has no need for advanced tools and is not going to use them in any useful fashion, would then skate through with nary a word said about their unsuitability, regardless of the foregone conclusion. The point of RFA is not to rubber-stamp. Unless their is some actual issue or genuine concern they might not get their tools back, they should just re-request them at BN and stop wasting people's time with pointless non-process wonkery. Only in death does duty end (talk) 09:05, 16 December 2024 (UTC)
I’m confused. Adminship requires continued use of the tools. If you think they’s suitable for BN, I don’t see how doing an RfA suddenly makes them unsuitable. If you have concerns, raise them. Aaron Liu (talk) 13:02, 16 December 2024 (UTC)
I don't think the suggested problem (which I acknowledge not everyone thinks is a problem) is resolved by these options. Admins can still run a re-confirmation RfA after regaining adminsitrative privileges, or even initiate a recall petition. I think as discussed on Barkeep49's talk page, we want to encourage former admins who are unsure if they continue to be trusted by the community at a sufficient level to explore lower cost ways of determining this. isaacl (talk) 00:32, 16 December 2024 (UTC)
In re the idea that RfAs use up a lot of community time: I first started editing Misplaced Pages in 2014. There were 62 RfAs that year, which was a historic low. Even counting all of the AElect candidates as separate RfAs, including those withdrawn before voting began, we're still up to only 53 in 2024 – counting only traditional RfAs it's only 18, which is the second lowest number ever. By my count we've has 8 resysop requests at BN in 2024; even if all of those went to RfA, I don't see how that would overwhelm the community. That would still leave us on 26 traditional RfAs per year, or (assuming all of them run the full week) one every other week. Caeciliusinhorto-public (talk) 10:26, 16 December 2024 (UTC)
What about an option 4 encouraging eligible candidates to go through BN? At the end of the Procedure section, add something like "Eligible users are encouraged to use this method rather than running a new request for adminship." The current wording makes re-RfAing sound like a plausible alternative to a BN request, when in actual fact the former rarely happens and always generates criticism. Giraffer (talk) 12:08, 16 December 2024 (UTC)
Discouraging RFAs is the second last thing we should be doing (after prohibiting them), rather per my comments here and in the VPI discussion we should be encouraging former administrators to demonstrate that they still have the approval of the community. Thryduulf (talk) 12:16, 16 December 2024 (UTC)
I think this is a good idea if people do decide to go with option 2, if only to stave off any further mixed messages that people are doing something wrong or rude or time-wasting or whatever by doing a second RfA, when it's explicitly mentioned as a valid thing for them to do. Gnomingstuff (talk) 15:04, 16 December 2024 (UTC)
If RFA is explicitly a valid thing for people to do (which it is, and is being reaffirmed by the growing consensus for option 2) then we don't need to (and shouldn't) discourage people from using that option. The mixed messages can be staved off by people simply not making comments that explicitly contradict policy. Thryduulf (talk) 15:30, 16 December 2024 (UTC)
This is not new. We've had sporadic "vanity" RfAs since the early days of the process. I don't believe they're particularly harmful, and think that it unlikely that we will begin to see so many of them that they pose a problem. As such I don't think this policy proposal solves any problem we actually have. UninvitedCompany21:56, 16 December 2024 (UTC)
This apparent negative feeling evoked at an RFA for a former sysop everyone agrees is fully qualified and trusted certainly will put a bad taste in the mouths of other former admins who might consider a reconfirmation RFA without first visiting BN. This comes in the wake of Worm That Turned's similar rerun. BusterD (talk) 23:29, 16 December 2024 (UTC)
Nobody should ever be discouraged from seeking community consensus for significant changes. Adminship is a significant change. Thryduulf (talk) 23:32, 16 December 2024 (UTC)
No argument from me. I was a big Hog Farm backer way back when he was merely one of Misplaced Pages's best content contributors. BusterD (talk) 12:10, 17 December 2024 (UTC)
I went looking for @Tamzin's comment because I know they had hung up the tools and came back, and I was interested in their perspective. But they've given me a different epiphany. I suddenly realize why people are doing confirmation RfAs: it's because of RECALL, and the one year immunity a successful RfA gives you. Maybe everyone else already figured that one out and is thinking "well duh Eek," but I guess I hadn't :) I'm not exactly sure what to do with that epiphany, besides note the emergent behavior that policy change can create. We managed to generate an entirely new process without writing a single word about it, and that's honestly impressive :P CaptainEek⚓18:18, 17 December 2024 (UTC)
Worm That Turned followed through on a pledge he made in January 2024, before the 2024 review of the request for adminship process began. I don't think a pattern can be extrapolated from a sample size of one (or even two). That being said, it's probably a good thing if admins occasionally take stock of whether or not they continue to hold the trust of the community. As I previously commented, it would be great if these admins would use a lower cost way of sampling the community's opinion. isaacl (talk) 18:31, 17 December 2024 (UTC)
If people decide to go through a community vote to get a one year immunity from a process that only might lead to a community vote which would then have a lower threshold then the one they decide to go through, and also give a year's immunity, then good for them. CMD (talk) 01:05, 22 December 2024 (UTC)
@CaptainEek I'm mildly bothered by this comment, mildly because I assume it's lighthearted and non-serious. But just in case anyone does feel this way - I was very clear about my reasons for RRFA, I've written a lot about it, anyone is welcome to use my personal recall process without prejudice, and just to be super clear - I waive my "1 year immunity" - if someone wants to start a petition in the next year, do not use my RRfA as a reason not to. I'll update my userpage accordingly. I can't speak for Hog Farm, but his reasoning seems similar to mine, and immunity isn't it. Worm(talk) 10:28, 23 December 2024 (UTC)
@Worm That Turned my quickly written comment was perhaps not as clear as it could have been :) I'm sorry, I didn't mean to suggest that y'all had run for dubious reasons. As I said in my !vote, Let me be clear: I am not suggesting that is why either Worm or Hogfarm re-upped, I'm just trying to create a general purpose rule here. I guess what I really meant was that the reason that we're having this somewhat spirited conversation seems to be the sense that re-RfA could provide a protection from recall. If not for recall and the one year immunity period, I doubt we'd have cared so much as to suddenly run two discussions about this. CaptainEek⚓16:59, 23 December 2024 (UTC)
I don't agree. No one else has raised a concern about someone seeking a one-year respite from a recall petition. Personally, I think essentially self-initiating the recall process doesn't really fit the profile of someone who wants to avoid the recall process. (I could invent some nefarious hypothetical situation, but since opening an arbitration case is still a possibility, I don't think it would work out as planned.) isaacl (talk) 05:19, 24 December 2024 (UTC)
I really don't think this is the reason behind WTT's and HF's reconfirmation RFA's. I don't think their RFA's had much utility and could have been avoided, but I don't doubt for a second that their motivations were anything other than trying to provide transparency and accountability for the community. BugGhost🦗👻12:04, 23 December 2024 (UTC)
I don't really care enough about reconf RFAs to think they should be restricted, but what about a lighter ORCP-like process (maybe even in the same place) where fewer editors can indicate, "yeah OK, there aren't really any concerns here, it would probably save a bit of time if you just asked at BN". Alpha3031 (t • c) 12:40, 19 December 2024 (UTC)
Is the "above 8000 words = split" an absolute rule?
Probably should be divided or trimmed, though the scope of a topic can sometimes justify the added reading material.
> 8,000 words
May need to be divided or trimmed; likelihood goes up with size.
< 6,000 words
Length alone does not justify division or trimming.
< 150 words
If an article or list has remained this size for over two months, consider merging it with a related article. Alternatively, the article could be expanded; see Misplaced Pages:Stub.
I have seen a few instances where, an editor will raise the issue that an article is too large at, say, 7500 words or 8100 words. We have multiple history pages (and medical/psychology pages) with well over 11,000+ words, even some with over 16000. Where does one draw the line? It seems like Misplaced Pages leaves it to the discretion of the editor after about 8000 words. Plasticwonder (talk) 07:21, 18 December 2024 (UTC)
Looking at the table, it's obvious that "above 8000 words=Split" is not "an absolute rule". I promise you that if it were, that table would say something that sounded remarkably like "if the article is above 8,000 words, then it absolutely must be split".
Where one draws the line is: In a place that makes sense for the topic of that specific article, having thoughtfully considered all the facts and circumstances that apply to that unique article. WhatamIdoing (talk) 07:41, 18 December 2024 (UTC)
In addition to the above, what matters for the technical aspects of article size is not the number of words but the number of bytes. Word count can only ever be an approximation of that as the length of the words used matters ("a" is 1 byte, "comprehensive" is 13), the number and size of included media matters very significantly more. Thryduulf (talk) 09:20, 18 December 2024 (UTC)
It isn't an absolute rule, but usually an article having an extremely long high word count is evidence of a bigger problem with WP:SUMMARYSTYLE -- that it's too dense or detailed for a reader to use it as a first-port-of-call summary. As such, usually, it's a wise move to create daughter articles for the detailed material, and strim it down to its essentials in the main article; this improves the readability of the main article and allows interested readers to follow up into the nitty-gritty. As Jo-Jo Eumerus rightly says above, though, there's not really such thing as an absolute rule in this place. UndercoverClassicist09:59, 18 December 2024 (UTC)
What we now know is that many readers are looking for specific information, with few reading from top to bottom, but the search engines send them to the mother article even when a more specific daughter article exists. So the first port of call needs to be the most highly detailed. The advice in WP:SUMMARYSTYLE is therefore considered well intentioned but obsolete; stripping the mother article and pushing information down to the daughter articles defeats our whole purpose in providing information. Hawkeye7(discuss)11:31, 22 December 2024 (UTC)
When you say “we know…”, “is considered” and similar, are you pointing to specific previous discussions, RfCs etc on this matter? “In the wild”, as it were, I still see these size limits regularly invoked, even if the conversation rarely ends at them. UndercoverClassicist09:17, 23 December 2024 (UTC)
Rather than draw a line, I'd rather just remove that chart. Can't imagine why a suite of concrete word counts and procedures would ever be very helpful. — Rhododendrites \\ 16:29, 18 December 2024 (UTC)
It absolutely makes sense to say at what page sizes that editors should start considering other options, as well as where splitting can be absolutely unnecessary. Nothing wrong with the table as long as it's clear those aren't hard or fast rules. Masem (t) 16:41, 18 December 2024 (UTC)
Agreed, I find it helpful because it helps me remember what is generally too long for mobile users (I understand that mobile is generally a blindspot for us as editors because the vast majority of us don't edit on mobile but most of the readers are actually on mobile) Horse Eye's Back (talk) 16:49, 18 December 2024 (UTC)
The optimal article size varies quite a lot, actually. Key things we need to consider include:
The likely readership. Someone who's looking up History of Libya under Muammar Gaddafi probably has time to read something long and thoughtful. Someone who's looking up emergency surgery might need basic facts, in simple words, very fast.
The cognitive load associated with the topic. Star Wars is (very) long but easy to understand; Fourier inversion theorem is much shorter, but I bet it takes you longer to read, unless you have unusual expertise in mathematics.
Misplaced Pages leaves it to the discretion of editors far far before 8,000 words. We have thousands of single sentence articles to attest to this. The average article is less than 700 words. CMD (talk) 17:15, 18 December 2024 (UTC)
I've always felt that the kB of readable prose was a better metric for page size (such as is produced by various page size gadgets). Turns out, bigger words take longer to read than shorter words :P Doing it just by wordcount encourages a certain verbosity. For me, my rule of thumb has always aimed to keep big articles under 100kb readable prose. But there's no hard and fast rule, and there shouldn't be. CaptainEek⚓23:08, 22 December 2024 (UTC)
If I'm being honest, what might be the best metric is starting at the top and lightly hammering the Page Down key for a bit. If I groan before reaching the References section, it's too long. Remsense ‥ 论23:10, 22 December 2024 (UTC)
26,000 words is 1.0 tomats. Another way to look at that table is by saying that if it's more than half the length of a book, it's pushing past being "an article" and edging up towards being "a book".
Or you can look at it in terms of how many minutes reading the whole thing would take. There's quite a bit of variation, but for easy math, 300 words per minute means that a 15,000-word-long article would take 50 minutes to read, which almost certainly exceeds the interest and attention span of most readers. WhatamIdoing (talk) 00:35, 23 December 2024 (UTC)
I think the most fundamental scalar isn't quite reading time or even visual size, but structural complexity—for an online encyclopedia article, being overlong expresses itself in my increasing inability to navigate an article comfortably to read or locate what I want, or to understand the structure of the scope covered by it at a glance. Remsense ‥ 论00:38, 23 December 2024 (UTC)
Come to think of it, one thing that makes an article feel longer than its word count is if its sections, media, and other landmarks have been laid out in a careless or unnatural way. Remsense ‥ 论00:48, 23 December 2024 (UTC)
No. And this was rather a pointless, self-answering question in the first place, not something for a VP thread. The answer to the posed question of 'Is the "above 8000 words=Split" an absolute rule?' is obviously "no", both by observing actual WP community practice, and just by reading the table the OP quoted: > 8,000 words — May need to be divided or trimmed; likelihood goes up with size. Is anyone here actually confused into believing that A) "must" and "may" are synonymous, or B) that a guideline, to which reasonable exceptions sometimes apply, is somehow a legal-level policy that must be obeyed at all costs? In reality, there is never any hurry to split a large article, and doing it properly often involves a tremendous amount of work, involving both repair of citations (sometimes in great detail), and resummarizing the background context in the side article while also resummarizing the side-matter in WP:SUMMARY style within the main article (and doing them distinctly enough that the results are not obnoxiously repetitive if the reader moves between the articles). Doing a good job of this can take several days up to a month or longer of tightly focused work, depending on the detail level of the material, the number citations, etc. It is not trivial, we're all volunteers here, and our readers are not going keel over and die if they reach a detailed article that's a bit longer than they were expecting or would prefer. Ultimately, an article that is ginormous usually should split, but there is no deadline, and it needs to be done properly (plus there are often conceptually different ways to go about it from a content-flow perspective, and that might require some consensus discussion). — SMcCandlish☏¢ 😼 01:22, 23 December 2024 (UTC)
I think I linked it once in Misplaced Pages:Policies and guidelines, years ago, and someone objected. I didn't follow up to see whether the objecting editor is one of the handful who think that should is a more polite and/or IAR-compliant way to say must, but as that's a fairly uncommon POV among editors, it probably wasn't. WhatamIdoing (talk) 05:41, 23 December 2024 (UTC)
The linked document pushes very hard on should, "here may exist valid reasons in particular circumstances to ignore a particular item, but the full implications must be understood and carefully weighed" is not a low bar. It sounds much like must except when IAR. CMD (talk) 09:39, 23 December 2024 (UTC)
1: no 2: I don’t see anything wrong with the chart if you just use it as a rule of thumb; 3: I don’t know why this needed to be discussed here, rather than a Q&A desk. Dronebogus (talk) 20:50, 28 December 2024 (UTC)
Guideline against use of AI images in BLPs and medical articles?
I have recently seen AI-generated images be added to illustrate both BLPs (e.g. Laurence Boccolini, now removed) and medical articles (e.g. Legionella#Mechanism). While we don't have any clear-cut policy or guideline about these yet, they appear to be problematic. Illustrating a living person with an AI-generated image might misinform as to how that person actually looks like, while using AI in medical diagrams can lead to anatomical inaccuracies (such as the lung structure in the second image, where the pleura becomes a bronnchiole twisting over the primary bronchi), or even medical misinformation. While a guideline against AI-generated images in general might be more debatable, do we at least have a consensus for a guideline against these two specific use cases?
I personally am strongly against using AI in biographies and medical articles - as you highlighted above, AI is absolutely not reliable in generating accurate imagery and may contribute to medical or general misinformation. I would 100% support a proposal banning AI imagery from these kinds of articles - and a recommendation to not use such imagery other than in specific scenarios. jolielover♥talk12:28, 30 December 2024 (UTC)
I'd prefer a guideline prohibiting the use of AI images full stop. There are too many potential issues with accuracy, honesty, copyright, etc. Has this already been proposed or discussed somewhere? – Joe (talk) 12:38, 30 December 2024 (UTC)
There is one very specific exception I would put to a very sensible blanket prohibition on using AI images to illustrate people, especially BLPs. That is where the person themselves is known to use that image, which I have encountered in Simon Ekpa. CMD (talk) 15:00, 30 December 2024 (UTC)
While the Ekpa portrait is just an upscale (and I'm not sure what positive value that has for us over its source; upscaling does not add accuracy, nor is it an artistic interpretation meant to reveal something about the source), this would be hard to translate to the general case. Many AI portraits would have copyright concerns, not just from the individual (who may have announced some appropriate release for it), but due to the fact that AI portraits can lean heavily on uncredited individual sources. --Nat Gertler (talk) 16:04, 30 December 2024 (UTC)
For the purposes of discussing whether to allow AI images at all, we should always assume that, for the purposes of (potential) policies and guidelines, there exist AI images we can legally use to illustrate every topic. We cannot use those that are not legal (including, but not limited to, copyright violations) so they are irrelevant. An image generator trained exclusively on public domain and cc0 images (and any other licenses that explicitly allow derivative works without requiring attribution) would not be subject to any copyright restrictions (other than possibly by the prompter and/or generator's license terms, which are both easy to determine). Similarly we should not base policy on the current state of the technology, but assume that the quality of its output will improve to the point it is equal to that of a skilled human artist. Thryduulf (talk) 17:45, 30 December 2024 (UTC)
The issue is, either there are public domain/CC0 images of the person (in which case they can be used directly) or there aren't, in which case the AI is making up how a person looks. Chaotic Enby (talk · contribs) 20:00, 30 December 2024 (UTC)
We tend to use art representations either where no photographs are available (in which case, AI will also not have access to photographs) or where what we are showing is an artist's insight on how this person is perceived, which is not something that AI can give us. In any case, we don't have to build policy now around some theoretical AI in the future; we can deal with the current reality, and policy can be adjusted if things change in the future. And even that theoretical AI does make it more difficult to detect copyvio -- Nat Gertler (talk) 20:54, 30 December 2024 (UTC)
I wouldn't call it an upscale given whatever was done appears to have removed detail, but we use that image as it was specifically it is the edited image which was sent to VRT. CMD (talk) 10:15, 31 December 2024 (UTC)
Is there any clarification on using purely AI-generated images vs. using AI to edit or alter images? AI tools have been implemented in a lot of photo editing software, such as to identify objects and remove them, or generate missing content. The generative expand feature would appear to be unreliable (and it is), but I use it to fill in gaps of cloudless sky produced from stitching together photos for a panorama (I don't use it if there are clouds, or for starry skies, as it produces non-existent stars or unrealistic clouds). Photos of Japan (talk) 18:18, 30 December 2024 (UTC)
Yes, my proposal is only about AI-generated images, not AI-altered ones. That could in fact be a useful distinction to make if we want to workshop a RfC on the matter. Chaotic Enby (talk · contribs) 20:04, 30 December 2024 (UTC)
I'm not sure if we need a clear cut policy or guideline against them... I think we treat them the same way as we would treat an editor's kitchen table sketch of the same figure. Horse Eye's Back (talk) 18:40, 30 December 2024 (UTC)
For those wanting to ban AI images full stop, well, you are too late. Most professional image editing software, including the software in one's smartphone as well as desktop, uses AI somewhere. Noise reduction software uses AI to figure out what might be noise and what might be texture. Sharpening software uses AI to figure out what should be smooth and what might have a sharp detail it can invent. For example, a bird photo not sharp enough to capture feather detail will have feather texture imagined onto it. Same for hair. Or grass. Any image that has been cleaned up to remove litter or dust or spots will have the cleaned area AI generated based on its surroundings. The sky might be extended with AI. These examples are a bit different from a 100% imagined image created from a prompt. But probably not in a way that is useful as a rule.
I think we should treat AI generated images the same as any user-generated image. It might be a great diagram or it might be terrible. Remove it from the article if the latter, not because someone used AI. If the image claims to photographically represent something, we may judge whether the creator has manipulated the image too much to be acceptable. For example, using AI to remove a person in the background of an image taken of the BLP subject might be perfectly fine. People did that with traditional Photoshop/Lightroom techniques for years. Using AI to generate what claims to be a photo of a notable person is on dodgy ground wrt copyright. -- Colin°19:12, 30 December 2024 (UTC)
I'm talking about the case of using AI to generate a depiction of a living person, not using AI to alter details in the background. That is why I only talk about AI-generated images, not AI-altered images. Chaotic Enby (talk · contribs) 20:03, 30 December 2024 (UTC)
Regarding some sort of brightline ban on the use of any such image in anything article medical related: absolutely not. For example, if someone wanted to use AI tools as opposed to other tools to make an image such as this one (as used in the "medical" article Fluconazole) I don't see a problem, so long as it is accurate. Accurate models and illustrations are useful and that someone used AI assistance as opposed to a chisel and a rock is of no concern. — xaosflux19:26, 30 December 2024 (UTC)
I believe that the appropriateness of AI images depends on how its used by the user. In BLP and medical articles, it is inappropriate for the images, but it is inappropriate to ban it completely across thw site. By the same logic, if you want full ban of AI, you are banning fire just because people can get burned, without considering cooking. JekyllTheFabulous (talk) 13:33, 31 December 2024 (UTC)
AI generated medical related image. No idea if this is accurate, but if it is I don't see what the problem would be compared to if this was made with ink and paper. — xaosflux00:13, 31 December 2024 (UTC)
I agree that AI-generated images should not be used in most cases. They essentially serve as misinformation. I also don't think that they're really comparable to drawings or sketches because AI-generation uses a level of photorealism that can easily trick the untrained eye into thinking it is real. Di (they-them) (talk) 20:46, 30 December 2024 (UTC)
AI doesn't need to be photorealistic though. I see two potential issues with AI. The first is images that might deceive the viewer into thinking they are photos, when they are not. The second is potential copyright issues. Outside of the copyright issues I don't see any unique concerns for an AI-generated image (that doesn't appear photorealistic). Any accuracy issues can be handled the same way a user who manually drew an image could be handled. Photos of Japan (talk) 21:46, 30 December 2024 (UTC)
AI-generated depictions of BLP subjects are often more "illustrative" than drawings/sketches of BLP subjects made by 'regular' editors like you and me. For example, compare the AI-generated image of Pope Francis and the user-created cartoon of Brigette Lundy-Paine. Neither image belongs on their respective bios, of course, but the AI-generated image is no more "misinformation" than the drawing. Some1 (talk) 00:05, 31 December 2024 (UTC)
I would argue the opposite: neither are made up, but the first one, because of its realism, might mislead readers into thinking that it is an actual photograph, while the second one is clearly a drawing. Which makes the first one less illustrative, as it carries potential for misinformation, despite being technically more detailed. Chaotic Enby (talk · contribs) 00:31, 31 December 2024 (UTC)
AI-generated images should always say "AI-generated image of " in the image caption. No misleading readers that way. Some1 (talk) 00:36, 31 December 2024 (UTC)
Yes, and they don't always do it, and we don't have a guideline about this either. The issue is, many people have many different proposals on how to deal with AI content, meaning we always end up with "no consensus" and no guidelines on use at all, even if most people are against it. Chaotic Enby (talk · contribs) 00:40, 31 December 2024 (UTC)
always end up with "no consensus" and no guidelines on use at all, even if most people are against it Agreed. Even a simple proposal to have image captions note whether an image is AI-generated will have editors wikilawyer over the definition of 'AI-generated.' I take back my recommendation of starting an RfC; we can already predict how that RfC will end. Some1 (talk) 02:28, 31 December 2024 (UTC)
We should absolutely not be including any AI images in anything that is meant to convey facts (with the obvious exception of an AI image illustrating the concept of an AI image). I also don't think we should be encouraging AI-altered images -- the line between "regular" photo enhancement and what we'd call "AI alteration" is blurry, but we shouldn't want AI edits for the same reason we wouldn't want fake Photoshop composites.
