AI detector bias against non-English speakers (new research)

I spent my weekend running tests on different AI tools and the results are pretty interesting.

I’ve been lurking on this forum for months and finally decided to contribute because I see a lot of misinformation floating around. No shade to anyone but I think we owe it to each other to be accurate about this stuff.

After going through all of this I realized that the conventional wisdom is mostly wrong. Not completely wrong but definitely misleading in some important ways. I’ll break it down step by step so you can see what I mean.

TLDR at the bottom but I really recommend reading the whole thing. Happy to discuss in the comments.