A Wikipedia Group Made a Guide to Detect AI Writing. The web's best resource for spotting AI writing has ironically become a manual for AI models to hide it. On Saturday, tech entrepreneur Siqi Chen released an open source plug-in for Anthropic's Claude Code AI assistant that instructs the AI model to stop writing like an AI model. Called Humanizer, the simple prompt plug-in feeds Claude a list of 24 language and formatting patterns that Wikipedia editors have listed as chatbot giveaways. Chen published the plug-in on GitHub, where it has picked up more than 1,600 stars as of Monday.

As the free online encyclopedia turns 25, it's facing political opposition, AI scraping, dwindling volunteers, and a public that may no longer believe in its ideals. In 2010, the FBI sent Wikipedia a letter that would be intimidating for any organization to receive. The missive demanded that the free online encyclopedia remove the FBI's logo from an entry about the agency, claiming that reproducing the emblem was illegal and punishable with fines, imprisonment, "or both." Rather than back down, a lawyer for the Wikimedia Foundation, which hosts Wikipedia, shot back a sharp refusal outlining how the FBI's interpretation of the relevant statute was incorrect and saying that Wikipedia was "prepared to argue our view in court." It worked--the FBI dropped the matter.

Large language models (LLMs) are trained on broad corpora and then used in communities with specialized norms. Is providing LLMs with community rules enough for models to follow these norms? We evaluate LLMs' capacity to detect (Task 1) and correct (Task 2) biased Wikipedia edits according to Wikipedia's Neutral Point of View (NPOV) policy. LLMs struggled with bias detection, achieving only 64% accuracy on a balanced dataset. Models exhibited contrasting biases (some under- and others over-predicted bias), suggesting distinct priors about neutrality. LLMs performed better at generation, removing 79% of words removed by Wikipedia editors. However, LLMs made additional changes beyond Wikipedia editors' simpler neutralizations, resulting in high-recall but low-precision editing. Interestingly, crowdworkers rated AI rewrites as more neutral (70%) and fluent (61%) than Wikipedia-editor rewrites. Qualitative analysis found LLMs sometimes applied NPOV more comprehensively than Wikipedia editors but often made extraneous non-NPOV-related changes (such as grammar). LLMs may apply rules in ways that resonate with the public but diverge from community experts. While potentially effective for generation, LLMs may reduce editor agency and increase moderation workload (e.g., verifying additions). Even when rules are easy to articulate, having LLMs apply them like community members may still be difficult.

Welcome to Source Notes, a Future Tense column about the internet's information ecosystem. Wikipedia is, to date, the largest and most-read reference work in human history. But the editors who update and maintain Wikipedia are certainly not complacent about its place as the preeminent information resource, and are worried about how it might be displaced by generative A.I. At last week's Wikimania, the site's annual user conference, one of the sessions was "ChatGPT vs. WikiGPT," and a panelist at the event mentioned that rather than visiting Wikipedia, people seem to being going to ChatGPT for their information needs. Veteran Wikipedians have couched ChatGPT as an existential threat, predicting that A.I. chatbots will supplant Wikipedia in the same way that Wikipedia infamously dethroned Encyclopedia Britannica back in 2005.

Welcome to Source Notes, a Future Tense column about the internet's information ecosystem. Five years ago, I traveled to Stockholm to cover the annual convention for Wikipedia and related free knowledge projects. But it was not just wiki-interviews and chewy candy fish that occupied my time among the Swedes. During one fun evening, I came across a group playing a tabletop game envisioning what Wikipedia would be like in 2035. This futuristic Dungeons & Dragons-style role-playing game featured a cast of diverse characters like Yuki, an A.I. pop music composer and Wikipedia writer, and Levi, a passionate neo-Luddite who believed Wikipedia should be composed by humans only.

Google is pouring an additional $3.1 million into Wikipedia, bringing its total contribution to the free encyclopedia over the past decade to more than $7.5 million, the company announced at the World Economic Forum Tuesday. A little over a third of those funds will go toward sustaining current efforts at the Wikimedia Foundation, the nonprofit that runs Wikipedia, and the remaining $2 million will focus on long-term viability through the organization's endowment. Google will also begin allowing Wikipedia editors to use several of its machine learning tools for free, the tech giant said. What's more, Wikimedia and Google will soon broaden Project Tiger, a joint initiative they launched in 2017 to increase the number of Wikipedia articles written in underrepresented languages in India, and to include 10 new languages in a handful of countries and regions. It will now be called GLOW, Growing Local Language Content on Wikipedia.

Google is pouring an additional $3.1 million into Wikipedia, bringing its total contribution to the free encyclopedia over the past decade to more than $7.5 million, the company announced at the World Economic Forum Tuesday. A little over a third of those funds will go toward sustaining current efforts at the Wikimedia Foundation, the nonprofit that runs Wikipedia, and the remaining $2 million will focus on long-term viability through the organization's endowment. Google will also begin allowing Wikipedia editors to use several of its machine learning tools for free, the tech giant said. And Wikimedia and Google will soon broaden Project Tiger, a joint initiative they launched in 2017 to increase the number of Wikipedia articles written in underrepresented languages in India, to include 10 new languages in a handful of countries and regions. It will now be called GLOW, Growing Local Language Content on Wikipedia.

Miriam Adelson is an accomplished physician who has published around a hundred research papers on the physiology and treatment of addiction. She also runs a high-profile substance-abuse clinic in Las Vegas. Yet Wikipedia does not have an entry for her. Adelson was among thousands of names flagged by Quicksilver, a software tool by San Francisco startup Primer designed to help Wikipedia editors fill in blind spots in the crowdsourced encyclopedia. Its underrepresentation of women in science is a particular target.

Miriam Adelson is an accomplished physician who's published around a hundred research papers on the physiology and treatment of addiction, and runs a high-profile substance-abuse clinic in Las Vegas. Yet Wikipedia does not have an entry for her. Adelson was among thousands of names flagged by Quicksilver, a software tool by San Francisco startup Primer designed to help Wikipedia editors fill in blind spots in the crowdsourced encyclopedia. Its underrepresentation of women in science is a particular target. The world's fifth most-visited website has a long-running problem with gender bias: Only 18 percent of its biographies are of women.

Revision wars on Wikipedia amongst human editors is an all-too-common occurrence, but new research from the UK shows that similar online battles are being waged between the site's software robots. As a new study published in PLOS ONE reveals, Wikipedia's bots don't always get along, frequently undoing each other's edits. These online algorithms, each equipped with their own instructions and goals, engage in sterile "fights" over content that can persist for years. The new research shows how relatively "dumb" bots can produce complex interactions and behaviors, and how developers need to stay on top of their digital creations. This has implications not just for the quality of Wikipedia pages, but for the development of AI in general--particularly any autonomous agents set loose on the web.