That said, I would assume good faith here: some of these images are probably being sourced from Commons, and Commons is dealing with a lot of undisclosed AI images. Gnomingstuff (talk) 23:31, 30 December 2024 (UTC)
Do you really mean to ban single images showing the way birds use their wings?
Sorry, should have been more clear -- composites that present themselves as the real thing, basically what people would use deepfakes for now. Gnomingstuff (talk) 20:20, 31 December 2024 (UTC)
I don't think any guideline, let alone policy, would be beneficial and indeed on balance is more likely to be harmful. There are always only two questions that matter when determining whether we should use an image, and both are completely independent of whether the image is AI-generated or not:
Can we use this image in this article? This depends on matters like copyright, fair use, whether the image depicts content that is legal for an organisation based in the United States to host, etc. Obviously if the answer is "no", then everything else is irrelevant, but as the law and WMF, Commons and en.wp policies stand today there exist some images in both categories we can use, and some images in both categories we cannot use.
Does using this image in this article improve the article? This is relative to other options, one of which is always not using any image, but in many cases also involves considering alternative images that we can use. In the case of depictions of specific, non-hypothetical people or objects one criteria we use to judge whether the image improves the article is whether it is an accurate representation of the subject. If it is not an accurate representation then it doesn't improve the article and thus should not be used, regardless of why it is inaccurate. If it is an accurate representation, then its use in the article will not be misrepresentative or misleading, regardless of whether it is or is not AI generated. It may or may not be the best option available, but if it is then it should be used regardless of whether it is or is not AI generated.
The potential harm I mentioned above is twofold, firstly Misplaced Pages is, by definition, harmed when an images exists we could use that would improve an article but we do not use it in that article. A policy or guideline against the use of AI images would, in some cases, prevent us from using an image that would improve an article. The second aspect is misidentification of an image as AI-generated when it isn't, especially when it leads to an image not being used when it otherwise would have been.
Finally, all the proponents of a policy or guideline are assuming that the line between images that are and are not AI-generated is sharp and objective. Other commenters here have already shown that in reality the line is blurry and it is only going to get blurrier in the future as more AI (and AI-based) technology is built into software and especially firmware. Thryduulf (talk) 00:52, 31 December 2024 (UTC)
I agree with almost the entirety of your post with a caveat on whether something "is an accurate representation". We can tell whether non-photorealistic images are accurate by assessing whether the image accurately conveys the idea of what it is depicting. Photos do more than convey an idea, they convey the actual look of something. With AI generated images that are photorealistic it is difficult to assess whether they accurately convey the look of something (the shading might be illogical in subtle ways, there could be an extra finger that goes unnoticed, a mole gets erased), but readers might be deceived by the photo-like presentation into thinking they are looking at an actual photographic depiction of the subject which could differ significantly from the actual subject in ways that go unnoticed. Photos of Japan (talk) 04:34, 31 December 2024 (UTC)
A policy or guideline against the use of AI images would, in some cases, prevent us from using an image that would improve an article. That's why I'm suggesting a guideline, not a policy. Guidelines are by design more flexible, and WP:IAR still does (and should) apply in edge cases.The second aspect is misidentification of an image as AI-generated when it isn't, especially when it leads to an image not being used when it otherwise would have been. In that case, there is a licensing problem. AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated.Finally, all the proponents of a policy or guideline are assuming that the line between images that are and are not AI-generated is sharp and objective. Other commenters here have already shown that in reality the line is blurry and it is only going to get blurrier in the future as more AI (and AI-based) technology is built into software and especially firmware. In that case, it's mostly because the ambiguity in wording: AI-edited images are very common, and are sometimes called "AI-generated", but here we should focus on actual prompt outputs, of the style "I asked a model to generate me an image of a BLP". Chaotic Enby (talk · contribs) 11:13, 31 December 2024 (UTC)
Simply not having a completely unnecessary policy or guideline is infinitely better than relying on IAR - especially as this would have to be ignored every time it is relevant. When the AI image is not the best option (which obviously includes all the times its unsuitable or inaccurate) existing policies, guidelines, practice and frankly common sense mean it won't be used. This means the only time the guideline would be relevant is when an AI image is the best option and as we obviously should be using the best option in all cases we would need to ignore the guideline against using AI images.
AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated. The key words here are "supposed to be" and "shouldn't", editors absolutely will speculate that images are AI-generated and that the Commons labelling is incorrect. We are supposed to assume good faith, but this very discussion shows that when it comes to AI some editors simply do not do that.
Regarding your final point, that might be what you are meaning but it is not what all other commenters mean when they want to exclude all AI images. Thryduulf (talk) 11:43, 31 December 2024 (UTC)
For your first point, the guideline is mostly to take care of the "prompt fed in model" BLP illustrations, where it is technically hard to prove that the person doesn't look like that (as we have no available image), but the model likely doesn't have any available image either and most likely just made it up. As my proposal is essentially limited to that (I don't include AI-edited images, only those that are purely generated by a model), I don't think there will be many cases where IAR would be needed.Regarding your two other points, you are entirely correct, and while I am hoping for nuance on the AI issue, it is clear that some editors might not do that. For the record, I strongly disagree with a blanket ban of "AI images" (which includes both blatant "prompt in model" creations and a wide range of more subtle AI retouching tools) or anything like that. Chaotic Enby (talk · contribs) 11:49, 31 December 2024 (UTC)
the guideline is mostly to take care of the "prompt fed in model" BLP illustrations, where it is technically hard to prove that the person doesn't look like that (as we have no available image). There are only two possible scenarios regarding verifiability:
The image is an accurate representation and we can verify that (e.g. by reference to non-free photos).
Verifiability is no barrier to using the image, whether it is AI generated or not.
If it is the best image available, and editors agree using it is better than not having an image, then it should be used whether it is AI generated or not.
The image is either not an accurate representation, or we cannot verify whether it is or is not an accurate representation
The only reasons we should ever use the image are:
It has been the subject of notable commentary and we are presenting it in that context.
The subject verifiably uses it as a representation of themselves (e.g. as an avatar or logo)
This is already policy, whether the image is AI generated or not is completely irrelevant.
In your first scenario, there is the issue of an accurate AI-generated image misleading people into thinking it is an actual photograph of the person, especially as they are most often photorealistic. Even besides that, a mostly accurate representation can still introduce spurious details, and this can mislead readers as they do not know to what level it is actually accurate. This scenario doesn't really happen with drawings (which are clearly not photographs), and is very much a consequence of AI-generated photorealistic pictures being a thing.In the second scenario, if we cannot verify that it is not an accurate representation, it can be hard to remove the image with policy-based reasons, which is why a guideline will again be helpful. Having a single guideline against fully AI-generated images takes care of all of these scenarios, instead of having to make new specific guidelines for each case that emerges because of them. Chaotic Enby (talk · contribs) 13:52, 31 December 2024 (UTC)
If the image is misleading or unverifiable it should not be used, regardless of why it is misleading or unverifiable. This is existing policy and we don't need anything specifically regarding AI to apply it - we just need consensus that the image is misleading or unverifiable. Whether it is or is not AI generated is completely irrelevant. Thryduulf (talk) 15:04, 31 December 2024 (UTC)
AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated.
I mean... yes, we should? At the very least Commons should go hunting for mislabeled images -- that's the whole point of license review. The thing is that things are absolutely swamped over there and there are hundreds of thousands of images waiting for review of some kind. Gnomingstuff (talk) 20:35, 31 December 2024 (UTC)
I just mean that given the reality of the backlogs, there are going to be mislabeled images, and there are almost certainly going to be more of them over time. That's just how it is. We don't have control over that, but we do have control over what images go into articles, and if someone has legitimate concerns about an image being AI-generated, then they should be raising those. Gnomingstuff (talk) 20:45, 31 December 2024 (UTC)
Support blanket ban on AI-generated images on Misplaced Pages. As others have highlighted above, the is not just a slippery slope but an outright downward spiral. We don't use AI-generated text and we shouldn't use AI-generated images: these aren't reliable and they're also WP:OR scraped from who knows what and where. Use only reliable material from reliable sources. As for the argument of 'software now has AI features', we all know that there's a huge difference between someone using a smoothing feature and someone generating an image from a prompt. :bloodofox: (talk) 03:12, 31 December 2024 (UTC)
Reply, the section of WP:OR concerning images is WP:OI which states "Original images created by a Wikimedian are not considered original research, so long as they do not illustrate or introduce unpublished ideas or arguments". Using AI to generate an image only violates WP:OR if you are using it to illustrate unpublished ideas, which can be assessed just by looking at the image itself. COPYVIO, however, cannot be assessed from looking at just the image alone, which AI could be violating. However, some images may be too simple to be copyrightable, for example AI-generated images of chemicals or mathematical structures potentially. Photos of Japan (talk) 04:34, 31 December 2024 (UTC)
Prompt generated images are unquestionably violation of WP:OR and WP:SYNTH: Type in your description and you get an image scraping who knows what and from who knows where, often Misplaced Pages. Misplaced Pages isn't an WP:RS. Get real. :bloodofox: (talk) 23:35, 1 January 2025 (UTC)
"Unquestionably"? Let me question that, @Bloodofox. ;-)
If an editor were to use an AI-based image-generating service and the prompt is something like this:
"I want a stacked bar chart that shows the number of games won and lost by FC Bayern Munich each year. Use the team colors, which are red #DC052D, blue #0066B2, and black #000000. The data is:
2014–15: played 34 games, won 25, tied 4, lost 5
2015–16: played 34 games, won 28, tied 4, lost 2
2016–17: played 34 games, won 25, tied 7, lost 2
2017–18: played 34 games, won 27, tied 3, lost 4
2018–19: played 34 games, won 24, tied 6, lost 4
2019–20: played 34 games, won 26, tied 4, lost 4
2020–21: played 34 games, won 24, tied 6, lost 4
2021–22: played 34 games, won 24, tied 5, lost 5
2022–23: played 34 games, won 21, tied 8, lost 5
2023–24: played 34 games, won 23, tied 3, lost 8"
I would expect it to produce something that is not a violation of either OR in general or OR's SYNTH section specifically. What would you expect, and why do you think it would be okay for me to put that data into a spreadsheet and upload a screenshot of the resulting bar chart, but you don't think it would be okay for me to put that same data into a image generator, get the same thing, and upload that?
Assuming you'd even get what you requested the model without fiddling with the prompt for a while, these sort of 'but we can use it for graphs and charts' devil's advocate scenarios aren't helpful. We're discussing generating images of people, places, and objects here and in those cases, yes, this would unquestionably be a form of WP:OR & WP:SYNTH. As for the charts and graphs, there are any number of ways to produce these. :bloodofox: (talk) 03:07, 2 January 2025 (UTC)
We're discussing generating images of people, places, and objects here The proposal contains no such limitation. and in those cases, yes, this would unquestionably be a form of WP:OR & WP:SYNTH. Do you have a citation for that? Other people have explained better than I can how that it is not necessarily true, and certainly not unquestionable. Thryduulf (talk) 03:14, 2 January 2025 (UTC)
As you're well aware, these images are produced by scraping and synthesized material from who knows what and where: it's ultimately pure WP:OR to produce these fake images and they're a straightforward product of synthesis of multiple sources (WP:SYNTH) - worse yet, these sources are unknown because training data is by no means transparent. Personally, I'm strongly for a total ban on generative AI on the site exterior to articles on the topic of generative AI. Not only do I find this incredible unethical, I believe it is intensely detrimental to Misplaced Pages, which is an already a flailing and shrinking project. :bloodofox: (talk) 03:23, 2 January 2025 (UTC)
So you think the lead image at Gisèle Pelicot is a SYNTH violation? Its (human) creator explicitly says "This is not done from one specific photo. As I usually do when I draw portraits of people that I can't see in person, I look at a lot of photos of them and then create my own rendition" in the image description, which sounds like the product of synthesis of multiple sources" to me, and "these sources are unknown because" the the images the artist looked at are not disclosed.
A lot of my concern about blanket statements is the principle that what's sauce for the goose is sauce for the gander, too. If it's okay for a human to do something by hand, then it should be okay for a human using a semi-automated tool to do it, too.
(Just in case you hadn't heard, the rumors that the editor base is shrinking have been false for over a decade now. Compared to when you created your account in mid-2005, we have about twice as many high-volume editors.) WhatamIdoing (talk) 06:47, 2 January 2025 (UTC)
Review WP:SYNTH and your attempts at downplaying a prompt-generated image as "semi-automated" shows the root of the problem: if you can't detect the difference between a human sketching from a reference and a machine scraping who-knows-what on the internet, you shouldn't be involved in this discussion. As for editor retention, this remains a serious problem on the site: while the site continues to grow (and becomes core fodder for AI-scraping) and becomes increasingly visible, editorial retention continues to drop. :bloodofox: (talk) 09:33, 2 January 2025 (UTC)
Please scroll down below SYNTH to the next section titled "What is not original research" which begins with WP:OI, our policies on how images relate to OR. OR (including SYNTH) only applies to images with regards to if they illustrate "unpublished ideas or arguments". It does not matter, for instance, if you synthesize an original depiction of something, so long as the idea of that thing is not original. Photos of Japan (talk) 09:55, 2 January 2025 (UTC)
Yes, which explicitly states:
It is not acceptable for an editor to use photo manipulation to distort the facts or position illustrated by an image. Manipulated images should be prominently noted as such. Any manipulated image where the encyclopedic value is materially affected should be posted to Misplaced Pages:Files for discussion. Images of living persons must not present the subject in a false or disparaging light.
Using a machine to generate a fake image of someone is far beyond "manipulation" and it is certainly "false". Clearly we need explicit policies on AI-generated images of people or we wouldn't be having this discussion, but this as it stands clarly also falls under WP:SYNTH: there is zero question that this is a result of "synthesis of published material", even if the AI won't list what it used. Ultimately it's just a synthesis of a bunch of published composite images of who-knows-what (or who-knows-who?) the AI has scraped together to produce a fake image of a person. :bloodofox: (talk) 10:07, 2 January 2025 (UTC)
The latter images you describe should be SVG regardless. If there are models that can generate that, that seems totally fine since it can be semantically altered by hand. Any generation with photographic or "painterly" characteristics (e.g. generating something in the style of a painting or any other convention of visual art that communicates aesthetic particulars and not merely abstract visual particulars) seems totally unacceptable. Remsense ‥ 论07:00, 31 December 2024 (UTC)
100 dots: 99 chocolate-colored dots and 1 baseball-shaped dot
@Bloodofox, here's an image I created. It illustrates the concept of 1% in an article. I made this myself, by typing 100 emojis and taking a screenshot. Do you really mean to say that if I'd done this with an image-generating AI tool, using a prompt like "Give me 100 dots in a 10 by 10 grid. Make 99 a dark color and 1, randomly placed, look like a baseball" that it would be hopelessly tainted, because AI is always bad? Or does your strongly worded statement mean something more moderate?
I'd worry about photos of people (including dead people). I'd worry about photos of specific or unique objects that have to be accurate or they're worse than worthless (e.g., artwork, landmarks, maps). But I'm not worried about simple graphs and charts like this one, and I'm not worried about ordinary, everyday objects. If you want to use AI to generate a photorealistic image of a cookie, or a spoon, and the output you get genuinely looks like those objects, I'm not actually going to worry about it. WhatamIdoing (talk) 06:57, 31 December 2024 (UTC)
As you know, Misplaced Pages has the unique factor of being entirely volunteer-ran. Misplaced Pages has fewer and fewer editors and, long-term, we're seeing plummeting birth rates in areas where most Misplaced Pages editors do exist. I wouldn't expect a wave of new ones aimed at keeping the site free of bullshit in the near future.
In addition, the Wikimedia Foundation's hair-brained continued effort to turn the site into its political cash machine is no doubt also not helping, harming the site's public perception and leading to fewer new editors.
Over the course of decades (I've been here for around 20 years), it seems clear that the site will be negatively impacted by all this, especially in the face of generative AI.
As a long-time editor who has frequently stumbled upon intense WP:PROFRINGE content, fended off armies of outside actors looking to shape the site into their ideological image (and sent me more than a few death threats), and who has identified large amount of politically-motivated nonsense explicitly designed to fool non-experts in areas I know intimately well (such as folklore and historical linguistics topics), I think it need be said that the use of generative AI for content is especially dangerous because of its capabilities of fooling Misplaced Pages readers and Misplaced Pages editors alike.
Misplaced Pages is written by people for people. We need to draw a line in the sand to keep from being flooded by increasingly accessible hoax-machines.
A blanket ban on generative AI resolves this issue or at least hands us another tool with which to attempt to fight back. We don't need what few editors we have here wasting what little time they can give the project checking over an ocean of AI-generated slop: we need more material from reliable sources and better tools to fend off bad actors usable by our shrinking editor base (anyone at the Wikimedia Foundation listening?), not more waves of generative AI garbage. :bloodofox: (talk) 07:40, 31 December 2024 (UTC)
A blanket ban doesn't actually resolve most of the issues though, and introduces new ones. Bad usages of AI can already be dealt with by existing policy, and malicious users will ignore a blanket ban anyways. Meanwhile, a blanket ban would harm many legitimate usages for AI. For instance, the majority of professional translators (at least Japanese to English) incorporate AI (or similar tools) into their workflow to speed up translations. Just imagine a professional translator who uses AI to help generate rough drafts of foreign language Misplaced Pages articles, before reviewing and correcting them, and another editor learning of this and mass reverting them for breaking the blanket ban, and ultimately causing them to leave. Many authors (particularly with carpal tunnel) use AI now to control their voice-to-text (you can train the AI on how you want character names spelled, the formatting of dialogue and other text, etc.). A wikipedia editor could train an AI to convert their voice into Misplaced Pages-formatted text. AI is subtly incorporated now into spell-checkers, grammar-checkers, photo editors, etc., in ways many people are not aware of. A blanket AI ban has the potential to cause many issues for a lot of people, without actually being that affective at dealing with malicious users. Photos of Japan (talk) 08:26, 31 December 2024 (UTC)
I think this is the least convincing one I've seen here yet: It contains the ol' 'there are AI features in programs now' while also attempting to invoke accessibility and a little bit of 'we must have machines to translate!'.
As a translator myself, I can only say: Oh please. Generative AI is notoriously terrible at translating and that's not likely to change. And I mean ever beyond a very, very basic level. Due to the complexities of communication and little matters like nuance, all machine translated material must be thoroughly checked and modified by, yes, human translators, who often encounter it spitting out complete bullshit scraped from who-knows-where (often Misplaced Pages itself).
I get that this topic attracts a lot of 'but what if generative AI is better than humans?' from the utopian tech crowd but the reality is that anyone who needs a machine to invent text and visuals for whatever reason simply shouldn't be using it on Misplaced Pages.
Either you, a human being, can contribute to the project or you can't. Slapping a bunch of machine-generated (generative AI) visuals and text (much of it ultimately coming from Misplaced Pages in the first place!) isn't some kind of human substitute, it's just machine-regurgitated slop and is not helping the project.
Over three thousand full-time professional translators from around the world responded to the surveys, which were broken into a survey for CAT tool users and one for those who do not use any CAT tool at all.
88% of respondents use at least one CAT tool for at least some of their translation tasks.
Of those using CAT tools, 83% use a CAT tool for most or all of their translation work.
Mind you, traditionally CAT tools didn't use AI, but many do now, which only adds to potential sources of confusion in a blanket ban of AI. Photos of Japan (talk) 17:26, 31 December 2024 (UTC)
You're barking up the tree with the pro-generative AI propaganda in response to me. I think we're all quite aware that generative AI tool integration is now common and that there's also a big effort to replace human translators — and anything that can be "written" with machines-generated text. I'm also keenly aware that generative AI is absolutely horrible at translation and all of it must be thoroughly checked by humans, as you would be if you were a translator yourself. :bloodofox: (talk) 22:20, 31 December 2024 (UTC)
"all machine translated material must be thoroughly checked and modified by, yes, human translators"
There are translators (particularly with non-creative works) who are using these tools to shift more towards reviewing. It should be up to them to decide what they think is the most efficient method for them. Photos of Japan (talk) 06:48, 1 January 2025 (UTC)
And any translator who wants to use generative AI to attempt to translate can do so off the site. We're not here to check it for them. I strongly support a total ban on any generative AI used on the site exterior to articles on generative AI. :bloodofox: (talk) 11:09, 1 January 2025 (UTC)
I wonder what you mean by "on the site". The question here is "Is it okay for an editor to go to a completely different website, generate an image all by themselves, upload it to Commons, and put it in a Misplaced Pages article?" The question here is not "Shall we put AI-generating buttons on Misplaced Pages's own website?" WhatamIdoing (talk) 02:27, 2 January 2025 (UTC)
I'm talking about users slapping machine-translated and/or machine-generated nonsense all over the site, only for us to have to go behind and not only check it but correct it. It takes users minutes to do this and it's already happening. It's the same for images. There are very few of us who volunteer here and our numbers are growing fewer. We need to be spending our time improving the site rather than opening the gate as wide as possible for a flood of AI-generated/rendered garbage. The site has enough problems that compound every day rather than having to fend off users armed with hoax machines at every corner. :bloodofox: (talk) 03:20, 2 January 2025 (UTC)
Sure, we're all opposed to "nonsense", but my question is: What about when the machine happens to generate something that is not "nonsense"?
