On Saturday, tech entrepreneur Siqi Chen released an open supply plug-in for Anthropic’s Claude Code AI assistant that instructs the AI mannequin to cease writing like an AI mannequin.
Referred to as Humanizer, the easy immediate plug-in feeds Claude a listing of 24 language and formatting patterns that Wikipedia editors have listed as chatbot giveaways. Chen revealed the plug-in on GitHub, the place it has picked up greater than 1,600 stars as of Monday.
“It’s actually useful that Wikipedia went and collated an in depth listing of ‘indicators of AI writing,’” Chen wrote on X. “A lot to be able to simply inform your LLM to … not do this.”
The supply materials is a information from WikiProject AI Cleanup, a gaggle of Wikipedia editors who’ve been searching AI-generated articles since late 2023. French Wikipedia editor Ilyas Lebleu based the undertaking. The volunteers have tagged over 500 articles for evaluate and, in August 2025, published a proper listing of the patterns they saved seeing.
Chen’s device is a “skill file” for Claude Code, Anthropic’s terminal-based coding assistant, which includes a Markdown-formatted file that provides a listing of written directions (you may see them here) appended to the immediate fed into the giant language mannequin that powers the assistant. In contrast to a traditional system prompt, for instance, the ability information is formatted in a standardized method that Claude fashions are fine-tuned to interpret with extra precision than a plain system immediate. (Customized abilities require a paid Claude subscription with code execution turned on.)
However as with all AI prompts, language fashions don’t all the time completely comply with ability recordsdata, so does the Humanizer really work? In our restricted testing, Chen’s ability file made the AI agent’s output sound much less exact and extra informal, nevertheless it might have some drawbacks: It received’t enhance factuality and would possibly hurt coding capacity.
Specifically, a few of Humanizer’s directions would possibly lead you astray, relying on the job. For instance, the Humanizer ability consists of this line: “Have opinions. Don’t simply report info—react to them. ‘I genuinely don’t know the way to really feel about this’ is extra human than neutrally itemizing execs and cons.” Whereas being imperfect appears human, this sort of recommendation would most likely not do you any favors in the event you had been utilizing Claude to write technical documentation.
Even with its drawbacks, it’s ironic that considered one of the net’s most referenced rule units for detecting AI-assisted writing might assist some individuals subvert it.
Recognizing the Patterns
So what does AI writing appear to be? The Wikipedia information is particular with many examples, however we’ll offer you only one right here for brevity’s sake.
Some chatbots love to pump up their topics with phrases like “marking a pivotal second” or “stands as a testomony to,” in accordance to the information. They write like tourism brochures, calling views “breathtaking” and describing cities as “nestled inside” scenic areas. They tack “-ing” phrases onto the finish of sentences to sound analytical: “symbolizing the area’s dedication to innovation.”
To work round these guidelines, the Humanizer ability tells Claude to change inflated language with plain info and provides this instance transformation:
Earlier than: “The Statistical Institute of Catalonia was formally established in 1989, marking a pivotal second in the evolution of regional statistics in Spain.”
After: “The Statistical Institute of Catalonia was established in 1989 to acquire and publish regional statistics.”
Claude will learn that and do its greatest as a pattern-matching machine to create an output that matches the context of the dialog or job at hand.
Why AI Writing Detection Fails
Even with such a assured algorithm crafted by Wikipedia editors, we’ve previously written about why AI writing detectors don’t work reliably: There is nothing inherently distinctive about human writing that reliably differentiates it from LLM writing.
One motive is that despite the fact that most AI language fashions have a tendency towards sure forms of language, they may also be prompted to keep away from them, as with the Humanizer ability. (Though generally it’s very troublesome, as OpenAI present in its yearslong struggle in opposition to the em sprint.)
Disclaimer: This article is sourced from external platforms. OverBeta has not independently verified the information. Readers are advised to verify details before relying on them.
