[dead]
Wikipedia: WikiProject AI Cleanup
61–70 of 99 posts
Re: Wikipedia: WikiProject AI Cleanup
#62It is really good that they are taking steps to remove this stuff. You can usually tell right away when something was not written by a human.
Re: Wikipedia: WikiProject AI Cleanup
#63I wish they also spent on the reverse: automatic rephrasing of the (many) obscure and very poorly worded and/or with no neutral tone whatsoever. And I say that as a general Wikipedia fan.
I would hate it so much if all the articles on Wikipedia were suddenly all rewritten to have a smiliar tone and style. Its beauty is its diversity.
Re: Wikipedia: WikiProject AI Cleanup
#64Isn't having a source the only thing that should be required. Why is AI speak bad? I'm a embarrassed to be associated with US Millennials who are anti AI. No one cares if you tie your legs together and finish a marathon in 12 hours. Just finish it in 3. Its more impressive. EDIT: I suppose people missed the first sentence: >Isn't having a source the only thing that should be required. >Isn't having a source the only…
>Isn't having a source the only thing that should be required.
No, referencing and discussing it properly whilst retaining the tone and inferred meaning are equally as important. I can cite anything as a source that I want, but if I use it incorrectly or my analysis misses the point of the source then the reference source itself is pointless.
Re: Wikipedia: WikiProject AI Cleanup
#65Earlier quoted context omitted.
This is very good, but I'm surprised the term "game-changer" is not mentioned there. From my observations this is used a lot in LLM texts.
Great point! That would be a game-changer!
"This is the smoking gun!"
_sigh_ Is it though, Claude, is it really?
Re: Wikipedia: WikiProject AI Cleanup
#66> Unfortunately, these models virtually always fail to properly source claims and often introduce errors.
A quote for the times.
May be a bit of a sisyphean task, though...
Re: Wikipedia: WikiProject AI Cleanup
#67The Sanderson wiki [1] has a time-travel feature where you read a snapshot just before a publication of a book, ensuring no spoilers. I would like a similar pre-LLM Wikipedia snapshot. Sometimes I would prefer potentially stale or incomplete info rather than have to wade through slop. 1: https://coppermind.net/wiki/Coppermind:Welcome
The easiest way to get this is probably Kiwix. You can download a ~100GB file containing all of English Wikipedia as of a particular date, then browse it locally offline. I'm not sure if it's real or not, but the Internet Archive has a listing claiming to be the dump from May 2022: https://archive.org/details/wikipedia_en_all_maxi_2022-05
There's a torrent at the linked URL. Trying that right now. (I have a couple of Kiwix dumps of Wikipedia offline already.)
Re: Wikipedia: WikiProject AI Cleanup
#68Earlier quoted context omitted.
That’s super interesting. I had a similar idea about 18 months ago. I think the biggest opportunity is building a knowledge graph based on Wikipedia and then checking against the graph when new edits are made . Detect any new assertions in the edit, check for conflicts against the graph, and bring up a warning along with a link to all the pages on Wikipedia that the new edit is contradicting. If the new edit is bad,…
Hopefully you know of Abstract Wikipedia? https://en.wikipedia.org/wiki/Abstract_Wikipedia Sounds pretty relevant
I didn’t know about that, thank you!
Re: Wikipedia: WikiProject AI Cleanup
#69There was a paper recently about using LLMs to find contradictions in Wikipedia, i.e. claims on the same page or between pages which appear to be mutually incompatible. https://arxiv.org/abs/2509.23233 I wonder if something more came out of that. Either way, I think that generation of article text is the least useful and interesting way to use AI on Wikipedia. It's much better to do things like this paper did.
You can easily do this with normal GPT 5.2 in ChatGPT, just turn on thinking (better if extended) and web search, point a Wikipedia page to the model and tell it to check the claims for errors. I've tried it before and surprisingly it finds errors very often, sometimes small, sometimes medium. The less popular the page you linked is, the more likely it'll have errors. This works because GPT 5.x actually properly use…
I am sure that could be useful with proper post-request research.
As a technique though, never ask an LLM to find errors. Ask it to either find errors or verify that there are no errors. That way it can answer without hallucinating more easily.
Re: Wikipedia: WikiProject AI Cleanup
#70Earlier quoted context omitted.
You can easily do this with normal GPT 5.2 in ChatGPT, just turn on thinking (better if extended) and web search, point a Wikipedia page to the model and tell it to check the claims for errors. I've tried it before and surprisingly it finds errors very often, sometimes small, sometimes medium. The less popular the page you linked is, the more likely it'll have errors. This works because GPT 5.x actually properly use…
I am sure that could be useful with proper post-request research. As a technique though, never ask an LLM to find errors. Ask it to either find errors or verify that there are no errors. That way it can answer without hallucinating more easily.
> As a technique though, never ask an LLM to find errors.
What I do is both ask it to explain why there are no errors at all and why there tons of errors. Then I use my natural intelligence to reason about the different claims.