I have some worries about AI content. I worry, for example, that they'll corrupt our sources. I worry that List of scholarly publishing stings will get dramatically longer, and also that even more undetected, unconfessed, unretracted papers will get published and believed to be true and trustworthy. I worry that academia will go back to a model in which personal connections are more important, because you really can't trust what's published. I worry that scientific journals will start refusing to publish research unless it comes from someone employed by a trusted institution, that is willing to put its reputation on the line by saying they have directly verified that the work described in the paper was actually performed to their standards, thus scuttling the citizen science movement and excluding people whose institutions are upset with them for other reasons (Oh, you thought you'd take a job elsewhere? Well, we refuse to certify the work you did for the last three years...).
But I'm not worried about a Misplaced Pages editor saying "Hey AI, give me a diagram of swingset" or "Make a chart for me out of the data I'm going to give you". In fact, if someone wants to pull the numbers out of Template:Misplaced Pages editor graph (100 per month), feed it to an AI, and replace the template's contents with an AI-generated image (until they finally fix the Graphs extension), I'd consider that helpful. WhatamIdoing (talk) 07:09, 2 January 2025 (UTC)
Translators are not using generative AI for translation, the applicability of LLMs to regular translation is still in its infancy and regardless will not be implementing any generative faculties to its output since that is the exact opposite of what translation is supposed to do. JoelleJay (talk) 02:57, 2 January 2025 (UTC)
Translators are not using generative AI for translation this entirely depends on what you mean by "generative". There are at least three contradictory understandings of the term in this one thread alone. Thryduulf (talk) 03:06, 2 January 2025 (UTC)
Please, you can just go through the entire process with a simple prompt command now. The results are typically shit but you can generate a ton of it quickly, which is perfect for flooding a site like this one — especially without a strong policy against it. I've found myself cleaning up tons of AI-generated crap (and, yes, rendered) stuff here and elsewhere, and now I'm even seeing AI-generated responses to my own comments. It's beyond ridiculous. :bloodofox: (talk) 03:20, 2 January 2025 (UTC)
Ban AI-generated from all articles, AI anything from BLP and medical articles is the position that seems it would permit all instances where there are plausible defenses that AI use does not fabricate or destroy facts intended to be communicated in the context of the article. That scrutiny is stricter with BLP and medical articles in general, and the restriction should be stricter to match. Remsense ‥ 论06:53, 31 December 2024 (UTC)
I think my previous comment is operative: almost anything we can see AI used programmatically to generate should be SVG, not raster—even if it means we are embedding raster images in SVG to generate examples like the above. I do not know if there are models that can generate SVG, but if there are I happily state I have no problem with that. I think I'm at risk of seeming downright paranoid—but understanding how errors can propagate and go unnoticed in practice, if we're to trust a black box, we need to at least be able to check what the black box has done on a direct structural level. Remsense ‥ 论07:02, 31 December 2024 (UTC)
Makes perfect sense that there would be. Again, maybe I come off like a paranoid lunatic, but I really need either the ability to check what the thing is doing, or the ability to check and correct exactly what a black box has done. (In my estimation, if you want to know what procedures person has done, theoretically you can ask them to get a fairly satisfactory result, and the pre-AI algorithms used in image manipulation are canonical and more or less transparent. Acknowledging human error etc., with AI there is not even the theoretical promise that one can be given a truthful account of how it decided to do what it did.) Remsense ‥ 论07:18, 31 December 2024 (UTC)
Like everyone said, there should be a de facto ban on using AI images in Misplaced Pages articles. They are effectively fake images pretending to be real, so they are out of step with the values of Misplaced Pages.--♦IanMacM♦08:20, 31 December 2024 (UTC)
Except, not everybody has said that, because the majority of those of us who have refrained from hyperbole have pointed out that not all AI images are "fake images pretending to be real" (and those few that are can already be removed under existing policy). You might like to try actually reading the discussion before commenting further. Thryduulf (talk) 10:24, 31 December 2024 (UTC)
@Remsense, exactly how much "ability to check what the thing is doing" do you need to be able to do, when the image shows 99 dots and 1 baseball, to illustrate the concept of 1%? If the image above said {{pd-algorithm}} instead of {{cc-by-sa-4.0}}, would you remove if from the article, because you just can't be sure that it shows 1%? WhatamIdoing (talk) 02:33, 2 January 2025 (UTC)
The above is a useful example to an extent, but it is a toy example. I really do think i is required in general when we aren't dealing with media we ourselves are generating. Remsense ‥ 论04:43, 2 January 2025 (UTC)
How do we differentiate in policy between a "toy example" (that really would be used in an article) and "real" examples? Is it just that if I upload it, then you know me, and assume I've been responsible? WhatamIdoing (talk) 07:13, 2 January 2025 (UTC)
There definitely exist generative AI for SVG files. Here's an example: I used generative AI in Adobe Illustrator to generate the SVG gear in File:Pinwheel scheduling.svg (from Pinwheel scheduling) before drawing by hand the more informative parts of the image. The gear drawing is not great (a real gear would have uniform tooth shape) but maybe the shading is better than I would have done by hand, giving an appearance of dimensionality and surface material while remaining deliberately stylized. Is that the sort of thing everyone here is trying to forbid?
I can definitely see a case for forbidding AI-generated photorealistic images, especially of BLPs, but that's different from human oversight of AI in the generation of schematic images such as this one. —David Eppstein (talk) 01:15, 1 January 2025 (UTC)
I'd include BDPs, too. I had to get a few AI-generated images of allegedly Haitian presidents deleted a while ago. The "paintings" were 100% fake, right down to the deformed medals on their military uniforms. An AI-generated "generic person" would be okay for some purposes. For a few purposes (e.g., illustrations of Obesity) it could even be preferable to have a fake "person" than a real one. But for individual/named people, it would be best not to have anything unless it definitely looks like the named person. WhatamIdoing (talk) 07:35, 2 January 2025 (UTC)
Of course, that's why I'm only looking at specific cases and refrain from proposing a blanket ban on generative AI. Regarding Donald Trump, we do have one AI-generated image of him that is reasonable to allow (in Springfield pet-eating hoax), as the image itself was the subject of relevant commentary. Of course, this is different from using an AI-generated image to illustrate Donald Trump himself, which is what my proposal would recommend against. Chaotic Enby (talk · contribs) 11:32, 31 December 2024 (UTC)
That's certainly true, but others are adopting much more extreme positions than you are, and it was the more extreme views that I wished to challenge.—S MarshallT/C11:34, 31 December 2024 (UTC)
Going off WAID's example above, perhaps we should be trying to restrict the use of AI where image accuracy/precision is essential, as it would be for BLP and medical info, among other cases, but in cases where we are talking generic or abstract concepts, like the 1% image, it's use is reasonable. I would still say we should strongly prefer am image made by a human with high control of the output, but when accuracy is not as important as just the visualization, it's reasonable to turn to AI to help. Masem (t) 15:12, 31 December 2024 (UTC)
Support total ban of AI imagery - There are probable copyright problems and veracity problems with anything coming out of a machine. In a word of manipulated reality, Misplaced Pages will be increasingly respected for holding a hard line against synthetic imagery. Carrite (talk) 15:39, 31 December 2024 (UTC)
For both issues AI vs not AI is irrelevant. For copyright, if the image is a copyvio we can't use it regardless of whether it is AI or not AI, if it's not a copyvio then that's not a reason to use or not use the image. If the images is not verifiably accurate then we already can (and should) exclude it, regardless of whether it is AI or not AI. For more detail see the extensive discussion above you've either not read or ignored. Thryduulf (talk) 16:34, 31 December 2024 (UTC)
Yes, we absolutely should ban the use of AI-generated images in these subjects (and beyond, but that's outside the scope of this discussion). AI should not be used to make up a simulation of a living person. It does not actually depict the person and may introduce errors or flaws that don't actually exist. The picture does not depict the real person because it is quite simply fake.
Even worse would be using AI to develop medical images in articles in any way. The possibility for error there is unacceptable. Yes, humans make errors too, but there there is a) someone with the responsibility to fix it and b) someone conscious who actually made the picture, rather than a black box that spat it out after looking at similar training data. Cremastra 🎄 u — c 🎄 20:08, 31 December 2024 (UTC)
It's incredibly disheartening to see multiple otherwise intelligent editors who have apparently not read and/or not understood what has been said in the discussion but rather responding with what appears to be knee-jerk reactions to anti-AI scaremongering. The sky will not fall in, Misplaced Pages is not going to be taken over by AI, AI is not out to subvert Misplaced Pages, we already can (and do) remove (and more commonly not add in the first placE) false and misleading information/images. Thryduulf (talk) 20:31, 31 December 2024 (UTC)
So what benefit does allowing AI images bring? We shouldn't be forced to decide these on a case-by-case basis.
I'm sorry to dishearten you, but I still respectfully disagree with you. And I don't think this is "scaremongering" (although I admit that if it was, I would of course claim it wasn't). Cremastra 🎄 u — c 🎄 21:02, 31 December 2024 (UTC) Cremastra 🎄 u — c 🎄 20:56, 31 December 2024 (UTC)
Determining what benefits any image brings to Misplaced Pages can only be done on a case-by-case basis. It is literally impossible to know whether any image improves the encyclopaedia without knowing the context of which portion of what article it would illustrate, and what alternative images are and are not available for that same spot.
The benefit of allowing AI images is that when an AI image is the best option for a given article we use it. We gain absolutely nothing by prohibiting using the best image available, indeed doing so would actively harm the project without bringing any benefits. AI images that are misleading, inaccurate or any of the other negative things any image can be are never the best option and so are never used - we don't need any policies or guidelines to tell us that. Thryduulf (talk) 21:43, 31 December 2024 (UTC)
Support blanket ban on AI-generated text or images in articles, except in contexts where the AI-generated content is itself the subject of discussion (in a specific or general sense). Generative AI is fundamentally at odds with Misplaced Pages's mission of providing reliable information, because of its propensity to distort reality or make up information out of whole cloth. It has no place in our encyclopedia. —pythoncoder (talk | contribs) 21:34, 31 December 2024 (UTC)
Support blanket ban on AI-generated images except in ABOUTSELF contexts. This is especially a problem given the preeminence Google gives to Misplaced Pages images in its image search. JoelleJay (talk) 22:49, 31 December 2024 (UTC)
Ban across the board, except in articles which are actually about AI-generated imagery or the tools used to create them, or the image itself is the subject of substantial commentary within the article for some reason. Even in those cases, clearly indicating that the image is AI-generated should be required. Seraphimblade00:29, 1 January 2025 (UTC)
Oppose blanket bans that would forbid the use of AI assistance in creating diagrams or other deliberately stylized content. Also oppose blanket bans that would forbid AI illustrations in articles about AI illustrations. I am not opposed to banning photorealistic AI-generated images in non-AI-generation contexts or banning AI-generated images from BLPs unless the image itself is specifically relevant to the subject of the BLP. —David Eppstein (talk) 01:27, 1 January 2025 (UTC)
Oppose blanket bans AI is just a new buzzword so, for example, Apple phones now include "Apple Intelligence" as a standard feature. Does this means that photographs taken using Apple phones will be inadmissable? That would be silly because legacy technologies are already rife with issues of accuracy and verification. For example, there's an image on the main page right now (right). This purports to be a particular person ("The Father of Australia") but, if you check the image description, you find that it may have been his brother and even the attribution to the artist is uncertain. AI features may help in exposing such existing weaknesses in our image use and so we should be free to use them in an intelligent way. Andrew🐉(talk) 08:03, 1 January 2025 (UTC)
So, you expect an the AI, notoriously trained on Misplaced Pages (and whatever else is floating around on the internet), to correct Misplaced Pages where humans have failed... using the data it scraped from Misplaced Pages (and who knows where else)? :bloodofox: (talk) 11:12, 1 January 2025 (UTC)
I tried using the Deep Research option of Gemini to assess the attribution of the Macquarie portrait. Its stated methodology seemed quite respectable and sensible.
The Opie Portrait of Lachlan Macquarie: An Examination of its Attribution: Methodology
To thoroughly investigate the attribution of the Opie portrait of Lachlan Macquarie, a comprehensive research process was undertaken. This involved several key steps:
Gathering information on the Opie portrait: This included details about its history, provenance, and any available information on its cost.
Reviewing scholarly articles and publications: This step focused on finding academic discussions specifically addressing the attribution of the portrait to John Opie.
Collecting expert opinions: Statements and opinions from art experts and historians were gathered to understand the range of perspectives on the certainty of the attribution.
Examining historical documents and records: This involved searching for any records that could shed light on the portrait's origins and authenticity, such as Macquarie's personal journals or contemporary accounts.
Exploring scientific and technical analyses: Information was sought on any scientific or technical analyses conducted on the portrait, such as pigment analysis or canvas dating, to determine its authenticity.
Comparing the portrait to other Opie works: This step involved analyzing the style and technique of the Opie portrait in comparison to other known portraits by Opie to identify similarities and differences.
It was quite transparent in listing and citing the sources that it used for its analysis. These included the Misplaced Pages image but if one didn't want that included, it would be easy to exclude it.
So, AIs don't have to be inscrutable black boxes. They can have programmatic parameters like the existing bots and scripts that we use routinely on Misplaced Pages. Such power tools seem needed to deal with the large image backlogs that we have on Commons. Perhaps they could help by providing captions and categories where these don't exist.
They don't have to be black boxes but they are by design: they exist in a legally dubious area and thus hide what they're scraping to avoid further legal problems. That's no secret. We know for example that Misplaced Pages is a core data set for likely most AIs today. They also notoriously and quite confidently spit out a lie ("hallucinate") and frequently spit out total nonsense. Add to that that they're restricted to whatever is floating around on the internet or whatever other data set they've been fed (usually just more internet), and many specialist topics, like texts on ancient history and even standard reference works, are not accessible on the internet (despite Google's efforts). :bloodofox: (talk) 09:39, 2 January 2025 (UTC)
While its stated methodology seems sensible, there's no evidence that it actually followed that methodology. The bullet points are pretty vague, and are pretty much the default methodologies used to examine actual historical works. Chaotic Enby (talk · contribs) 17:40, 2 January 2025 (UTC)
Yes, there's evidence. As I stated above, the analysis is transparent and cites the sources that it used. And these all seem to check out rather than being invented. So, this level of AI goes beyond the first generation of LLM and addresses some of their weaknesses. I suppose that image generation is likewise being developed and improved and so we shouldn't rush to judgement while the technology is undergoing rapid development. Andrew🐉(talk) 17:28, 4 January 2025 (UTC)
Oppose blanket ban: best of luck to editors here who hope to be able to ban an entirely undefined and largely undetectable procedure. The term 'AI' as commonly used is no more than a buzzword - what exactly would be banned? And how does it improve the encyclopedia to encourage editors to object to images not simply because they are inaccurate, or inappropriate for the article, but because they subjectively look too good? Will the image creator be quizzed on Commons about the tools they used? Will creators who are transparent about what they have created have their images deleted while those who keep silent don’t? Honestly, this whole discussion is going to seem hopelessly outdated within a year at most. It’s like when early calculators were banned in exams because they were ‘cheating’, forcing students to use slide rules. MichaelMaggs (talk) 12:52, 1 January 2025 (UTC)
I am genuinely confused as to why this has turned into a discussion about a blanket ban, even though the original proposal exclusively focused on AI-generated images (the kind that is generated by an AI model from a prompt, which are already tagged on Commons, not regular images with AI enhancement or tools being used) and only in specific contexts. Not sure where the "subjectively look too good" thing even comes from, honestly. Chaotic Enby (talk · contribs) 12:58, 1 January 2025 (UTC)
That just show how ill-defined the whole area is. It seem you restrict the term 'AI-generated' to mean "images generated solely(?) from a text prompt". The question posed above has no such restriction. What a buzzword means is largely in the mind of the reader, of course, but to me and I think to many, 'AI-generated' means generated by AI. MichaelMaggs (talk) 13:15, 1 January 2025 (UTC)
I used the text prompt example because that is the most common way to have an AI model generate an image, but I recognize that I should've clarified it better. There is definitely a distinction between an image being generated by AI (like the Laurence Boccolini example below) and an image being altered or retouched by AI (which includes many features integrated in smartphones today). I don't think it's a "buzzword" to say that there is a meaningful difference between an image being made up by an AI model and a preexisting image being altered in some way, and I am surprised that many people understand "AI-generated" as including the latter. Chaotic Enby (talk · contribs) 15:24, 1 January 2025 (UTC)
Oppose as unenforceable. I just want you to imagine enforcing this policy against people who have not violated it. All this will do is allow Wikipedians who primarily contribute via text to accuse artists of using AI because they don't like the results to get their contributions taken down. I understand the impulse to oppose AI on principle, but the labor and aesthetic issues don't actually have anything to do with Misplaced Pages. If there is not actually a problem with the content conveyed by the image—for example, if the illustrator intentionally corrected any hallucinations—then someone objecting over AI is not discussing page content. If the image was not even made with AI, they are hallucinating based on prejudices that are irrelevant to the image. The bottom line is that images should be judged on their content, not how they were made. Besides all the policy-driven stuff, if Misplaced Pages's response to the creation of AI imaging tools is to crack down on all artistic contributions to Misplaced Pages (which seems to be the inevitable direction of these discussions), what does that say? Categorical bans of this kind are ill-advised and anti-illustrator. lethargilistic (talk) 15:41, 1 January 2025 (UTC)
And the same applies to photography, of course. If in my photo of a garden I notice there is a distracting piece of paper on the lawn, nobody would worry if I used the old-style clone-stamp tool to remove it in Photoshop, adding new grass in its place (I'm assuming here that I don't change details of the actual landscape in any way). Now, though, Photoshop uses AI to achieve essentially the same result while making it simpler for the user. A large proportion of all processed photos will have at least some similar but essentially undetectable "generated AI" content, even if only a small area of grass. There is simply no way to enforce the proposed policy, short of banning all high-quality photography – which requires post-processing by design, and in which similar encyclopedically non-problematic edits are commonplace. MichaelMaggs (talk) 17:39, 1 January 2025 (UTC)
Before anyone objects that my example is not "an image generated from a text prompt", note that there's no mention of such a restriction in the proposal we are discussing. Even if there were, it makes no difference. Photoshop can already generate photo-realistic areas from a text prompt. If such use is non-misleading and essentially undetectable, it's fine; if if changes the image in such a way as to make it misleading, inaccurate or non-encycpopedic in any way it can be challenged on that basis. MichaelMaggs (talk) 17:58, 1 January 2025 (UTC)
As I said previously, the text prompt is just an example, not a restriction of the proposal. The point is that you talk about editing an existing image (which is what you talk about, as you say if if changes the image), while I am talking about creating an image ex nihilo, which is what "generating" means. Chaotic Enby (talk · contribs) 18:05, 1 January 2025 (UTC)
I'm talking about a photograph with AI-generated areas within it. This is commonplace, and is targeted by the proposal. Categorical bans of the type suggested are indeed ill-advised. MichaelMaggs (talk) 18:16, 1 January 2025 (UTC)
Even if the ban is unenforceable, there are many editors who will choose to use AI images if they are allowed and just as cheerfully skip them if they are not allowed. That would mean the only people posting AI images are those who choose to break the rule and/or don't know about it. That would probably add up to many AI images not used. Darkfrog24 (talk) 22:51, 3 January 2025 (UTC)
Support blanket ban because "AI" is a fundamentally unethical technology based on the exploitation of labor, the wanton destruction of the planetary environment, and the subversion of every value that an encyclopedia should stand for. ABOUTSELF-type exceptions for "AI" output that has already been generated might be permissible, in order to document the cursed time in which we live, but those exceptions are going to be rare. How many examples of Shrimp Jesus slop do we need? XOR'easter (talk) 23:30, 1 January 2025 (UTC)
Support blanket ban - Primarily because of the "poisoning the well"/"dead internet" issues created by it. FOARP (talk) 14:30, 2 January 2025 (UTC)
Support that WP:POLICY applies to images: images should be verifiable, neutral, and absent of original research. AI is just the latest quickest way to produce images that are original, unverifiable, and potentially biased. Is anyone in their right mind saying that we allow people to game our rules on WP:OR and WP:V by using images instead of text? Shooterwalker (talk) 17:04, 3 January 2025 (UTC)
As an aside on this: in some cases Commons is being treated as a way of side-stepping WP:NOR and other restrictions. Stuff that would get deleted if it were written content on WP gets in to WP as images posted on Commons. The worst examples are those conflict maps that are created from a bunch of Twitter posts (eg the Syrian civil war one). AI-generated imagery is another field where that appears to be happening. FOARP (talk) 10:43, 4 January 2025 (UTC)
Support temporary blanket ban with a posted expiration/requred rediscussion date of no more than two years from closing. AI as the term is currently used is very, very new. Right now these images would do more harm than good, but it seems likely that the culture will adjust to them. I support an exception for the when the article is about the image itself and that image is notable, such as the photograph of the black-and-blue/gold-and-white dress in The Dress and/or examples of AI images in articles in which they are relevant. E.g. "here is what a hallucination is: count the fingers." Darkfrog24 (talk) 23:01, 3 January 2025 (UTC)
First, I think any guidance should avoid referring to specific technology, as that changes rapidly and is used for many different purposes. Second, assuming that the image in question has a suitable copyright status for use on Misplaced Pages, the key question is whether or not the reliability of the image has been established. If the intent of the image is to display 100 dots with 99 having the same appearance and 1 with a different appearance, then ordinary math skills are sufficient and so any Misplaced Pages editor can evaluate the reliability without performing original research. If the intent is to depict a likeness of a specific person, then there needs to be reliable sources indicating that the image is sufficiently accurate. This is the same for actual photographs, re-touched ones, drawings, hedcuts, and so forth. Typically this can be established by a reliable source using that image with a corresponding description or context. isaacl (talk) 17:59, 4 January 2025 (UTC)
Support Blanket Ban on AI generated imagery per most of the discussion above. It's a very slippery slope. I might consider a very narrow exception for an AI generated image of a person that was specifically authorized or commissioned by the subject. -Ad Orientem (talk) 02:45, 5 January 2025 (UTC)
Oppose blanket ban It is far too early to take an absolutist position, particularly when the potential is enormous. Misplaced Pages is already is image desert and to reject something that is only at the cusp of development is unwise. scope_creep20:11, 5 January 2025 (UTC)
Support blanket ban on AI-generated images except in ABOUTSELF contexts. An encyclopedia should not be using fake images. I do not believe that further nuance is necessary. LEPRICAVARK (talk) 22:44, 5 January 2025 (UTC)
Support blanket ban as the general guideline, as accuracy, personal rights, and intellectual rights issues are very weighty, here (as is disclosure to the reader). (I could see perhaps supporting adoption of a sub-guideline for ways to come to a broad consensus in individual use cases (carve-outs, except for BLPs) which address all the weighty issues on an individual use basis -- but that needs to be drafted and agreed to, and there is no good reason to wait to adopt the general ban in the meantime). Alanscottwalker (talk) 15:32, 8 January 2025 (UTC)
Which parts of this photo are real?
Support indefinite blanket ban except ABOUTSELF and simple abstract examples (such as the image of 99 dots above). In addition to all the issues raised above, including copyvio and creator consent issues, in cases of photorealistic images it may never be obvious to all readers exactly which elements of the image are guesswork. The cormorant picture at the head of the section reminded me of the first video of a horse in gallop, in 1878. Had AI been trained on paintings of horses instead of actual videos and used to "improve" said videos, we would've ended up with serious delusions about the horse's gait. We don't know what questions -- scientific or otherwise -- photography will be used to settle in the coming years, but we do know that consumer-grade photo AI has already been trained to intentionally fake detail to draw sales, such as on photos of the Moon. I think it's unrealistic to require contributors to take photos with expensive cameras or specially-made apps, but Misplaced Pages should act to limit its exposure to this kind of technology as far as is feasible. DaßWölf20:57, 9 January 2025 (UTC)
BLPs
CONSENSUS AGAINST
There is clear consensus against using AI-generated imagery to depict BLP subjects. Marginal cases (such as major AI enhancement or where an AI-generated image of a living person is itself notable) can be worked out on a case-by-case basis. I will add a sentence reflecting this consensus to the image use policy and the BLP policy. —Ganesha811 (talk) 14:02, 8 January 2025 (UTC)
The following discussion is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.
Are AI-generated images (generated via text prompts, see also: text-to-image model) okay to use to depict BLP subjects? The Laurence Boccolini example was mentioned in the opening paragraph. The image was created using Grok / Aurora, a text-to-image model developed by xAI, to generate images...As with other text-to-image models, Aurora generates images from natural language descriptions, called prompts.AI-generated image of Laurence BoccoliniSome1 (talk) 12:34, 31 December 2024 (UTC)AI-generated cartoon portrait of Germán Larrea Mota-Velasco
03:58, January 3, 2025: Note: that these images can either be photorealistic in style (such as the Laurence Boccolini example) or non-photorealistic in style (see the Germán Larrea Mota-Velasco example, which was generated using DALL-E, another text-to-image model).
No. I don't think they are at all, as, despite looking photorealistic, they are essentially just speculation about what the person might look like. A photorealistic image conveys the look of something up to the details, and giving a false impression of what the person looks like (or, at best, just guesswork) is actively counterproductive. (Edit 21:59, 31 December 2024 (UTC): clarified bolded !vote since everyone else did it) Chaotic Enby (talk · contribs) 12:46, 31 December 2024 (UTC)
There are plenty of non-free images of Laurence Boccolini with which this image can be compared. Assuming at least most of those are accurate representations of them (I've never heard of them before and have no other frame of reference) the image above is similar to but not an accurate representation of them (most obviously but probably least significantly, in none of the available images are they wearing that design of glasses). This means the image should not be used to identify them unless they use it to identify themselves. It should not be used elsewhere in the article unless it has been the subject of notable commentary. That it is an AI image makes absolutely no difference to any of this. Thryduulf (talk) 16:45, 31 December 2024 (UTC)
No. Well, that was easy.They are fake images; they do not actually depict the person. They depict an AI-generated simulation of a person that may be inaccurate. Cremastra 🎄 u — c 🎄 20:00, 31 December 2024 (UTC)
No, with the caveat that its mostly on the grounds that we don't have enough information and when it comes to BLP we are required to exercise caution. If at some point in the future AI generated photorealistic simulacrums living people become mainstream with major newspapers and academic publishers it would be fair to revisit any restrictions, but in this I strongly believe that we should follow not lead. Horse Eye's Back (talk) 20:37, 31 December 2024 (UTC)
No. The use of AI-generated images to depict people (living or otherwise) is fundamentally misleading, because the images are not actually depicting the person. —pythoncoder (talk | contribs) 21:30, 31 December 2024 (UTC)
Yes, when that image is an accurate representation and better than any available alternative, used by the subject to represent themselves, or the subject of notable commentary. However, as these are the exact requirements to use any image to represent a BLP subject this is already policy. Thryduulf (talk) 21:46, 31 December 2024 (UTC)
How well can we determine how accurate a representation it is? Looking at the example above, I'd argue that the real Laurence Boccolini has a somewhat rounder/pointier chin, a wider mouth, and possibly different eye wrinkles, although the latter probably depends quite a lot on the facial expression.
How well can we determine how accurate a representation it is? in exactly the same way that we can determine whether a human-crafted image is an accurate representation. How accurate a representation any image is is ultimately a matter of editor opinion. Whether an image is AI or not is irrelevant. I agree the example image above is not sufficiently accurate, but we wouldn't ban photoshopped images because one example was not deemed accurate enough, because we are rational people who understand that one example is not representative of an entire class of images - at least when the subject is something other than AI. Thryduulf (talk) 23:54, 31 December 2024 (UTC)
I think except in a few exceptional circumstances of actual complex restorations, human photoshopping is not going to change or distort a person's appearance in the same way an AI image would. Modifications done by a person who is paying attention to what they are doing and merely enhancing an image, by person who is aware, while they are making changes, that they might be distorting the image and is, I only assume, trying to minimise it – those careful modifications shouldn't be equated with something made up by an AI image generator. Cremastra 🎄 u — c 🎄 00:14, 1 January 2025 (UTC)
A photo of a person can be connected to a specific time, place, and subject that existed. It can be compared to other images sharing one or more of those properties. A photo that was PhotoShopped is still either a generally faithful reproduction of a scene that existed, or has significant alterations that can still be attributed to a human or at least to a specific algorithm, e.g. filters. The artistic license of a painting can still be attributed to a human and doesn't run much risk of being misidentified as real, unless it's by Chuck Close et al. An AI-generated image cannot be connected to a particular scene that ever existed and cannot be attributable to a human's artistic license (and there is legal precedent that such images are not copyrightable to the prompter specifically because of this). Individual errors in a human-generated artwork are far more predictable, understandable, identifiable, traceable... than those in AI-generated images. We have innate assumptions when we encounter real images or artwork that are just not transferable. These are meaningful differences to the vast majority of people: according to a Getty poll, 87% of respondents want AI-generated art to at least be transparent, and 98% consider authentic images "pivotal in establishing trust". And even if you disagree with all that, can you not see the larger problem of AI images on Misplaced Pages getting propagated into generative AI corpora? JoelleJay (talk) 04:20, 2 January 2025 (UTC)
I agree that our old assumptions don't hold true. I think the world will need new assumptions. We will probably have those in place in another decade or so.
Absolutely no fake/AI images of people, photorealistic or otherwise. How is this even a question? These images are fake. Readers need to be able to trust Misplaced Pages, not navigate around whatever junk someone has created with a prompt and presented as somehow representative. This includes text. :bloodofox: (talk) 22:24, 31 December 2024 (UTC)
For the requested clarification by Some1, no AI-generated images (except when the image itself is specifically discussed in the article, and even then it should not be the lead image and it should be clearly indicated that the image is AI-generated), no drawings, no nothing of that sort. Actual photographs of the subject, nothing else. Articles are not required to have images at all; no image whatsoever is preferable to something which is not an image of the person. Seraphimblade05:42, 3 January 2025 (UTC)
No, but with exceptions. I could imagine a case where a specific AI-generated image has some direct relevance to the notability of the subject of a BLP. In such cases, it should be included, if it could be properly licensed. But I do oppose AI-generated images as portraits of BLP subjects. —David Eppstein (talk) 01:27, 1 January 2025 (UTC)
Since I was pinged on this point: when I wrote "I do oppose AI-generated images as portraits", I meant exactly that, including all AI-generated images, such as those in a sketchy or artistic style, not just the photorealistic ones. I am not opposed to certain uses of AI-generated images in BLPs when they are not the main portrait of the subject, for instance in diagrams (not depicting the subject) to illustrate some concept pioneered by the subject, or in case someone becomes famous for being the subject of an AI-generated image. —David Eppstein (talk) 05:41, 3 January 2025 (UTC)
No, and no exceptions or do-overs. Better to have no images (or Stone-Age style cave paintings) than Frankenstein images, no matter how accurate or artistic. Akin to shopped manipulated photographs, they should have no room (or room service) at the WikiInn. Randy Kryn (talk) 01:34, 1 January 2025 (UTC)
Some "shopped manipulated photographs" are misleading and inaccurate, others are not. We can and do exclude the former from the parts of the encyclopaedia where they don't add value without specific policies and without excluding them where they are relevant (e.g. Photograph manipulation) or excluding those that are not misleading or inaccurate. AI images are no different. Thryduulf (talk) 02:57, 1 January 2025 (UTC)
Assuming we know. Assuming it's material. The infobox image in – and the only extant photo of – Blind Lemon Jefferson was "photoshopped" by a marketing team, maybe half a century before Adobe Photoshop was created. They wanted to show him wearing a necktie. I don't think that this level of manipulation is actually a problem. WhatamIdoing (talk) 07:44, 2 January 2025 (UTC)
No Not at all relevant for pictures of people, as the accuracy is not enough and can misrepresent. Also (and I'm shocked as it seems no one has mentioned this), what about Copyright issues? Who holds the copyright for an AI-generated image? The user who wrote the prompt? The creator(s) of the AI model? The creator(s) of the images in the database that the AI used to create the images? It's sounds to me such a clusterfuck of copyright issues that I don't understand how this is even a discussion. --SuperJew (talk) 07:10, 1 January 2025 (UTC)
Under the US law / copyright office, machine-generated images including those by AI cannot be copyrighted. That also means that AI images aren't treated as derivative works. What is still under legal concern is whether the use of bodies of copyrighted works without any approve or license from the copyright holders to train AI models is under fair use or not. There are multiple court cases where this is the primary challenge, and none have yet to reach a decision yet. Assuming the courts rule that there was no fair use, that would either require the entity that owns the AI to pay fines and ongoing licensing costs, or delete their trained model to start afresh with free licensed/works, but in either case, that would not impact how we'd use any resulting AI image from a copyright standpoint. — Masem (t) 14:29, 1 January 2025 (UTC)
No, I'm in agreeance with Seraphimblade here. Whether we like it or not, the usage of a portrait on an article implies that it's just that, a portrait. It's incredibly disingenuous to users to represent an AI generated photo as truth. Doawk7 (talk) 09:32, 1 January 2025 (UTC)
So you just said a portrait can be used because wikipedia tells you it's a portrait, and thus not a real photo. Can't AI be exactly the same? As long as we tell readers it is an AI representation? Heck, most AI looks closer to the real thing than any portrait. Fyunck(click) (talk) 10:07, 2 January 2025 (UTC)
To clarify, I didn't mean "portrait" as in "painting," I meant it as "photo of person."
However, I really want to stick to what you say at the end there: Heck, most AI looks closer to the real thing than any portrait.
That's exactly the problem: by looking close to the "real thing" it misleads users into believing a non-existent source of truth.
Per the wording of the RfC of "depict BLP subjects," I don't think there would be any valid case to utilize AI images. I hold a strong No. Doawk7 (talk) 04:15, 3 January 2025 (UTC)
No. We should not use AI-generated images for situations like this, they are basically just guesswork by a machine as Quark said and they can misinform readers as to what a person looks like. Plus, there's a big grey area regarding copyright. For an AI generator to know what somebody looks like, it has to have photos of that person in its dataset, so it's very possible that they can be considered derivative works or copyright violations. Using an AI image (derivative work) to get around the fact that we have no free images is just fair use with extra steps. Di (they-them) (talk) 19:33, 1 January 2025 (UTC)Gisèle Pelicot?
Maybe There was a prominent BLP image which we displayed on the main page recently. (right) This made me uneasy because it was an artistic impression created from photographs rather than life. And it was "colored digitally". Functionally, this seems to be exactly the same sort of thing as the Laurence Boccolini composite. The issue should not be whether there's a particular technology label involved but whether such creative composites and artists' impressions are acceptable as better than nothing. Andrew🐉(talk) 08:30, 1 January 2025 (UTC)
Except it is clear to everyone that the illustration to the right is a sketch, a human rendition, while in the photorealistic image above, it is less clear. Cremastra (u — c) 14:18, 1 January 2025 (UTC)
Except it says right below it "AI-generated image of Laurence Boccolini." How much more clear can it be when it say point-blank "AI-generated image." Fyunck(click) (talk) 10:12, 2 January 2025 (UTC)
People taking a quick glance at an infobox image that looks pretty like a photograph are not going to scrutinize commons tagging. Cremastra (u — c) 14:15, 2 January 2025 (UTC)
Keep in mind that many AIs can produce works that match various styles, not just photographic quality. It is still possible for AI to produce something that looks like a watercolor or sketched drawing. — Masem (t) 14:33, 1 January 2025 (UTC)
Same thing I wrote above, but for "photoshopping" read "drawing": (Bold added for emphasis)
...human is not going to change or distort a person's appearance in the same way an AI image would. done by a person who is paying attention to what they are doing by person who is aware, while they are making , that they might be distorting the image and is, I only assume, trying to minimise it – those careful modifications shouldn't be equated with something made up by an AI image generator.Cremastra (u — c) 20:56, 1 January 2025 (UTC)
@Cremastra then why are you advocating for a ban on AI images rather than a ban on distorted images? Remember that with careful modifications by someone who is aware of what they are doing that AI images can be made more accurate. Why are you assuming that a human artist is trying to minimise the distortions but someone working with AI is not? Thryduulf (talk) 22:12, 1 January 2025 (UTC)
I believe that AI-generated images are fundamentally misleading because they are a simulation by a machine rather than a drawing by a human. To quote pythoncoder above: The use of AI-generated images to depict people (living or otherwise) is fundamentally misleading, because the images are not actually depicting the person.Cremastra (u — c) 00:16, 2 January 2025 (UTC)
Once again your actual problem is not AI, but with misleading images. Which can be, and are, already a violation of policy. Thryduulf (talk) 01:17, 2 January 2025 (UTC)
I think all AI-generated images, except simple diagrams as WhatamIdoing point out above, are misleading. So yes, my problem is with misleading images, which includes all photorealistic images generated by AI, which is why I support this proposal for a blanket ban in BLPs and medical articles. Cremastra (u — c) 02:30, 2 January 2025 (UTC)
Despite the fact that not all AI-generated images are misleading, not all misleading images are AI-generated and it is not always possible to tell whether an image is or is not AI-generated? Thryduulf (talk) 02:58, 2 January 2025 (UTC)
Enforcement is a separate issue. Whether or not all (or the vast majority) of AI images are misleading is the subject of this dispute.
I'm not going to mistreat the horse further, as we've each made our points and understand where the other stands. Cremastra (u — c) 15:30, 2 January 2025 (UTC)
Even "simple diagrams" are not clear-cut. The process of AI-generating any image, no matter how simple, is still very complex and can easily follow any number of different paths to meet the prompt constraints. These paths through embedding space are black boxes and the likelihood they converge on the same output is going to vary wildly depending on the degrees of freedom in the prompt, the dimensionality of the embedding space, token corpus size, etc. The only thing the user can really change, other than switching between models, is the prompt, and at some point constructing a prompt that is guaranteed to yield the same result 100% of the time becomes a Borgesian exercise. This is in contrast with non-generative AI diagram-rendering software that follow very fixed, reproducible, known paths. JoelleJay (talk) 04:44, 2 January 2025 (UTC)
Why does the path matter? If the output is correct it is correct no matter what route was taken to get there. If the output is incorrect it is incorrect no matter what route was taken to get there. If it is unknown or unknowable whether the output is correct or not that is true no matter what route was taken to get there. Thryduulf (talk) 04:48, 2 January 2025 (UTC)
If I use BioRender or GraphPad to generate a figure, I can be confident that the output does not have errors that would misrepresent the underlying data. I don't have to verify that all 18,000 data points in a scatter plot exist in the correct XYZ positions because I know the method for rendering them is published and empirically validated. Other people can also be certain that the process of getting from my input to the product is accurate and reproducible, and could in theory reconstruct my raw data from it. AI-generated figures have no prescribed method of transforming input beyond what the prompt entails; therefore I additionally have to be confident in how precise my prompt is and confident that the training corpus for this procedure is so accurate that no error-producing paths exist (not to mention absolutely certain that there is no embedded contamination from prior prompts). Other people have all those concerns, and on top of that likely don't have access to the prompt or the raw data to validate the output, nor do they necessarily know how fastidious I am about my generative AI use. At least with a hand-drawn diagram viewers can directly transfer their trust in the author's knowledge and reliability to their presumptions about the diagram's accuracy. JoelleJay (talk) 05:40, 2 January 2025 (UTC)
The original "simple geometric diagrams" comment was referring to your 100 dots image. I don't think increasing the dots materially changes the discussion beyond increasing the laboriousness of verifying the accuracy of the image. Photos of Japan (talk) 07:56, 2 January 2025 (UTC)
Yes, but since "the laboriousness of verifying the accuracy of the image" is exactly what she doesn't want to undertake for 18,000 dots, then I think that's very relevant. WhatamIdoing (talk) 07:58, 2 January 2025 (UTC)
And where is that cutoff supposed to be? 1000 dots? A single straight line? An atomic diagram? What is "simple" to someone unfamiliar with a topic may be more complex.And I don't want to count 100 dots either! JoelleJay (talk) 17:43, 2 January 2025 (UTC)
Maybe you don't. But I know for certain that you can count 10 across, 10 down, and multiply those two numbers to get 100. That's what I did when I made the image, after all. WhatamIdoing (talk) 07:44, 3 January 2025 (UTC)
Comment: when you Google search someone (at least from the Chrome browser), often the link to the Misplaced Pages article includes a thumbnail of the lead photo as a preview. Even if the photo is labelled as an AI image in the article, people looking at the thumbnail from Google would be misled (if the image is chosen for the preview). Photos of Japan (talk) 09:39, 1 January 2025 (UTC)
This is why we should not use inaccurate images, regardless of how the image was created. It has absolutely nothing to do with AI. Thryduulf (talk) 11:39, 1 January 2025 (UTC)
Already opposed a blanket ban: It's unclear to me why we have a separate BLP subsection, as BLPs are already included in the main section above. Anyway, I expressed my views there. MichaelMaggs (talk)
No For at least now, let's not let the problems of AI intrude into BLP articles which need to have the highest level of scrutiny to protect the person represented. Other areas on WP may benefit from AI image use, but let's keep it far out of BLP at this point. --Masem (t) 14:35, 1 January 2025 (UTC)
I am not a fan of “banning” AI images completely… but I agree that BLPs require special handling. I look at AI imagery as being akin to a computer generated painting. In a BLP, we allow paintings of the subject, but we prefer photos over paintings (if available). So… we should prefer photos over AI imagery. That said, AI imagery is getting good enough that it can be mistaken for a photo… so… If an AI generated image is the only option (ie there is no photo available), then the caption should clearly indicate that we are using an AI generated image. And that image should be replaced as soon as possible with an actual photograph. Blueboar (talk) 14:56, 1 January 2025 (UTC)
The issue with the latter is that Misplaced Pages images get picked up by Google and other search engines, where the caption isn't there anymore to add the context that a photorealistic image was AI-generated. Chaotic Enby (talk · contribs) 15:27, 1 January 2025 (UTC)
We're here to build an encyclopedia, not to protect commercial search engine companies.
I think my view aligns with Blueboar's (except that I find no firm preference for photos over classical portrait paintings): We shouldn't have inaccurate AI images of people (living or dead). But the day appears to be coming when AI will generate accurate ones, or at least ones that are close enough to accurate that we can't tell the difference unless the uploader voluntarily discloses that information. Once we can no longer tell the difference, what's the point in banning them? Images need to look like the thing being depicted. When we put an photorealistic image in an article, we could be said to be implicitly claiming that the image looks like whatever's being depicted. We are not necessarily warranting that the image was created through a specific process, but the image really does need to look like the subject. WhatamIdoing (talk) 03:12, 2 January 2025 (UTC)
You are presuming that sufficient accuracy will prevent us from knowing whether someone is uploading an AI photo, but that is not the case. For instance, if someone uploads large amounts of "photos" of famous people, and can't account for how they got them (e.g. can't give a source where they scraped them from, or dates or any Exif metadata at all for when they were taken), then it will still be obvious that they are likely using AI. Photos of Japan (talk) 17:38, 3 January 2025 (UTC)
As another editor pointed out in their comment, there's the ethics/moral dilemma of creating fake photorealistic pictures of people and putting them on the internet, especially on a site such as Misplaced Pages and especially on their own biography. WP:BLP says the bios must be written conservatively and with regard for the subject's privacy.Some1 (talk) 18:37, 3 January 2025 (UTC)
Once we can no longer tell the difference, what's the point in banning them? Sounds like a wolf's in sheep's clothing to me. Just because the surface appeal of fake pictures gets better, doesn't mean we should let the horse in. Cremastra (u — c) 18:47, 3 January 2025 (UTC)
If there are no appropriately-licensed images of a person, then by definition any AI-generated image of them will be either a copyright infringement or a complete fantasy. JoelleJay (talk) 04:48, 2 January 2025 (UTC)
Whether it would be a copyright infringement or not is both an unsettled legal question and not relevant: If an image is a copyvio we can't use it and it is irrelevant why it is a copyvio. If an image is a "complete fantasy" then it is exactly as unusable as a complete fantasy generated by non-AI means, so again AI is irrelevant. I've had to explain this multiple times in this discussion, so read that for more detail and note the lack of refutation. Thryduulf (talk) 04:52, 2 January 2025 (UTC)
Ooooh, I'm not sure that we can assume that humans aren't blatantly copying something. We can assume that they meant to be helpful, but that's not quite the same thing. WhatamIdoing (talk) 07:48, 2 January 2025 (UTC)
What this conversation is really circling around is banning entire skillsets from contributing to Misplaced Pages merely because some of us are afraid of AI images and some others of us want to engineer a convenient, half-baked, policy-level "consensus" to point to when they delete quality images from Misplaced Pages. Every time someone generates text based on a source, they are doing some acceptable level of interpretation to extract facts or rephrase it around copyright law, and I don't think illustrations should be considered so severely differently as to justify a categorical ban. For instance, the Gisele Pelicot portrait is based on non-free photos of her. Once the illustration exists, it is trivial to compare it to non-free images to determine if it is an appropriate likeness, which it is. That's no different than judging contributed text's compliance with fact and copyright by referring to the source. It shouldn't be treated differently just because most Wikipedians contribute via text. Additionally, referring to interpretive skillsets that synthesize new information like, random example, statistical analysis. Excluding those from Misplaced Pages is current practice and not controversial. Meanwhile, I think the ability to create images is more fundamental than that. It's not (inheretly) synthesizing new information. A portrait of a person (alongside the other examples in this thread) contains verifiable information. It is current practice to allow them to fill the gaps where non-free photos can't. That should continue. Honestly, it should expand.
Additionally, in direct response to "these images are fake": All illustrations of a subject could be called "fake" because they are not photographs. (Which can also be faked.) The standard for the inclusion of an illustration on Misplaced Pages has never been photorealism, medium, or previous publication in a RS. The standard is how adequately it reflects the facts which it claims to depict. If there is a better image that can be imported to Misplaced Pages via fair use or a license, then an image can be easily replaced. Until such a better image has been sourced, it is absolutely bewildering to me that we would even discuss removing images of people from their articles. What a person looked like is one of the most basic things that people want to know when they look someone up on Misplaced Pages. Including an image of almost any quality (yes, even a cartoon) is practically by definition an improvement to the article and addressing an important need. We should be encouraging artists to continue filling the gaps that non-free images cannot fill, not creating policies that will inevitably expand into more general prejudices against all new illustrations on Misplaced Pages. lethargilistic (talk) 15:59, 1 January 2025 (UTC)
By "Oppose", I'm assuming your answer to the RfC question is "Yes". And this RfC is about using AI-generated images (generated via text prompts, see also: text-to-image model) to depict BLP subjects, not regarding human-created drawings/cartoons/sketches, etc. of BLPs. Some1 (talk) 16:09, 1 January 2025 (UTC)
I've changed it to "yes" to reflect the reversed question. I think all of this is related because there is no coherent distinguishing point; AI can be used to create images in a variety of styles. These discussions have shown that a policy of banning AI images will be used against non-AI images of all kinds, so I think it's important to say these kinds of things now. lethargilistic (talk) 16:29, 1 January 2025 (UTC)
Photorealistic images scraped from who knows where from who knows what sources are without question simply fake photographs and also clear WP:OR and outright WP:SYNTH. There's no two ways about it. Articles do not require images: An article with some Frankenstein-ed image scraped from who knows what, where and, when that you "created" from a prompt is not an improvement over having no image at all. If we can't provide a quality image (like something you didn't cook up from a prompt) then people can find quality, non-fake images elsewhere. :bloodofox: (talk) 23:39, 1 January 2025 (UTC)
I really encourage you to read the discussion I linked before because it is on the WP:NOR talk page. Images like these do not inherently include either OR or SYNTH, and the arguments that they do cannot be distinguished from any other user-generated image content. But, briefly, I never said articles required images, and this is not about what articles require. It is about improvements to the articles. Including a relevant picture where none exists is almost always an improvement, especially for subjects like people. Your disdain for the method the person used to make an image is irrelevant to whether the content of the image is actually verifiable, and the only thing we ought to care about is the content. lethargilistic (talk) 03:21, 2 January 2025 (UTC)
Images like these are absolutely nothing more than synthesis in the purest sense of the world and are clearly a violation of WP:SYNTH: Again, you have no idea what data was used to generate these images and you're going to have a very hard time convincing anyone to describe them as anything other than outright fakes.
A reminder that WP:SYNTH shuts down attempts at manipulation of images ("It is not acceptable for an editor to use photo manipulation to distort the facts or position illustrated by an image. Manipulated images should be prominently noted as such. Any manipulated image where the encyclopedic value is materially affected should be posted to Misplaced Pages:Files for discussion. Images of living persons must not present the subject in a false or disparaging light.") and generating a photorealistic image (from who knows what!) is far beyond that.
Fake images of people do not improve our articles in any way and only erode reader trust. What's next, an argument for the fake sources LLMs also love to "hallucinate"? :bloodofox: (talk) 03:37, 2 January 2025 (UTC)
So, if you review the first sentence of SYNTH, you'll see it has no special relevance to this discussion: Do not combine material from multiple sources to state or imply a conclusion not explicitly stated by any of the sources.. My primary example has been a picture of a person; what a person looks like is verifiable by comparing the image to non-free images that cannot be used on Misplaced Pages. If the image resembles the person, it is not SYNTH. An illustration of a person created and intended to look like that person is not a manipulation. The training data used to make the AI is irrelevant to whether the image in fact resembles the person. You should also review WP:NOTSYNTH because SYNTH is not a policy; NOR is the policy: If a putative SYNTH doesn't constitute original research, then it doesn't constitute SYNTH. Additionally, not all synthesis is even SYNTH. A categorical rule against AI cannot be justified by SYNTH because it does not categorically apply to all use cases of AI. To do so would be illogical on top of ill-advised. lethargilistic (talk) 08:08, 2 January 2025 (UTC)
"training data used to make the AI is irrelevant" — spoken like a true AI evangelist! Sorry, 'good enough' photorealism is still just synthetic slop, a fake image presented as real of a human being. A fake image of someone generated from who-knows-what that 'resembles' an article's subject is about as WP:SYNTH as it gets. Yikes. As for the attempts to pass of prompt-generated photorealistic fakes of people as somehow the same as someone's illustration, you're completely wasting your time. :bloodofox: (talk) 09:44, 2 January 2025 (UTC)
NOR is a content policy and SYNTH is content guidance within NOR. Because you have admitted that this is not about the content for you, NOR and SYNTH are irrelevant to your argument, which boils down to WP:IDONTLIKEIT and, now, inaccurate personal attacks. Continuing this discussion between us would be pointless. lethargilistic (talk) 09:52, 2 January 2025 (UTC)
This is in fact entirely about content (why the hell else would I bother?) but it is true that I also dismissed your pro-AI 'it's just like a human drawing a picture!' as outright nonsense a while back. Good luck convincing anyone else with that line - it didn't work here. :bloodofox: (talk) 09:59, 2 January 2025 (UTC)
Maybe: there is an implicit assumption with this RFC that an AI generated image would be photorealistic. There hasn't been any discussion of an AI generated sketch. If you asked an AI to generate a sketch (that clearly looked like a sketch, similar to the Gisèle Pelicot example) then I would potentially be ok with it. Photos of Japan (talk) 18:14, 1 January 2025 (UTC)
That's an interesting thought to consider. At the same time, I worry about (well-intentioned) editors inundating image-less BLP articles with AI-generated images in the style of cartoons/sketches (if only photorealistic ones are prohibited) etc. At least requiring a human to draw/paint/whatever creates a barrier to entry; these AI-generated images can be created in under a minute using these text-to-image models. Editors are already wary about human-created cartoon portraits (see the NORN discussion), now they'll be tasked with dealing with AI-generated ones in BLP articles. Some1 (talk) 20:28, 1 January 2025 (UTC)
It sounds like your problem is not with AI but with cartoon/sketch images in BLP articles, so AI is once again completely irrelevant. Thryduulf (talk) 22:14, 1 January 2025 (UTC)
That is a good concern you brought up. There is a possibility of the spamming of low quality AI-generated images which would be laborious to discuss on a case-by-case basis but easy to generate. At the same time though that is a possibility, but not yet an actuality, and WP:CREEP states that new policies should address current problems rather than hypothetical concerns. Photos of Japan (talk) 22:16, 1 January 2025 (UTC)
Easy no for me. I am not against the use of AI images wholesale, but I do think that using AI to represent an existent thing such as a person or a place is too far. Even a tag wouldn't be enough for me. Cessaune19:05, 1 January 2025 (UTC)
No obviously, per previous discussions about cartoonish drawn images in BLPs. Same issue here as there, it is essentially original research and misrepresentation of a living person's likeness. Zaathras (talk) 22:19, 1 January 2025 (UTC)
No to photorealistic, no to cartoonish... this is not a hard choice. The idea that "this has nothing to do with AI" when "AI" magnifies the problem to stupendous proportions is just not tenable. XOR'easter (talk) 23:36, 1 January 2025 (UTC)
While AI might "amplify" the thing you dislike, that does not make AI the problem. The problem is whatever underlying thing is being amplified. Thryduulf (talk) 01:16, 2 January 2025 (UTC)
That is arguable, but banning the amplifier does not do anything to solve the problem. In this case, banning the amplifier would cause multiple other problems that nobody supporting this proposal as even attempted to address, let alone mitigate. Thryduulf (talk) 03:04, 2 January 2025 (UTC)
No - We should not be hosting faked images (except as notable fakes). We should also not be hosting copyvios ("Whether it would be a copyright infringement or not is both an unsettled legal question and not relevant" is just totally wrong - we should be steering clear of copyvios, and if the issue is unsettled then we shouldn't use them until it is).
If people upload faked images to WP or Commons the response should be as it is now. The fact that fakes are becoming harder to detect simply from looking at them hardly affects this - we simply confirm when the picture was supposed to have been taken and examine the plausibility of it from there. FOARP (talk) 14:39, 2 January 2025 (UTC) FOARP (talk) 14:39, 2 January 2025 (UTC)
we should be steering clear of copyvio we do - if an image is a copyright violation it gets deleted, regardless of why it is a copyright violation. What we do not do is ban using images that are not copyright violations because they are copyright violations. Currently the WMF lawyers and all the people on Commons who know more about copyright than I do say that at least some AI images are legally acceptable for us to host and use. If you want to argue that, then go ahead, but it is not relevant to this discussion.
if people upload faked images the response should be as it is now in other words you are saying that the problem is faked images not AI, and that current policies are entirely adequate to deal with the problem of faked images. So we don't need any specific rules for AI images - especially given that not all AI images are fakes. Thryduulf (talk) 15:14, 2 January 2025 (UTC)
The idea that current policies are entirely adequate is like saying that a lab shouldn't have specific rules about wearing eye protection when it already has a poster hanging on the wall that says "don't hurt yourself". XOR'easter (talk) 18:36, 2 January 2025 (UTC)
"in other words you are saying that the problem is faked images not AI" - AI generated images *are* fakes. This is merely confirming that for the avoidance of doubt.
"at least some AI images are legally acceptable for us" - Until they decide which ones that isn't much help. FOARP (talk) 19:05, 2 January 2025 (UTC)
Those specific rules exist because generic warnings have proven not to be sufficient. Nobody has presented any evidence that the current policies are not sufficient, indeed quite the contrary. Thryduulf (talk) 19:05, 2 January 2025 (UTC)
Noting that I think that no AI-generated images are acceptable in BLP articles, regardless of whether they are photorealistic or not. JuxtaposedJacob (talk) | :) | he/him | 15:40, 3 January 2025 (UTC)
No, unless the AI image has encyclopedic significance beyond "depicts a notable person". AI images, if created by editors for the purpose of inclusion in Misplaced Pages, convey little reliable information about the person they depict, and the ways in which the model works are opaque enough to most people as to raise verifiability concerns. ModernDayTrilobite (talk • contribs) 15:25, 2 January 2025 (UTC)
To clarify, do you object to uses of an AI image in a BLP when the subject uses that image for self-identification? I presume that AI images that have been the subject of notable discussion are an example of "significance beyond depict a notable person"? Thryduulf (talk) 15:54, 2 January 2025 (UTC)
If the subject uses the image for self-identification, I'd be fine with it - I think that'd be analogous to situations such as "cartoonist represented by a stylized self-portrait", which definitely has some precedent in articles like Al Capp. I agree with your second sentence as well; if there's notable discussion around a particular AI image, I think it would be reasonable to include that image on Misplaced Pages. ModernDayTrilobite (talk • contribs) 19:13, 2 January 2025 (UTC)
No, with obvious exceptions, including if the subject theyrself uses the image as a their representation, or if the image is notable itself. Not including the lack of a free aleternative, if there is no free alternative... where did the AI find data to build an image... non free too. Not including images generated by WP editors (that's kind of original research... - Nabla (talk) 18:02, 2 January 2025 (UTC
Maybe I think the question is unfair as it is illustrated with what appears to be a photo of the subject but isn't. People are then getting upset that they've been misled. As others note, there are copyright concerns with AI reproducing copyrighted works that in turn make an image that is potentially legally unusable. But that is more a matter for Commons than for Misplaced Pages. As many have noted, a sketch or painting never claims to be an accurate depiction of a person, and I don't care if that sketch or painting was done by hand or an AI prompt. I strongly ask Some1 to abort the RFC. You've asked people to give a yes/no vote to what is a more complex issue. A further problem with the example used is the unfortunate prejudice on Misplaced Pages against user-generated content. While the text-generated AI of today is crude and random, there will come a point where many professionally published photos illustrating subjects, including people, are AI generated. Even today, your smartphone can create a groupshot where everyone is smiling and looking at the camera. It was "trained" on the 50 images it quickly took and responded to the build-in "text prompt" of "create a montage of these photos such that everyone is smiling and looking at the camera". This vote is a knee jerk reaction to content that is best addressed by some other measure (such as that it is a misleading image). And a good example of asking people to vote way too early, when the issues haven't been throught out -- Colin°18:17, 2 January 2025 (UTC)
No This would very likely set a dangerous precedent. The only exception I think should be if the image itself is notable. If we move forward with AI images, especially for BLPs, it would only open up a whole slew of regulations and RfCs to keep them in check. Better no image than some digital multiverse version of someone that is "basically" them but not really. Not to mention the ethics/moral dilemma of creating fake photorealistic pictures of people and putting them on the internet. Tepkunset (talk) 18:31, 2 January 2025 (UTC)
No. LLMs don't generate answers, they generate things that look like answers, but aren't; a lot of the time, that's good enough, but sometimes it very much isn't. It's the same issue for text-to-image models: they don't generate photos of people, they generate things that look like photos. Using them on BLPs is unacceptable. DS (talk) 19:30, 2 January 2025 (UTC)
No. I would be pissed if the top picture of me on Google was AI-generated. I just don't think it's moral for living people. The exceptions given above by others are okay, such as if the subject uses the picture themselves or if the picture is notable (with context given). win8x (talk) 19:56, 2 January 2025 (UTC)
No. Uploading alone, although mostly a Commons issue, would already a problem to me and may have personality rights issues. Illustrating an article with a fake photo (or drawing) of a living person, even if it is labeled as such, would not be acceptable. For example, it could end up being shown by search engines or when hovering over a Misplaced Pages link, without the disclaimer. ~ ToBeFree (talk) 23:54, 2 January 2025 (UTC)
I was going to say no... but we allow paintings as portraits in BLPs. What's so different between an AI generated image, and a painting? Arguments above say the depiction may not be accurate, but the same is true of some paintings, right? (and conversely, not true of other paintings) ProcrastinatingReader (talk) 00:48, 3 January 2025 (UTC)
A painting is clearly a painting; as such, the viewer knows that it is not an accurate representation of a particular reality. An AI-generated image made to look exactly like a photo, looks like a photo but is not.
Not all paintings are clearly paintings. Not all AI-generated images are made to look like photographs. Not all AI-generated images made to look like photos do actually look like photos. This proposal makes no distinction. Thryduulf (talk) 02:55, 3 January 2025 (UTC)
Not to mention, hyper-realism is a style an artist may use in virtually any medium. Colored pencils can be used to make extremely realistic portraits. If Misplaced Pages would accept an analog substitute like a painting, there's no reason Misplaced Pages shouldn't accept an equivalent painting made with digital tools, and there's no reason Misplaced Pages shouldn't accept an equivalent painting made with AI. That is, one where any obvious defects have been edited out and what remains is a straightforward picture of the subject. lethargilistic (talk) 03:45, 3 January 2025 (UTC)
For the record (and for any media watching), while I personally find it fascinating that a few editors here are spending a substantial amount of time (in the face of an overwhelming 'absolutely not' consensus no less) attempting to convince others that computer-generated (that is, faked) photos of human article subjects are somehow a good thing, I also find it interesting that these editors seem to express absolutely no concern for the intensely negative reaction they're already seeing from their fellow editors and seem totally unconcerned about the inevitable trust drop we'd experience from Misplaced Pages readers when they would encounter fake photos on our BLP articles especially. :bloodofox: (talk) 03:54, 3 January 2025 (UTC)
Misplaced Pages's reputation would not be affected positively or negatively by expanding the current-albeit-sparse use of illustrations to depict subjects that do not have available pictures. In all my writing about this over the last few days, you are the only one who has said anything negative about me as a person or, really, my arguments themselves. As loath as I am to cite it, WP:AGF means assuming that people you disagree with are not trying to hurt Misplaced Pages. Thryduulf, I, and others have explained in detail why we think our ultimate ideas are explicit benefits to Misplaced Pages and why our opposition to these immediate proposals comes from a desire to prevent harm to Misplaced Pages. I suggest taking a break to reflect on that, matey. lethargilistic (talk) 04:09, 3 January 2025 (UTC)
Look, I don't know if you've been living under a rock or what for the past few years but the reality is that people hate AI images and dumping a ton of AI/fake images on Misplaced Pages, a place people go for real information and often trust, inevitably leads to a huge trust issue, something Misplaced Pages is increasingly suffering from already. This is especially a problem when they're intended to represent living people (!). I'll leave it to you to dig up the bazillion controversies that have arisen and continue to arise since companies worldwide have discovered that they can now replace human artists with 'AI art' produced by "prompt engineers" but you can't possibly expect us to ignore that reality when discussing these matters. :bloodofox: (talk) 04:55, 3 January 2025 (UTC)
Those trust issues are born from the publication of hallucinated information. I have only said that it should be OK to use an image on Misplaced Pages when it contains only verifiable information, which is the same standard we apply to text. That standard is and ought to be applied independently of the way the initial version of an image was created. lethargilistic (talk) 06:10, 3 January 2025 (UTC)
To my eye, the distinction between AI images and paintings here is less a question of medium and more of verifiability: the paintings we use (or at least the ones I can remember) are significant paintings that have been acknowledged in sources as being reasonable representations of a given person. By contrast, a purpose-generated AI image would be more akin to me painting a portrait of somebody here and now and trying to stick that on their article. The image could be a faithful representation (unlikely, given my lack of painting skills, but let's not get lost in the metaphor), but if my painting hasn't been discussed anywhere besides Misplaced Pages, then it's potentially OR or UNDUE to enshrine it in mainspace as an encyclopedic image. ModernDayTrilobite (talk • contribs) 05:57, 3 January 2025 (UTC)
An image contains a collection of facts, and those facts need to be verifiable just like any other information posted on Misplaced Pages. An image that verifiably resembles a subject as it is depicted in reliable sources is categorically not OR. Discussion in other sources is not universally relevant; we don't restrict ourselves to only previously-published images. If we did that, Misplaced Pages would have very few images. lethargilistic (talk) 06:18, 3 January 2025 (UTC)
Verifiable how? Only by the editor themselves comparing to a real photo (which was probably used by the LLM to create the image…).
Verifiable by comparing them to a reliable source. Exactly the same as what we do with text. There is no coherent reason to treat user-generated images differently than user-generated text, and the universalist tenor of this discussion has damaging implications for all user-generated images regardless of whether they were created with AI. Honestly, I rarely make arguments like this one, but I think it could show some intuition from another perspective: Imagine it's 2002 and Misplaced Pages is just starting. Most users want to contribute text to the encyclopedia, but there is a cadre of artists who want to contribute pictures. The text editors say the artists cannot contribute ANYTHING to Misplaced Pages because their images that have not been previously published are not verifiable. That is a double-standard that privileges the contributions of text-editors simply because most users are text-editors and they are used to verifying text; that is not a principled reason to treat text and images differently. Moreover, that is simply not what happened—The opposite happend, and images are treated as verifiable based on their contents just like text because that's a common sense reading of the rule. It would have been madness if images had been treated differently. And yet that is essentially the fundamentalist position of people who are extending their opposition to AI with arguments that apply to all images. If they are arguing verifiability seriously at all, they are pretending that the sort of degenerate situation I just described already exists when the opposite consensus has been reached consistently for years. In the related NOR thread, they even tried to say Wikipedians had "turned a blind eye" to these image issues as if negatively characterizing those decisions would invalidate the fact that those decisions were consensus. The motivated reasoning of these discussions has been as blatant as that. At the bottom of this dispute, I take issue with trying to alter the rules in a way that creates a new double-standard within verifiability that applies to all images but not text. That's especially upsetting when (despite my and others' best efforts) so many of us are still focusing SOLELY on their hatred for AI rather than considering the obvious second-order consequences for user-generated images as a whole. Frankly, in no other context has any Wikipedian ever allowed me to say text they wrote was "fake" or challenge an image based on whether it was "fake." The issue has always been verifiability, not provenance or falsity. Sometimes, IMO, that has lead to disaster and Misplaced Pages saying things I know to be factually untrue despite the contents of reliable sources. But that is the policy. We compare the contents of Misplaced Pages to reliable sources, and the contents of Misplaced Pages are considered verifiable if they cohere. I ask again: If Misplaced Pages's response to the creation of AI imaging tools is to crack down on all artistic contributions to Misplaced Pages (which seems to be the inevitable direction of these discussions), what does that say? If our negative response to AI tools is to limit what humans can do on Misplaced Pages, what does that say? Are we taking a stand for human achievements, or is this a very heated discussion of cutting off our nose to save our face? lethargilistic (talk) 23:31, 4 January 2025 (UTC)
"Verifiable by comparing them to a reliable source" - comparing two images and saying that one looks like the other is not "verifying" anything. The text equivalent is presenting something as a quotation that is actually a user-generated paraphrasing.
"Frankly, in no other context has any Wikipedian ever allowed me to say text they wrote was "fake" or challenge an image based on whether it was "fake."" - Try presenting a paraphrasing as a quotation and see what happens.
"Imagine it's 2002 and Misplaced Pages is just starting. Most users want to contribute text to the encyclopedia, but there is a cadre of artists who want to contribute pictures..." - This basically happened, and is the origin of WP:NOTGALLERY. Misplaced Pages is not a host for original works. FOARP (talk) 22:01, 6 January 2025 (UTC)
Comparing two images and saying that one looks like the other is not "verifying" anything. Comparing text to text in a reliable source is literally the same thing.
The text equivalent is presenting something as a quotation that is actually a user-generated paraphrasing. No it isn't. The text equivalent is writing a sentence in an article and putting a ref tag on it. Perhaps there is room for improving the referencing of images in the sense that they should offer example comparisons to make. But an image created by a person is not unverifiable simply because it is user-generated. It is not somehow more unverifiable simply because it is created in a lifelike style.
Try presenting a paraphrasing as a quotation and see what happens. Besides what I just said, nobody is even presenting these images as equatable to quotations. People in this thread have simply been calling them "fake" of their own initiative; the uploaders have not asserted that these are literal photographs to my knowledge. The uploaders of illustrations obviously did not make that claim either. (And, if the contents of the image is a copyvio, that is a separate issue entirely.)
This basically happened, and is the origin of WP:NOTGALLERY. That is not the same thing. User-generated images that illustrate the subject are not prohibited by WP:NOTGALLERY. Misplaced Pages is a host of encyclopedic content, and user-generated images can have encyclopedic content. lethargilistic (talk) 02:41, 7 January 2025 (UTC)
Images are way more complex than text. Trying to compare them in the same way is a very dangerous simplification. Cremastra (u — c) 02:44, 7 January 2025 (UTC)
Assume only non-free images exist of a person. An illustrator refers to those non-free images and produces a painting. From that painting, you see a person who looks like the person in the non-free photographs. The image is verified as resembling the person. That is a simplification, but to call it "dangerous" is disingenuous at best. The process for challenging the image is clear. Someone who wants to challenge the veracity of the image would just need to point to details that do not align. For instance, "he does not typically have blue hair" or "he does not have a scar." That is what we already do, and it does not come up much because it would be weird to deliberately draw an image that looks nothing like the person. Additionally, someone who does not like the image for aesthetic reasons rather than encyclopedic ones always has the option of sourcing a photograph some other way like permission, fair use, or taking a new one themself. This is not an intractable problem. lethargilistic (talk) 02:57, 7 January 2025 (UTC)
So a photorealistic AI-generated image would be considered acceptable until someone identifies a "big enough" difference? How is that anything close to ethical? An portrait that's got an extra mole or slightly wider nose bridge or lacks a scar is still not an image of the person regardless of whether random Misplaced Pages editors notice. And while I don't think user-generated non-photorealistic images should ever be used on biographies either, at least those can be traced back to a human who is ultimately responsible for the depiction, who can point to the particular non-free images they used as references, and isn't liable to average out details across all time periods of the subject. And that's not even taking into account the copyright issues. JoelleJay (talk) 22:52, 7 January 2025 (UTC)
+1 to what JoelleJay said. The problem is that AI-generated images are simulations trying to match existing images, sometimes, yes, with an impressive degree of accuracy. But they will always be inferior to a human-drawn painting that's trying to depict the person. We're a human encyclopedia, and we're built by humans doing human things and sometimes with human errors. Cremastra (u — c) 23:18, 7 January 2025 (UTC)
You can't just raise this to an "ethical" issue by saying the word "ethical." You also can't just invoke copyright without articulating an actual copyright issue; we are not discussing copyvio. Everyone agrees that a photo with an actual copyvio in it is subject to that policy.
But to address your actual point: Any image—any photo—beneath the resolution necessary to depict the mole would be missing the mole. Even with photography, we are never talking about science-fiction images that perfectly depict every facet of a person in an objective sense. We are talking about equipment that creates an approximation of reality. The same is true of illustrations and AI imagery.
Finally, a human being is responsible for the contents of the image because a human is selecting it and is responsible for correcting any errors. The result is an image that someone is choosing to use because they believe it is an appropriate likeness. We should acknowledge that human decision and evaluate it naturally—Is it an appropriate likeness?lethargilistic (talk) 10:20, 8 January 2025 (UTC)
(Second comment because I'm on my phone.) I realize I should also respond to this in terms of additive information. What people look like is not static in the way your comment implies. Is it inappropriate to use a photo because they had a zit on the day it was taken? Not necessarily. Is an image inappropriate because it is taken at a bad angle that makes them look fat? Judging by the prolific ComicCon photographs (where people seem to make a game of choosing the worst-looking options; seriously, it's really bad), not necessarily. Scars and bruises exist and then often heal over time. The standard for whether an image with "extra" details is acceptable would still be based on whether it comports acceptably with other images; we literally do what you have capriciously described as "unethical" and supplement it with our compassionate desire to not deliberately embarrass BLPs. (The ComicCon images aside, I guess.) So, no, I would not be a fan of using images that add prominent scars where the subject is not generally known to have one, but that is just an unverifiable fact that does not belong in a Misplaced Pages image. Simple as. lethargilistic (talk) 10:32, 8 January 2025 (UTC)
We don't evaluate the reliability of a source solely by comparing it to other sources. For example, there is an ongoing discussion at the baseball WikiProject talk page about the reliability of a certain web site. It lists no authors nor any information on its editorial control policy, so we're not able to evaluate its reliability. The reliability of all content being used as a source, including images, needs to be considered in terms of its provenance. isaacl (talk) 23:11, 7 January 2025 (UTC)
Still no, I thought I was clear on that but we should not be using AI-generated images in articles for anything besides representing the concept of AI-generated images, or if an AI-generated image is notable or irreplaceable in its own right -- e.g, a musician uses AI to make an album cover.
(this isn't even a good example, it looks more like Steve Bannon)
I still think no. My opposition isn't just to the fact that AI images are misinformation, but also that they essentially serve as a loophole for getting around Enwiki's image use policy. To know what somebody looks like, an AI generator needs to have images of that person in its dataset, and it draws on those images to generate a derivative work. If we have no free images of somebody and we use AI to make one, that's just using a fair use copyrighted image but removed by one step. The image use policy prohibits us from using fair use images for BLPs so I don't think we should entertain this loophole. If we do end up allowing AI images in BLPs, that just disqualifies the rationale of not allowing fair use in the first place. Di (they-them) (talk) 04:40, 3 January 2025 (UTC)
No those are not okay, as this will just cause arguments from people saying a picture is obviously AI-generated, and that it is therefore appropriate. As I mentionned above, there are some exceptions to this, which Gnomingstuff perfectly describes. Fake sketches/cartoons are not appropriate and provide little encyclopedic value. win8x (talk) 05:27, 3 January 2025 (UTC)
No to this as well, with the same carveout for individual images that have received notable discussion. Non-photorealistic AI images are going to be no more verifiable than photorealistic ones, and on top of that will often be lower-quality as images. ModernDayTrilobite (talk • contribs) 05:44, 3 January 2025 (UTC)
No, and that image should be deleted before anyone places it into a mainspace article. Changing the RfC intro long after its inception seems a second bite at an apple that's not aged well. Randy Kryn (talk) 09:28, 3 January 2025 (UTC)
The RfC question has not been changed; another editor was complaining that the RfC question did not make a distinction between photorealistic/non-photorealistic AI-generated images, so I had to add a note to the intro and ping the editors who'd voted !No to clarify things. It has only been 3 days; there's still 27 more days to go. Some1 (talk) 11:18, 3 January 2025 (UTC)
Also answering No to this one per all the arguments above. "It has only been 3 days" is not a good reason to change the RfC question, especially since many people have already !voted and the "30 days" is mostly indicative rather than an actual deadline for a RfC. Chaotic Enby (talk · contribs) 14:52, 3 January 2025 (UTC)
No. We're the human encyclopedia. We should have images drawn or taken by real humans who are trying to depict the subject, not by machines trying to simulate an image. Besides, the given example is horribly drawn. Cremastra (u — c) 15:03, 3 January 2025 (UTC)
I like these even less than the photorealistic ones... This falls into the same basket for me: if we wouldn't let a random editor who drew this at home using conventional tools add it to the article why would we let a random editor who drew this at home using AI tools at it to the article? (and just to be clear the AI generated image of Germán Larrea Mota-Velasco is not recognizable as such) Horse Eye's Back (talk) 16:06, 3 January 2025 (UTC)
No Having such images as said above means the AI had to use copyrighted pictures to create it and we shouldn't use it. --SuperJew (talk) 01:12, 5 January 2025 (UTC)
Still no. If for no other reason than that it's a bad precedent. As others have said, if we make one exception, it will just lead to arguments in the future about whether something is "realistic" or not. I also don't see why we would need cartoon/illustrated-looking AI pictures of people in BLPs. Tepkunset (talk) 20:43, 6 January 2025 (UTC)
Absolutely not. These images are based on whatever the AI could find on the internet, with little to no regard for copyright. Misplaced Pages is better than this. Retswerb (talk) 10:16, 3 January 2025 (UTC)
Comment The RfC question should not have been fiddled with, esp. for such a minor argument that the complai9nmant could have simply included in their own vote. I have no need to re-confirm my own entry. Zaathras (talk) 14:33, 3 January 2025 (UTC)
The RfC question hasn't been modified; I've only added a 03:58, January 3, 2025: Note clarifying that these images can either be photorealistic in style or non-photorealistic in style. I pinged all the !No voters to make them aware. I could remove the Note if people prefer that I do (but the original RfC question is the exact same as it is now, so I don't think the addition of the Note makes a whole ton of difference). Some1 (talk) 15:29, 3 January 2025 (UTC)
No At this point it feels redundant, but I'll just add to the horde of responses in the negative. I don't think we can fully appreciate the issues that this would cause. The potential problems and headaches far outweigh whatever little benefit might come from AI images for BLPs. pillowcrow21:34, 3 January 2025 (UTC)
Support temporary blanket ban with a posted expiration/requred rediscussion date of no more than two years from closing. AI as the term is currently used is very, very new. Right now these images would do more harm than good, but it seems likely that the culture will adjust to them. Darkfrog24 (talk) 23:01, 3 January 2025 (UTC)
No. Misplaced Pages is made by and for humans. I don't want to become Google. Adding an AI-generated image to a page whose topic isn't about generative AI makes me feel insulted. SWinxy (talk) 00:03, 4 January 2025 (UTC)
No. Generative AI may have its place, and it may even have a place on Misplaced Pages in some form, but that place isn't in BLPs. There's no reason to use images of someone that do not exist over a real picture, or even something like a sketch, drawing, or painting. Even in the absence of pictures or human-drawn/painted images, I don't support using AI-generated images; they're not really pictures of the person, after all, so I can't support using them on articles of people. Using nothing would genuinely be a better choice than generated images. SmittenGalaxy | talk!01:07, 4 January 2025 (UTC)
No. Even if you are willing to ignore the inherently fraught nature of using AI-generated anything in relation to BLP subjects, there is simply little to no benefit that could possibly come from trying something like this. There's no guarantee the images will actually look like the person in question, and therefore there's no actual context or information that the image is providing the reader. What a baffling proposal. Ithinkiplaygames (talk) 19:53, 4 January 2025 (UTC)
There's no guarantee the images will actually look like the person in question there is no guarantee any image will look like the person in question. When an image is not a good likeness, regardless of why, we don't use it. When am image is a good likeness we consider using it. Whether an image is AI-generated or not it is completely independent of whether it is a good likeness. There are also reason other then identification why images are used on BLP-articles. Thryduulf (talk) 20:39, 4 January 2025 (UTC)
Foreseeably there may come a time when people's official portraits are AI-enhanced. That time might not be very far in the future. Do we want an exception for official portraits?—S MarshallT/C01:17, 5 January 2025 (UTC)
Yes, depending on specific case. One can use drawings by artists, even such as caricature. The latter is an intentional distortion, one could say an intentional misinformation. Still, such images are legitimate on many pages. Or consider numerous images of Jesus. How realiable are they? I am not saying we must deliberatly use AI images on all pages, but they may be fine in some cases. Now, speaking on "medical articles"... One might actually use the AI generated images of certain biological objects like proteins or organelles. Of course a qualified editorial judgement is always needed to decide if they would improve a specific page (frequently they would not), but making a blanket ban would be unacceptable, in my opinion. For example, the images of protein models generatated by AlphaFold would be fine. The AI-generated images of biological membranes I saw? I would say no. It depends. My very best wishes (talk) 02:50, 5 January 2025 (UTC)
This is complicated of course. For example, there are tools that make an image of a person that (mis)represents him as someone much better and clever than he really is in life. That should be forbidden as an advertisement. This is a whole new world, but I do not think that a blanket rejection would be appropriate. My very best wishes (talk) 03:19, 5 January 2025 (UTC)
No Too risky for BLP's. Besides if people want AI generated content over editor made content, we should make it clear they are in the wrong place, and readers should be given no doubt as to our integrity, sincerity and effort to give them our best, not a program's. Alanscottwalker (talk) 14:51, 5 January 2025 (UTC)
No, as AI's grasp on the Internet takes hold stronger and stronger, it's important Misplaced Pages, as the online encyclopedia it sets out to be, remains factual and real. Using AI images on Wiki would likely do more harm than good, further thinning the boundaries between what's real and what's not. – zmbro(talk) (cont)16:52, 5 January 2025 (UTC)
No, not at the moment. I think it will hard to avoid portraits that been enhanced by AI, as it already been on-going for a number of years and there is no way to avoid it, but I don't want arbitary generated AI portraits of any type. scope_creep20:19, 5 January 2025 (UTC)
No for natural images (e.g. photos of people). Generative AI by itself is not a reliable source for facts. In principle, generating images of people and directly sticking them in articles is no different than generating text and directly sticking it in articles. In practice, however, generating images is worse: Text can at least be discussed, edited, and improved afterwards. In contrast, we have significantly less policy and fewer rigorous methods of discussing how AI-generated images of natural objects should be improved (e.g. "make his face slightly more oblong, it's not close enough yet"). Discussion will devolve into hunches and gut feelings about the fidelity of images, all of which essentially fall under WP:OR. spintheer (talk) 20:37, 5 January 2025 (UTC)
No I'm appalled that even a small minority of editors would support such an idea. We have enough credibility issues already; using AI-generated images to represent real people is not something that a real encyclopedia should even consider. LEPRICAVARK (talk) 22:26, 5 January 2025 (UTC)
No I understand the comparison to using illustrations in BLP articles, but I've always viewed that as less preferable to no picture in all honestly. Images of a person are typically presented in context, such as a performer on stage, or a politician's official portrait, and I feel like there would be too many edge cases to consider in terms of making it clear that the photo is AI generated and isn't representative of anything that the person specifically did, but is rather an approximation. Tpdwkouaa (talk) 06:50, 6 January 2025 (UTC)
No - Too often the images resemble caricatures. Real caricatures may be included in articles if the caricature (e.g., political cartoon) had significant coverage and is attributed to the artist. Otherwise, representations of living persons should be real representations taken with photographic equipment. Robert McClenon (talk) 02:31, 7 January 2025 (UTC)
No - Not only is this effectively guesswork that usually includes unnatural artefacts, but worse, it is also based on unattributed work of photographers who didn't release their work into public domain. I don't care if it is an open legal loophole somewhere, IMO even doing away with the fair use restriction on BLPs would be morally less wrong. I suspect people on whose work LLMs in question were trained would also take less offense to that option. DaßWölf23:25, 7 January 2025 (UTC)
No – WP:NFC says that Non-free content should not be used when a freely licensed file that serves the same purpose can reasonably be expected to be uploaded, as is the case for almost all portraits of living people. While AI images may not be considered copyrightable, it could still be a copyright violation if the output resembles other, copyrighted images, pushing the image towards NFC. At the very least, I feel the use of non-free content to generate AI images violates the spirit of the NFC policy. (I'm assuming copyrighted images of a person are used to generate an AI portrait of them; if free images of that person were used, we should just use those images, and if no images of the person were used, how on Earth would we trust the output?) RunningTiger123 (talk) 02:43, 8 January 2025 (UTC)
The discussion above is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.
Expiration date?
"AI," as the term is currently used, is very new. It feels like large language models and the type of image generators under discussion just got here in 2024. (Yes, I know it was a little earlier.) The culture hasn't completed its initial response to them yet. Right now, these images do more harm than good, but that may change. Either we'll come up with a better way of spotting hallucinations or the machines will hallucinate less. Their copyright status also seems unstable. I suggest that any ban decided upon here have some expiration date or required rediscussion date. Two years feels about right to me, but the important thing would be that the ban has a number on it. Darkfrog24 (talk) 23:01, 3 January 2025 (UTC)
No need for any end-date. If there comes a point where consensus on this changes, then we can change any ban then. FOARP (talk) 05:27, 5 January 2025 (UTC)
An end date is a positive suggestion. Consensus systems like Misplaced Pages's are vulnerable to half-baked precedential decisions being treated as inviolate. With respect, this conversation does not inspire confidence that this policy proposal's consequences are well-understood at this time. If Misplaced Pages goes in this direction, it should be labeled as primarily reactionary and open to review at a later date. lethargilistic (talk) 10:22, 5 January 2025 (UTC)
Agree with FOARP, no need for an end date. If something significantly changes (e.g. reliable sources/news outlets such as the New York Times, BBC, AP, etc. start using text-to-image models to generate images of living people for their own articles) then this topic can be revisited later. Editors will have to go through the usual process of starting a new discussion/proposal when that time comes. Some1 (talk) 11:39, 5 January 2025 (UTC)
Seeing as this discussion has not touched at all on what other organizations may or may not do, it would not be accurate to describe any consensus derived from this conversation in terms of what other organizations may or may not be doing. That is, there has been no consensus that we ought to be looking to the New York Times as an example. Doing so would be inadvisable for several reasons. For one, they have sued an AI company over semi-related issues and they have teams explicitly working on what the future of AI in news ought to look like, so they have some investment in what the future of AI looks like and they are explicitly trying to shape its norms. For another, if they did start to use AI in a way that may be controversial, they would have no positive reason to disclose that and many disincentives. They are not a neutral signal on this issue. Misplaced Pages should decide for itself, preferably doing so while not disrupting the ability of people to continue creating user-generated images. lethargilistic (talk) 03:07, 6 January 2025 (UTC)
No need per others. Additionally, if practices change, it doesn't mean editors will decide to follow new practices. As for the technology, it seems the situation has been fairly stable for the past two years: we can detect some fakes and hallucinations immediately, many more in the past, but certainly not all retouched elements and all generated photos available right now, even if there was a readily accessible tool or app that enabled ordinary people to reliably do so.
Through the history, art forgeries have been fairly reliably detected, but rarely quickly. Relatedly, I don't see why the situation with AI images would change in the next 24 months or any similar time period. DaßWölf22:17, 9 January 2025 (UTC)
Non-Admin XFD Close as Delete
There is a contentious Deletion Review currently resulting from a Non-administrative close of a Redirect for Discussion in which the closer found that the consensus was Delete. The closer then tagged the redirect with G6, in particular {{db-xfd}}. It was then deleted by an admin who had taken part in the deletion discussion. The guideline on non-administrative closes says that a non-administrative close of Delete is not permitted, because the closer cannot press the Delete button. The first question at DRV seems to be whether DRV must vacate the close and allow a new close by an uninvolved administrator, or whether DRV can endorse the close and leave the close standing. My opinion is that a DRV endorsement of a non-admin close is as good a close as a regular admin close, but that is only my opinion.
The second question that is raised by the DRV discussion is about the existing practice that non-admins sometimes make Delete closes at CFD. Should this practice be stopped, because the guideline says that non-admins may not make Delete closes, or should the guideline be revised, or should the guideline be left as is, but with such closes being sometimes allowed? My own opinion is that if it is necessary sometimes to allow a practice that is contrary to the guideline, the guideline should be revised, so as to reduce the load at DRV, but that is only my opinion.
On the first question, I think that whatever decision DRV makes at Misplaced Pages:Deletion review#Clock/calendar will be 'legal'. They are not required to vacate the close, no matter how much one editor might like to have a second bite at that apple.
On your second question, I prefer the existing rules. It is not necessary to allow NACs (non-admin closures) of 'delete'. Good admins will not blindly trust anyone else's decision, so a NAC to delete does not necessarily save any time, and if the admin disagrees, then it could cause drama. NACs to delete should be gently but firmly discouraged. WhatamIdoing (talk) 07:30, 31 December 2024 (UTC)
As I said at the Deletion Review, I support non-admins closing RfDs as Delete. If TfDs have been made an exception, RfDs can be too. Closing a heavily discussed nomination at RfD is more about the reading, analysis and thought process at arriving at the outcome, and less about the technicality of the subsequent page actions. It will help making non-admins mentally prepared to advance to admin roles. Jay 💬17:28, 1 January 2025 (UTC)
It seems dumb to think that a close can go through DRV and 'pass' only for it to be vacated because the closer didn't have the right credentials. If the close is found to be good, does it matter who closed it? If bad Delete closes by non-admins were regular occurrences, then maybe, but I don't imagine this is the case. Cessaune19:12, 1 January 2025 (UTC)
The only problem is that if it becomes a regular occurrence, it creates more work overall. An admin can delete and carry out the delete. A non-admin can say it needs to be deleted, but still needs an admin to carry out the delete. That's why this should be discouraged - if it becomes commonplace it will generate a lot more work, but a one-off can clearly be endorsed at DRV. SportingFlyerT·C19:26, 1 January 2025 (UTC)
I think it's time for the long-standing "it creates more work" argument to be retired. In the first scenario, person 1 does A and B. In the second scenario, person 1 does A and person 2 does B. That does not create more work overall, it's the same amount of work overall, and it reduces work for person 1. Splitting work between two people doesn't create more work. Levivich (talk) 14:55, 4 January 2025 (UTC)
If person 2 here did B without doing any additional work whatsoever, then person 2 shouldn't be able to do B. We expect admins to look at what they're deleting. Plus, you're creating additional work for persons 3-20, who are watching CAT:CSD and don't appreciate demands to go sanity-check low-urgency, possibly-complex closes at unfamiliar deletion venues mixed into the copyright infringement, spam, and attack pages they're trying to prioritize. —Cryptic15:15, 4 January 2025 (UTC)
Discussion of How Much Attention Admins Pay to What They Are Deleting
No, we don't expect admins to look at what they're deleting. Anyone familiar with the admin deletion stats (as you are) knows that every day, admins delete many pages without ever looking at them. Person 2 can do B without A. It's OK for person 2 to rely on person 1 to do A correctly. It's not true that in order for person 2 to do B then person 2 must also have done A, and it's not how we operate with other deletions. Non-admins are perfectly capable of closing RfCs and many other discussions; there is nothing about a deletion discussion that suddenly makes non-admins unable to summarize consensus. There is no reason an admin can't rely on a non-admins summary of consensus, just as admins rely on non-admins CSD tagging. Levivich (talk) 15:21, 4 January 2025 (UTC)
We absolutely do expect admins to look at what they're deleting. At most a NAC delete close can save an admin the trouble of writing the close themself, but if an admin is blindly deleting without verifying that the CSD tag is actually valid for CSD then sooner or later they're going to wind up at WP:ANI. Anomie⚔15:49, 4 January 2025 (UTC)
Levivich, I agree with your conclusion, but not with your analogy. As Anomie pointed out, we do not blindly delete pages tagged as CSD. WP:CSD specifically instructs us to verify that the page meets a speedy deletion criterion, rather than just appeared as such to one user. This is a very different situation to an AfD that garnered consensus among multiple editors over the course of at least seven days, where the admin's job is just to verify that the NAC read consensus correctly. Owen×☎16:01, 4 January 2025 (UTC)
We can say it all we want but we can't argue with WP:ADMINSTATS. The admin who has deleted over 1 million pages did not read 1 million pages. Nor did the admin who deleted 800,000 pages read 800,000 pages. An admin who has deleted 600,000 pages--no doubt without reading even half of them--just got elected to arbcom. Nobody is taking those admins to ANI or thinks they're doing anything wrong (including me).
So no, admins don't read the pages they delete, and no, we don't expect them to, as proven by the massive number of deletions, and no, admins who delete without reading aren't taken to ANI, they're promoted. This includes CSDs.
More broadly, there is no reason not to allow admins to rely on non-admin XfD closures when making deletion decisions. We already do this for multiple types of XfDs, we can and should do it for AfDs. Levivich (talk) 16:05, 4 January 2025 (UTC)
Explicit didn't have to read over one million pages, because most of those deletions were the result of an XfD, not a CSD. He had to review almost a million XfD discussions to make sure consensus was to delete, which is exactly what he does when closing. And the majority of CSD deletions are of clumsy, unsourced self-promotion pages that take less than ten seconds to assess and confirm as such. I know for a fact that Liz -- number #3 on that list -- carefully reviews every speedy-tagged page before deleting it, and routinely rejects such requests when they do not meet CSD. Levivich, you are making some serious accusations here, with zero evidence to support them. I don't think this will help your case here. Owen×☎16:24, 4 January 2025 (UTC)
I have no case here and I'm making no accusations. If you want to believe that a person has read over a million XfDs, you go ahead and believe that. I don't, because even over 15 years, that would be 182 XfDs a day every day with no days off, and I don't believe anyone does, or is capable of doing, that much XfD reading. Levivich (talk) 17:03, 4 January 2025 (UTC)
Levivich You're completely wrong, because you're missing a number of very obvious issues with those statistics.
Not even a majority of Explicit's deletions are XfDs - most are speedies
Many are G13 deletions, which don't need any analysis, they're simply done on timeframe. You can do those in seconds. Similarly U1, R2 and F8
Most articles have a talk page, which also needs to be deleted (G8), so deleting most articles means two deletions.
RfDs don't take very long to close at all; most are unanimous
Of Explicit's last 500 deletions, only 58 have been XfDs (and their associated talk pages where they existed, making 97 deletions).
The vast majority of the rest have been G13, G8, U1, R2 and F8.
Owen: Explicit didn't have to read over one million pages, because most of those deletions were the result of an XfD, not a CSD
BK: Not even a majority of Explicit's deletions are XfDs - most are speedies
I don't know which one of you is wrong but it doesn't matter. Explicit did not read 1 million pages over the last 15 years prior to deleting them, whether they were XfDs or CSDs. Nobody is reading 182 Misplaced Pages pages 7 days a week for 15 years. Nobody has read a million Misplaced Pages pages. No human can thoroughly review 182 things a day. It's mathematics, guys. If a person spends 5 minutes on each review -- which isn't a thorough review of anything -- that's 15 hours per day to do 182 reviews. Nobody is spending that much time, 7 days a week, for 15 years. Even if the person spends just 1 minute, that's over 3 hours a day... every day for 15 years. The math proves that Explicit is spending maybe 1 minute per deletion.
Now: an admin spending 1 minute per deletion is not providing any real kind of level of oversight that can't be provided by a non-admin closing the XfD and the admin then spending 1 minute reviewing the close and deleting the page.
The math and the stats don't lie. The suggestion that admins carefully review every page before deleting them is plainly not true. The suggestion that if admins didn't do that, they'd be taken to ANI, is also plainly not true. We have admins spending a minute or less per deletion and not being taken to ANI. These are facts. Levivich (talk) 19:31, 4 January 2025 (UTC)
Your "math" is based on a lot of faulty assumptions and oversimplifications, which you seem to be persisting in despite others trying to correct you. Anomie⚔20:42, 4 January 2025 (UTC)
Those are not facts, because your data is faulty. Your reply simply tells me that you didn't read what I wrote. Someone with the editing pattern of Explicit isn't reviewing 182 things a day. Nowhere near that. Quite apart from the talk page issue (which, if every page had a talk page, would immediately halve the number of reviews) in some of the speedy categories I mention there's nothing to review; it's simply pressing a button. Indeed, deleting the articles in the stale G13 queue, orphaned G8 queue, or the F5 or F8 category, can result in dozens - even hundreds - of deletions in one button press. As an example, on the 3rd January alone, Explicit deleted 113 F8 images, plus 83 talk pages of those images. That's 196 deletions, all done in a few seconds, as there's nothing to review. In comparison, the number of XfDs he closed that day was 25. Black Kite (talk)21:21, 4 January 2025 (UTC)
Cryptic: We expect admins to look at what they're deleting.
BK: That's 196 deletions, all done in a few seconds, as there's nothing to review.
I disagreed with Cryptic's point, and thank you BK for providing an example of exactly what I'm talking about. We do not expect admins to review (or "look at") what they're deleting, sometimes there's not even anything to look at. Admins delete things without reviewing what they're deleting all the time, and they're not hauled off to ANI for it. BK, you're arguing with me, but you're not actually disagreeing with what I'm saying. You're not arguing, as others have said above, that all admins review everything they delete before they delete it, or that this is the community expectation. Levivich (talk) 22:24, 4 January 2025 (UTC)
I'm simply pointing out that the claim you have made The math proves that Explicit is spending maybe 1 minute per deletion. Now: an admin spending 1 minute per deletion is not providing any real kind of level of oversight that can't be provided by a non-admin closing the XfD and the admin then spending 1 minute reviewing the close and deleting the page. is not correct; Explicit is not spending 1 minute per XfD, he is spending 1 minute per deletion, and because in many cases the admin pressing the button is simply completing an automated process (in the case of G13, that the article has not been edited for six months; in the case of F8, that the identical file exists at Commons), and deleting many files in one button-press, that skews the data. Now, if you are saying that an admin is closing AfDs or deleting G7 or G11 speedies at a high rate (not just "deleting things"), and their speed suggests they aren't reviewing them carefully - then you have a point. Black Kite (talk)23:33, 4 January 2025 (UTC)
Not actually reviewing deletions to make sure they were correct was one of the two major factors that resulted in Arbcom desysopping RHaworth (the other was a refusal to engage with good-faith queries about his actions and refusing to engage at all with IP editors). As others have said, how long it takes to ensure that what you are deleting should be deleted varies considerably. For G13s it's as simple as checking that bot has correctly determined that a given timestamp was more than 6 months ago - either the entire batch will be correct or the entire batch will be incorrect. Most of the deletions I do are the result of RfDs, after determining that the consensus is to delete (which is usually very simple) I delete the page. The software then tells me that page has a talk page, at least 9 times out of 10 (maybe more) it takes less than a second to verify there isn't any any reason they are G8 exempt. There is no excuse for not doing the reviewing properly though because there are exceptions. Thryduulf (talk) 00:22, 5 January 2025 (UTC)
I didn't say Explicit is spending 1 minute per XfD, I said "per deletion." And your point about "many files in one button-press" is literally the same as my point, which is that admins don't carefully review every single thing they delete, they sometimes delete many files in one button press (196 deletions in a few seconds is an example). So, you agree with me that "we expect admins to look at what they're deleting" is not correct, it's actually disproven by the data. Levivich (talk) 00:37, 5 January 2025 (UTC)
Admins are expected to review everything they delete. It's just that in some cases many pages can be reviewed together very quickly. It is also possible to spend time carefully reviewing many pages in detail, assembling a list of which should be deleted and then deleting them the pages on that together with a single click. Thryduulf (talk) 01:08, 5 January 2025 (UTC)
It was in the context of XfDs, however ("If you want to believe that a person has read over a million XfDs, you go ahead and believe that"). Black Kite (talk)08:03, 5 January 2025 (UTC)
That was in response to someone saying they were mostly XfDs. The same point holds if they were mostly CSDs. That's why I said it doesn't matter whether they were mostly XfDs or CSDs. Regardless of whether it's XfD or CSD, when someone makes 500k or 1 million deletions, we know they didn't look at each and every individual thing (page, file, whatever) that was deleted, nor do we expect them to. (Which I said in response to people saying we expect admins to look at every single thing they delete.) Levivich (talk) 13:18, 5 January 2025 (UTC)
By pressing the delete button you are asserting that at least one of the following is true:
The page met the specified speedy deletion criterion (e.g. if the deletion log says G12 you are asserting the page, including all of its old revisions, was copyvio).
The page was eligible for PROD, this was the first time that it was prodded and nobody has objected to the prod.
The deletion of the page was discussed a the relevant XfD (or, exceptionally, in an RfC) and that the consensus of that discussion was to delete the page.
If an admin is not prepared to put their name to the truthfulness of that assertion then they should not be deleting the page. Thryduulf (talk) 16:12, 4 January 2025 (UTC)
My own opinion is that if it is necessary sometimes to allow a practice that is contrary to the guideline, the guideline should be revised, so as to reduce the load at DRV, but that is only my opinion - actually, Robert McClenon, your opinion is solidly anchored in policy. WP:NOTBURO tells us: the written rules themselves do not set accepted practice. Rather, they document already-existing community consensus regarding what should be accepted and what should be rejected. If CfD is working fine as it is, let's update policy to reflect the practice. Owen×☎16:09, 2 January 2025 (UTC)
Is there a guideline that says that unregistered editors (IP addresses) should not edit in Misplaced Pages space (project space)? We had am MFD discussion in which an unregistered editor asked a registered editor to nominate an essay for deletion. The registered editor did as requested, which I think is known as proxying. As I understand, unregistered editors cannot create new pages in either article space or project space, and an AFD or MFD discussion is its own page. The MFD was then closed as a Speedy Keep 1, because no rationale was given. The question has to do with a comment made by one of the MFD regular editors that IP editors should not edit in project space. Another editor questioned whether there was a guideline to that effect. I cannot recall having seen a guideline that restricts or discourages unregistered editors from editing in project space. Is there such a guideline? Robert McClenon (talk) 00:39, 1 January 2025 (UTC)
No, and anyone who claims there is can be safely disregarded as full of shit. (Not that it's the first time that people confidently claim false authority.) Gnomingstuff (talk) 08:11, 1 January 2025 (UTC)
Thank you. Three trouts were then in order. One to the unregistered editor, for not giving a reason for the deletion request. Two to the registered editor who was proxying, for making an MFD nomination without stating a reason. Three to the editor who said that IPs should stay out of project space. I think that the third editor would have had a case to argue that policy should be changed and the English Misplaced Pages should follow the Portuguese example of not permitting IP editing, but that is only my opinion and is an unrelated issue. Robert McClenon (talk) 16:30, 1 January 2025 (UTC)
Using AI to write your comments in a discussion makes it difficult for others to assume that you are discussing in good faith, rather than trying to use AI to argue someone into exhaustion (see example of someone using AI in their replies "Because I don't have time to argue with, in my humble opinion, stupid PHOQUING people"). More fundamentally, WP:AGF can't apply to the AI itself as AI lacks intentionality, and it is difficult for editors to assess how much of an AI-generated comment reflects the training of the AI vs. the actual thoughts of the editor.
No. As with all the other concurrent discussions (how many times do we actually need to discuss the exact same FUD and scaremongering?) the problem is not AI, but rather inappropriate use of AI. What we need to do is to (better) explain what we actually want to see in discussions, not vaguely defined bans of swathes of technology that, used properly, can aid communication. Thryduulf (talk) 01:23, 2 January 2025 (UTC)
Note that this topic is discussing using AI to generate replies, as opposed to using it as an aid (e.g. asking it to edit for grammar, or conciseness). As the above concurrent discussion demonstrates, users are already using AI to generate their replies in AfD, so it isn't scaremongering but an actual issue.
WP:DGF also does not ban anything ("Showing good faith is not required"), but offers general advice on demonstrating good faith. So it seems like the most relevant place to include mention of the community's concerns regarding AI-generated comments, without outright banning anything. Photos of Japan (talk) 01:32, 2 January 2025 (UTC)
And as pointed out, multiple times in those discussions, different people understand different things from the phrase "AI-generated". The community's concern is not AI-generated comments, but comments that do not clearly and constructively contribute to a discussion - some such comments are AI-generated, some are not. This proposal would, just as all the other related ones, cause actual harm when editors falsely accuse others of using AI (and this will happen). Thryduulf (talk) 02:34, 2 January 2025 (UTC)
Nobody signed up to argue with bots here. If you're pasting someone else's comment into a prompt and asking the chatbot to argue against that comment and just posting it in here, that's a real problema and absolutely should not be acceptable. :bloodofox: (talk) 03:31, 2 January 2025 (UTC)
Thank you for the assumption of bad faith and demonstrating one of my points about the harm caused. Nobody is forcing you to engage with bad-faith comments, but whether something is or is not bad faith needs to be determined by its content not by its method of generation. Simply using an AI demonstrates neither good faith nor bad faith. Thryduulf (talk) 04:36, 2 January 2025 (UTC)
I don't see why we have any particular to reason to suspect a respected and trustworthy editor of using AI. Cremastra (u — c) 14:31, 2 January 2025 (UTC)
I'm one of those people who clarified the difference between AI-generated vs. edited, and such a difference could be made explicit with a note. Editors are already accusing others of using AI. Could you clarify how you think addressing AI in WP:DGF would cause actual harm? Photos of Japan (talk) 04:29, 2 January 2025 (UTC)
By encouraging editors to accuse others of using AI, by encouraging editors to dismiss or ignore comments because they suspect that they are AI-generated rather than engaging with them. @Bloodofox has already encouraged others to ignore my arguments in this discussion because they suspect I might be using an LLM and/or be a bot (for the record I'm neither). Thryduulf (talk) 04:33, 2 January 2025 (UTC)
Given your relentlessly pro-AI comments here, it seems that you'd be A-OK with just chatting with a group of chatbots here — or leaving the discussion to them. However, most of us clearly are not. In fact, I would immediately tell someone to get lost were it confirmed that indeed that is what is happening. I'm a human being and find the notion of wasting my time with chatbots on Misplaced Pages to be incredibly insulting and offensive. :bloodofox: (talk) 04:38, 2 January 2025 (UTC)
My comments are neither pro-AI nor anti-AI, indeed it seems that you have not understood pretty much anything I'm saying. Thryduulf (talk) 04:43, 2 January 2025 (UTC)
Funny, you've done nothing here but argue for more generative AI on the site and now you seem to be arguing to let chatbots run rampant on it while mocking anyone who doesn't want to interface with chatbots on Misplaced Pages. Hey, why not just sell the site to Meta, am I right? :bloodofox: (talk) 04:53, 2 January 2025 (UTC)
I haven't been arguing for more generative AI on the site. I've been arguing against banning it on the grounds that such a ban would be unclear, unenforceable, wouldn't solve any problems (largely because whether something is AI or not is completely irrelevant to the matter at hand) but would instead cause harm. Some of the issues identified are actual problems, but AI is not the cause of them and banning AI won't fix them.
I'm not mocking anybody, nor am I advocating to let chatbots run rampant. I'm utterly confused why you think I might advocate for selling Misplaced Pages to Meta (or anyone else for that matter)? Are you actually reading anything I'm writing? You clearly are not understanding it. Thryduulf (talk) 05:01, 2 January 2025 (UTC)
So we're now in 'everyone else is the problem, not me!' territory now? Perhaps try communicating in a different way because your responses here are looking very much like the typical AI apologetics one can encounter on just about any contemporary LinkedIn thread from your typical FAANG employee. :bloodofox: (talk) 05:13, 2 January 2025 (UTC)
No, this is not a everyone else is the problem, not me issue because most other people appear to be able to understand my arguments and respond to them appropriately. Not everybody agrees with them, but that's not an issue.
I'm not familiar with Linkedin threads (I don't use that platform) nor what a "FAANG employee" is (I've literally never heard the term before now) so I have no idea whether your characterisation is a compliment or a personal attack, but given your comments towards me and others you disagree with elsewhere I suspect it's closer to the latter.
AI is a tool. Just like any other tool it can be used in good faith or in bad faith, it can be used well and it can be used badly, it can be used in appropriate situations and it can be used in inappropriate situations, the results of using the tool can be good and the results of using the tool can be bad. Banning the tool inevitably bans the good results as well as the bad results but doesn't address the reasons why the results were good or bad and so does not resolve the actual issue that led to the bad outcomes. Thryduulf (talk) 12:09, 2 January 2025 (UTC)
In the context of generating comments to other users though, AI is much easier to use for bad faith than for good faith. LLMs don't understand Misplaced Pages's policies and norms, and so are hard to utilize to generate posts that productively address them. By contrast, bad actors can easily use LLMs to make low quality posts to waste people's time or wear them down.
In the context of generating images, or text for articles, it's easy to see how the vast majority of users using AI for those purposes is acting in good faith as these are generally constructive tasks, and most people making bad faith changes to articles are either obvious vandals who won't bother to use AI because they'll be reverted soon anyways, or trying to be subtle (povpushers) in which case they tend to want to carefully write their own text into the article.
It's true that AI "is just a tool", but when that tool is much easier to use for bad faith purposes (in the context of discussions) then it raises suspicions about why people are using it. Photos of Japan (talk) 22:44, 2 January 2025 (UTC)
Not really – I agree with Thryduulf's arguments on this one. Using AI to help tweak or summarize or "enhance" replies is of course not bad faith – the person is trying hard. Maybe English is their second language. Even for replies 100% AI-generated the user may be an ESL speaker struggling to remember the right words (I always forget 90% of my French vocabulary when writing anything in French, for example). In this case, I don't think we should make a blanket assumption that using AI to generate comments is not showing good faith. Cremastra (u — c) 02:35, 2 January 2025 (UTC)
Yes because generating walls of text is not good faith. People "touching up" their comments is also bad (for starters, if you lack the English competency to write your statements in the first place, you probably lack the competency to tell if your meaning has been preserved or not). Exactly what AGF should say needs work, but something needs to be said, and AGFDGF is a good place to do it. XOR'easter (talk) 02:56, 2 January 2025 (UTC)
Not all walls of text are generated by AI, not all AI generated comments are walls of text. Not everybody who uses AI to touch up their comments lacks the competencies you describe, not everybody who does lack those competencies uses AI. It is not always possible to tell which comments have been generated by AI and which have not. This proposal is not particularly relevant to the problems you describe. Thryduulf (talk) 03:01, 2 January 2025 (UTC)
Someone has to ask: Are you generating all of these pro-AI arguments using ChatGPT? It'd explain a lot. If so, I'll happily ignore any and all of your contributions, and I'd advise anyone else to do the same. We're not here to be flooded with LLM-derived responses. :bloodofox: (talk) 03:27, 2 January 2025 (UTC)
That you can't tell whether my comments are AI-generated or not is one of the fundamental problems with these proposals. For the record they aren't, nor are they pro-AI - they're simply anti throwing out babies with bathwater. Thryduulf (talk) 04:25, 2 January 2025 (UTC)
I'd say it also illustrates the serious danger: We can no longer be sure that we're even talking to other people here, which is probably the most notable shift in the history of Misplaced Pages. :bloodofox: (talk) 04:34, 2 January 2025 (UTC)
How is that a "serious danger"? If a comment makes a good point, why does it matter whether ti was AI generated or not? If it doesn't make a good point, why does it matter if it was AI generated or not? How will these proposals resolve that "danger"? How will they be enforceable? Thryduulf (talk) 04:39, 2 January 2025 (UTC)
Misplaced Pages is made for people, by people, and I like most people will be incredibly offended to find that we're just playing some kind of LLM pong with a chatbot of your choice. You can't be serious. :bloodofox: (talk) 04:40, 2 January 2025 (UTC)
"why does it matter if it was AI generated or not?"
Because it takes little effort to post a lengthy, low quality AI-generated post, and a lot of effort for human editors to write up replies debunking them.
"How will they be enforceable? "
WP:DGF isn't meant to be enforced. It's meant to explain to people how they can demonstrate good faith. Posting replies to people (who took the time to write them) that are obviously AI-generated harms the ability of those people to assume good faith. Photos of Japan (talk) 05:16, 2 January 2025 (UTC)
The linked "example of someone using AI in their replies" appears – to me – to be a non-AI-generated comment. I think I preferred the allegedly AI-generated comments from that user (example). The AI was at least superficially polite. WhatamIdoing (talk) 04:27, 2 January 2025 (UTC)
Obviously the person screaming in all caps that they use AI because they don't want to waste their time arguing is not using AI for that comment. Their first post calls for the article to be deleted for not "offering new insights or advancing scholarly understanding" and "merely" reiterating what other sources have written.
Yes, after a human had wasted their time explaining all the things wrong with its first post, then the bot was able to write a second post which looks ok. Except it only superficially looks ok, it doesn't actually accurately describe the articles. Photos of Japan (talk) 04:59, 2 January 2025 (UTC)
Multiple humans have demonstrated in these discussions that humans are equally capable of writing posts which superficially look OK but don't actually accurately relate to anything they are responding to. Thryduulf (talk) 05:03, 2 January 2025 (UTC)
But I can assume that everyone here is acting in good faith. I can't assume good faith in the globally-locked sock puppet spamming AfD discussions with low effort posts, whose bot is just saying whatever it can to argue for the deletion of political pages the editor doesn't like. Photos of Japan (talk) 05:09, 2 January 2025 (UTC)
True, but I think that has more to do with the "globally-locked sock puppet spamming AfD discussions" part than with the "some of it might be " part. WhatamIdoing (talk) 07:54, 2 January 2025 (UTC)
All of which was discovered because of my suspicions from their inhuman, and meaningless replies. "Reiteration isn't the problem; redundancy is," maybe sounds pithy in a vacuum, but this was written in reply to me stating that we aren't supposed to be doing OR but reiterating what the sources say.
"Your criticism feels overly prescriptive, as though you're evaluating this as an academic essay" also sounds good, until you realize that the bot is actually criticizing its own original post.
The fact that my suspicions about their good faith were ultimately validated only makes it even harder for me to assume good faith in users who sound like ChatGPT. Photos of Japan (talk) 08:33, 2 January 2025 (UTC)
I wonder if we need some other language here. I can understand feeling like this is a bad interaction. There's no sense that the person cares; there's no feeling like this is a true interaction. A contract lawyer would say that there's no meeting of the minds, and there can't be, because there's no mind in the AI, and the human copying from the AI doesn't seem to be interested in engaging their brain.
The user's talk page has a header at the top asking people not to template them because it is "impersonal and disrespectful", instead requesting "please take a moment to write a comment below in your own words"
Does this look like acting in good faith to you? Requesting other people write personalized responses to them while they respond with an LLM? Because it looks to me like they are trying to waste other people's time. Photos of Japan (talk) 09:35, 2 January 2025 (UTC)
"Being hypocritical" in the abstract isn't the problem, it's the fact that asking people to put effort into their comments, while putting in minimal effort into your own comments appears bad faith, especially when said person says they don't want to waste time writing comments to stupid people. The fact you are arguing AGF for this person is both astounding and disappointing. Photos of Japan (talk) 16:08, 3 January 2025 (UTC)
It feels like there is a lack of reciprocity in the interaction, even leaving aside the concern that the account is a block-evading sock.
But I wonder if you have read AGF recently. The first sentence is "Assuming good faith (AGF) means assuming that people are not deliberately trying to hurt Misplaced Pages, even when their actions are harmful."
So we've got some of this (e.g., harmful actions). But do you really believe this person woke up in the morning and decided "My main goal for today is to deliberately hurt Misplaced Pages. I might not be successful, but I sure am going to try hard to reach my goal"? WhatamIdoing (talk) 23:17, 4 January 2025 (UTC)
Trying to hurt Misplaced Pages doesn't mean they have to literally think "I am trying to hurt Misplaced Pages", it can mean a range of things, such as "I am trying to troll Wikipedians". A person who thinks a cabal of editors is guarding an article page, and that they need to harass them off the site, may think they are improving Misplaced Pages, but at the least I wouldn't say that they are acting in good faith. Photos of Japan (talk) 23:27, 4 January 2025 (UTC)
The issues with AI in discussions is not related to good faith, which is narrowly defined to intent. CMD (talk) 04:45, 2 January 2025 (UTC)
In my mind, they are related inasmuch as it is much more difficult for me to ascertain good faith if the words are eminently not written by the person I am speaking to in large part, but instead generated based on an unknown prompt in what is likely a small fraction of the expected time. To be frank, in many situations it is difficult to avoid the conclusion that the disparity in effort is being leveraged in something less than good faith. Remsense ‥ 论05:02, 2 January 2025 (UTC)
Assume good faith, don't ascertain! Llm use can be deeply unhelpful for discussions and the potential for mis-use is large, but the most recent discussion I've been involved with where I observed an llm post was responded to by an llm post, I believe both the users were doing this in good faith. CMD (talk) 05:07, 2 January 2025 (UTC)
All I mean to say is it should be licit that unhelpful LLM use should be something that can be mentioned like any other unhelpful rhetorical pattern. Remsense ‥ 论05:09, 2 January 2025 (UTC)
The fact that everyone (myself included) defending "LLM use" says "use" rather than "generated", is a pretty clear sign that no one really wants to communicate with someone using "LLM generated" comments. We can argue about bans (not being proposed here), how to know if someone is using LLM, the nuances of "LLM use", etc., but at the very least we should be able to agree that there are concerns with LLM generated replies, and if we can agree that there are concerns then we should be able to agree that somewhere in policy we should be able to find a place to express those concerns. Photos of Japan (talk) 05:38, 2 January 2025 (UTC)
For instance, I am OK with someone using a LLM to post a productive comment on a talk page. I am also OK with someone generating a reply with a LLM that is a productive comment to post to a talk page. I am not OK with someone generating text with an LLM to include in an article, and also not OK with someone using a LLM to contribute to an article.
Most people already assume good faith in those making productive contributions. In situations where good faith is more difficult to assume, would you trust someone who uses an LLM to generate all of their comments as much as someone who doesn't? Photos of Japan (talk) 09:11, 2 January 2025 (UTC)
Given that LLM-use is completely irrelevant to the faith in which a user contributes, yes. Of course what amount that actually is may be anywhere between completely and none. Thryduulf (talk) 11:59, 2 January 2025 (UTC)
LLM-use is relevant as it allows bad faith users to disrupt the encyclopedia with minimal effort. Such a user posted in this thread earlier, as well as started a disruptive thread here and posted here, all using AI. I had previously been involved in a debate with another sock puppet of theirs, but at that time they didn't use AI. Now it seems they are switching to using an LLM just to troll with minimal effort. Photos of Japan (talk) 21:44, 2 January 2025 (UTC)
LLMs are a tool that can be used by good and bad faith users alike. Using an LLM tells you nothing about whether a user is contributing in good or bad faith. If somebody is trolling they can be, and should be, blocked for trolling regardless of the specifics of how they are trolling. Thryduulf (talk) 21:56, 2 January 2025 (UTC)
A can of spray paint, a kitchen knife, etc., are tools that can be used for good or bad, but if you bring them some place where they have few good uses and many bad uses then people will be suspicious about why you brought them. You can't just assume that a tool in any context is equally harmless. Using AI to generate replies to other editors is more suspicious than using it to generate a picture exemplifying a fashion style, or a description of a physics concept. Photos of Japan (talk) 23:09, 2 January 2025 (UTC)
WP:AGF is not a death pact though. At times you should be suspicious. Do you think that if a user, who you already have suspicions of, is also using an LLM to generate their comments, that that doesn't have any effect on those suspicions? Photos of Japan (talk) 21:44, 2 January 2025 (UTC)
So… If you suspect that someone is not arguing in good faith… just stop engaging them. If they are creating walls of text but not making policy based arguments, they can be ignored. Resist the urge to respond to every comment… it isn’t necessary to “have the last word”. Blueboar (talk) 21:57, 2 January 2025 (UTC)
That they've been banned for disruption indicates we can do everything we need to do to deal with bad faith users of LLMs without assuming that everyone using an LLM is doing so in bad faith. Thryduulf (talk) 00:33, 3 January 2025 (UTC)
I don't believe we should assume everyone using an LLM is doing so in bad faith, so I'm glad you think my comment indicates what I believe. Photos of Japan (talk) 01:09, 3 January 2025 (UTC)
No -- whatever you think of LLMs, the reason they are so popular is that the people who use them earnestly believe they are useful. Claiming otherwise is divorced from reality. Even people who add hallucinated bullshit to articles are usually well-intentioned (if wrong). Gnomingstuff (talk) 06:17, 2 January 2025 (UTC)
Yes I find it incredibly rude for someone to procedurally generate text and then expect others to engage with it as if they were actually saying something themselves. Simonm223 (talk) 14:34, 2 January 2025 (UTC)
Yes, mention that use of an LLM should be disclosed and that failure to do so is like not telling someone you are taping the call. Selfstudier (talk) 14:43, 2 January 2025 (UTC)
I could support general advice that if you're using machine translation or an LLM to help you write your comments, it can be helpful to mention this in the message. The tone to take, though, should be "so people won't be mad at you if it screwed up the comment" instead of "because you're an immoral and possibly criminal person if you do this". WhatamIdoing (talk) 07:57, 3 January 2025 (UTC)
No. When someone publishes something under their own name, they are incorporating it as their own statement. Plagiarism from an AI or elsewhere is irrelevant to whether they are engaging in good faith. lethargilistic (talk) 17:29, 2 January 2025 (UTC)
Comment LLMs know a few tricks about logical fallacies and some general ways of arguing (rhetoric), but they are incredibly dumb at understanding the rules of Misplaced Pages. You can usually tell this because it looks like incredibly slick and professional prose, but somehow it cannot get even the simplest points about the policies and guidelines of Misplaced Pages. I would indef such users for lacking WP:CIR. tgeorgescu (talk) 17:39, 2 January 2025 (UTC)
That guideline states "Sanctions such as blocks and bans are always considered a last resort where all other avenues of correcting problems have been tried and have failed." Gnomingstuff (talk) 19:44, 2 January 2025 (UTC)
I blocked that user as NOTHERE a few minutes ago after seeing them (using ChatGPT) make suggestions for text to live pagespace while their previous bad behaviors were under discussion. AGF is not a suicide pact. BusterD (talk) 20:56, 2 January 2025 (UTC)
Yes Using a 3rd party service to contribute to the Misplaced Pages on your behalf is clearly bad-faith, analogous to paying someone to write your article. Zaathras (talk) 14:39, 3 January 2025 (UTC)
Its a stretch to say that a newbie writing a comment using AI is automatically acting in bad faith and not here to build an encyclopedia. PackMecEng (talk) 16:55, 3 January 2025 (UTC)
Comment Large language model AI like Chat GPT are in their infancy. The culture hasn't finished its initial reaction to them yet. I suggest that any proposal made here have an automatic expiration/required rediscussion date two years after closing. Darkfrog24 (talk) 22:42, 3 January 2025 (UTC)
No – It is a matter of how you use AI. I use Google translate to add trans-title parameters to citations, but I am careful to check for Google's output making for good English as well as reflecting the foreign title when it is a language I somewhat understand. I like to think that I am careful, and I do not pretend to be fluent in a language I am not familiar with, although I usually don't announce the source of such a translation. If an editor uses AI profligately and without understanding the material generated, then that is the sin; not AI itself. Dhtwiki (talk) 05:04, 5 January 2025 (UTC)
There's a legal phrase, "when the exception swallows the rule", and I think we might be headed there with the recent LLM/AI discussions.
We start off by saying "Let's completely ban it!" Then in discussion we add "Oh, except for this very reasonable thing... and that reasonable thing... and nobody actually meant this other reasonable thing..."
Do you want us to reply to you, because you are a human? Or are you just posting the output of an LLM without bothering to read anything yourself? DS (talk) 06:08, 7 January 2025 (UTC)
Most likely you would reply because someone posted a valid comment and you are assuming they are acting in good faith and taking responsibility for what they post. To assume otherwise is kind of weird and not inline with general Misplaced Pages values. PackMecEng (talk) 15:19, 8 January 2025 (UTC)
No The OP seems to misunderstand WP:DGF which is not aimed at weak editors but instead exhorts stronger editors to lead by example. That section already seems to overload the primary point of WP:AGF and adding mention of AI would be quite inappropriate per WP:CREEP. Andrew🐉(talk) 23:11, 5 January 2025 (UTC)
Yes. AI use is not a demonstration of bad faith (in any case not every new good-faith editor is familiar with our AI policies), but it is equally not a "demonstration of good faith", which is what the WP:DGF section is about.
It seems some editors are missing the point and !voting as if every edit is either a demonstration of good faith or bad faith. Most interactions are neutral and so is most AI use, but I find it hard to imagine a situation where AI use would point away from unfamiliarity and incompetence (in the CIR sense), and it often (unintentionally) leads to a presumption of laziness and open disinterest. It makes perfect sense to recommend against it. DaßWölf22:56, 9 January 2025 (UTC)
Yes. Per Dass Wolf, though I would say passing off a completely AI-generated comment as your own anywhere is inherently bad-faith and one doesn't need to know Wiki policies to understand that. JoelleJay (talk) 23:30, 9 January 2025 (UTC)
Yes. Sure, LLMs may have utility somewhere, and it might be a crutch for people unfamiliar with English, but as I've said above in the other AI RfC, that's a competence issue. This is about comments eating up editor time, energy, about LLMs easily being used to ram through changes and poke at editors in good standing. I don't see a case wherein a prospective editor's command of policy and language is good enough to discuss with other editors while being bad enough to require LLM use. Iseulttalk to me01:26, 10 January 2025 (UTC)
No - anyone using a washing machine to wash their clothes must be evil and inherently lazy. They cannot be trusted. ... Oh, sorry, wrong century. Regards, --Goldsztajn (talk) 01:31, 10 January 2025 (UTC)
Edit quality in Android application
Several contributors, including myself, don't understand the point of the ‘edit quality’ mention in the Android application.
The mw:Wikimedia Apps/Android FAQ states that edit quality is ‘based on how many of your edits were reverted’. Is this the only criterion used? If so, calling it ‘edit quality’ is presumptuous, not to say irresponsible, given that there should be so many criteria. What are the different levels of judgement: excellent, good, bad, horrible, etc. ? What does this mean for developers, bots, patrollers and administrators? Whatever the case, the consequences of such a statement could be quite serious.
It's clear that the choice to keep this mention in the application doesn't just concern the application developers or even a small team, but all Misplaced Pages contributors, whatever their language. So we think it's important that you answer our questions. (As my English isn't very good, could you answer me in basic English, or at least without figures of speech? Thank you in advance.) Abalg (talk) 13:12, 7 January 2025 (UTC)
Hi Albag. I agree with the core of your message. But I don't get why you have been redirected to English Village Pump. This should be discussed somewhere on Meta or Mediawiki wiki, as it's relevant for all Misplaced Pages communities, not only the English one. (You and I are from fr-wp.) Best, — Jules*13:28, 7 January 2025 (UTC)
While I have no issue with the direction the linked discussion has taken, I agree with almost every contributor there: As a practice I have zero interest in generally allowing random editors closing outside their permissions. It might make DRV a more chatty board, granted. BusterD (talk) 15:02, 7 January 2025 (UTC)
Tamzin makes a reasonable case in their comment below. When we have already chosen to trust certain editors with advanced permissions, we might allow those folks to utilize them as fully as accepted practice allows. Those humans already have skin in the game. They are unlikely to act rashly. BusterD (talk) 19:32, 7 January 2025 (UTC)
To me, non-admin delete closes at any XfD have always seemed inconsistent with what we say about how adminship and discussion closing work. I would be in violation of admin policy if I deleted based on someone else's close without conducting a full review myself, in which case, what was the point of their close? It's entirely redundant to my own work. That said, I can't really articulate a reason that this should be allowed at some XfDs but not others, and it seems to have gone fine at CfD and TfD. I guess call me neutral. What I'd be more open to is allowing page movers to do this. Page movers do have the tools to turn a bluelink red, so it doesn't create the same admin accountability issue if I'm just cleaning up the stray page left over from a page mover's use of a tool that they were duly granted and subject to their own accountability rules for. We could let them move a redirect to some other plausible title (this would violate WP:MOVEREDIRECT as currently written but I think I'd be okay with making this a canonical exception), and/or allow moving to some draftspace or userspace page and tagging for G6, as we do with {{db-moved}}. I'll note that when I was a non-admin pagemover, I did close a few things as delete where some edge case applied that let me effect the deletion using only suppressredirect, and no one ever objected. -- Tamzin (they|xe|🤷) 19:07, 7 January 2025 (UTC)
I see that I was sort of vague, which is consistent with the statement that I hinted at allowing non-admin delete closures. My main concern is that I would like to see our guidelines and our practice made consistent, either by changing the guidelines or changing the practice. It appears that there is a rough consensus emerging that non-admin delete closures should continue to be disallowed in RFD, but that CFD may be a special case. So what I am saying is that if, in practice, we allow non-admin Delete closures at CFD, the guideline should say something vague to that effect.
I also see that there is a consensus that DRV can endorse irregular non-admin closures, including irregular non-admin Delete closures. Specifically, it isn't necessary for DRV to vacate the closure for an uninvolved admin to close. A consensus at DRV, some of whose editors will be uninvolved admins, is at least as good a close as a normal close by an uninvolved admin.
Also, maybe we need clearer guidance about non-admin Keep closures of AFDs. I think that if an editor is not sure whether they have sufficient experience to be closing AFDs as Keep, they don't have enough experience. I think that the guidance is clear enough in saying that administrator accountability applies to non-admin closes, but maybe it needs to be further strengthened, because at DRV we sometimes deal with non-admin closes where the closer doesn't respond to inquiries, or is rude in response to them.
Also, maybe we need clearer guidance about non-admin No Consensus closures of AFDs. In particular, a close of No Consensus is a contentious closure, and should either be left to an admin, or should be Relisted.
As for I can't really articulate a reason that this should be allowed at some XfDs, the argument is that more work is needed to enact closures at TfD and CfD (namely orphaning templates and emptying/moving/merging categories). Those extra steps aren't present at RfD. At most, there are times when it's appropriate to unlink the redirect or add WP:RCATs but those are automated steps that WP:XFDC handles. From my limited experience at TfD and CfD though, it does seem that the extra work needed at closure does not compensate for the extra work from needing two people reviewing the closure (especially at CfD because a bot that handles the clean-up). Consistency has come up and I would much rather consistently disallow non-admin delete closures at all XfD venues. I know it's tempting for non-admins to think they're helping by enacting these closures but it's not fair for them to be spinning their wheels. As for moving redirects, that's even messier than deleting them. There's a reason that WP:MOVEREDIRECT advises not to move redirects except for limited cases when preserving history is important. --Tavix20:16, 7 January 2025 (UTC)
@Tamzin: I do have one objection to this point of redundancy, which you are quite familiar with. Here, an AfD was closed as "transwiki and delete", however, the admin who did the closure does not have the technical ability to transwiki pages to the English Wikibooks, meaning that I, who does, had to determine that the outcome was actually to transwiki rather than blindly accepting a request at b:WB:RFI. Then, I had to mark the pages for G6 deletion, that way an admin, in this case you, could determine that the page was ready to be deleted. Does this mean that that admin who closed the discussion shouldn't have closed it, since they only have the technical ability to delete, not transwiki? Could I have closed it, having the technical ability to transwiki, but not delete? Either way, someone else would have had to review it. Or, should only people who have importing rights on the target wiki and admin rights on the English Misplaced Pages be allowed to close discussions as "transwiki and delete"? JJPMaster (she/they) 12:04, 8 January 2025 (UTC)
I do support being explicit when a non-administrator can close a discussion as "delete" and I think that explicitly extending to RfD and CfD is appropriate. First, there can be a backlog in both of these areas and there are often few comments in each discussion (and there is usually not the same passion as in an AfD). Second, the delete close of a non-administrator is reviewed by an administrator before action is taken to delete the link, or category (a delete close is a two-step process, the writeup and the delete action, so in theory the administrators workload is reduced). Third, non-admins do face administrator accountability for their actions, and can be subject to sanction. Fourth, the community has a role in reviewing closing decisions at DRV, so there is already a process in place to check a unexperienced editor or poor close. Finally, with many, if not most discussions for deletion the outcome is largely straight forward. --Enos733 (talk) 20:01, 7 January 2025 (UTC)
There is currently no rule against non-admin delete closures as far as I know; the issue is the practical one that you don't have the ability to delete. However, I have made non-admin delete closures at AfD. This occurred when an admin deleted the article under consideration (usually for COPYVIO) without closing the related AfD. The closures were not controversial and there was no DRV. Hawkeye7(discuss)20:31, 7 January 2025 (UTC)
The situation you're referring to is an exception allowed per WP:NACD: If an administrator has deleted a page (including by speedy deletion) but neglected to close the discussion, anyone with a registered account may close the discussion provided that the administrator's name and deletion summary are included in the closing rationale. --Tavix20:37, 7 January 2025 (UTC)
Bad idea to allow, this sort of closure is just busy work, that imposes more work on the admin that then has to review the arguments, close and then delete. Graeme Bartlett (talk) 22:05, 7 January 2025 (UTC)
(1) As I've also noted in the other discussion, the deletion process guidelines at WP:NACD do say non-admins shouldn't do "delete" closures and do recognize exceptions for CfD and TfD. There isn't a current inconsistency there between guidelines and practice. (2) In circumstances where we do allow for non-admin "delete" closures, I would hope that the implementing admin isn't fully reviewing the discussion de novo before implementing, but rather giving deference to any reasonable closure. That's how it goes with requested move closers asking for technical help implementing a "moved" closure at WP:RM/TR (as noted at WP:RMNAC, the closure will "generally be respected by the administrator (or page mover)" but can be reverted by an admin if "clearly improper"). SilverLocust💬08:41, 9 January 2025 (UTC)
Comment - A couple things to note about the CFD process: It very much requires work by admins. The non-admin notes info about the close at WT:CFD/Working, and then an admin enters the info on the CFD/Working page (which is protected) so that the bot can perform the various actions. Remember that altering a category is potentially more labour intensive than merely editing or deleting a single page - every page in that category must be edited, and then the category deleted. (There are other technical things involved, like the mess that template transclusion can cause, but let's keep it simple.) So I wouldn't suggest that that process is very useful as a precedent for anything here. It was done at a time when there was a bit of a backlog at CfD, and this was a solution some found to address that. Also - since then, I think at least one of the regular non-admin closers there is now an admin. So there is that as well. - jc3709:14, 9 January 2025 (UTC)
If the expectation is that an admin needs to review the deletion discussion to ensure they agree with that outcome before deleting via G6, as multiple people here are suggesting, then I'm not sure this is worthwhile. However, I have had many admins delete pages I've tagged with G6, and I have been assuming that they only check that the discussion was indeed closed as delete, and trust the closer to be responsible for the correctness of it. This approach makes sense to me, because if a non-admin is competent to close and be responsible for any other outcome of a discussion, I don't see any compelling reason they can't be responsible for a delete outcome and close accordingly. —Compassionate72719:51, 9 January 2025 (UTC)
Placement of dynamic list template
Where does the template {{dynamic list}} actually go? It superficially looks like it should be a hatnote at the top of the article, but there are a great number (perhaps a majority) of dynamic list articles where the template is placed under the infobox and lead. I can't find anything in the MOS specifically addressing this. Anonymous21:44, 7 January 2025 (UTC)
In many cases, the template is neither at the very top nor within a section. Just to be clear, this placement is not correct? Anonymous22:25, 7 January 2025 (UTC)
That talk page has been checked by at least 100 registered editors during the last month, which makes it one of our better watched pages. WhatamIdoing (talk) 18:22, 9 January 2025 (UTC)
Apparently. :) Getting no response in 36 hours was surprising. The silence could mean "no objection" (since I'm not proposing a change, just a clarification that already used to be there), but since it's a policy page, it would be good to have something more tangible. Gamapamani (talk) 08:20, 10 January 2025 (UTC)
Does my name technically violate the promotional username policy?
Comment: It would appear Jimbo responded indirectly in a interview: 
Sm8900 (talk) 17:46, 24 December 2024 (UTC)
Facepalm). Not gonna link what I can't (quickly) verify!)) (As an aside, I think "afflicted with" can come across as a bit... charged? Just something to note.)
Done 
Pope Francis and Brigette Lundy-Paine
.jpg)
