Re: ambiguous results—I somewhat agree. I try to highlight repeatedly that the logit shifts I observe are not statistically significant, but they also do generally ‘beat’ every control here, so the detection effect seems non-trivial.
Re: AI—although I used Claude code extensively to implement this project (and checked all generated code manually), I wrote the whole post by hand. I only used AI for a final pass on minor latex equation fixes and grammar errors. When I paste it into AI-checkers now, I get either low percentages or ‘mixed’ - perhaps this is a result of chatting with LLMs when scoping out the experiment? (If the objectionable part is that some ideas / sentences are undeveloped / shallow, I’d love feedback on that, though!)
I think your post looks LLM written because extensively bolding words mid sentence is much more common in LLM writing. But spot reading a few sentences I do think it looks human written, though it does feel like a lot of the terminology is chosen by an LLM.
That makes sense. I think the way I bolded was somewhat unlike typical LLM formatting, since I tended to bold entire sentences when I thought they were important, in addition to highlighting individual key concepts. This is also consistent with my other post on LW (which was not flagged).
Re: ambiguous results—I somewhat agree. I try to highlight repeatedly that the logit shifts I observe are not statistically significant, but they also do generally ‘beat’ every control here, so the detection effect seems non-trivial.
Re: AI—although I used Claude code extensively to implement this project (and checked all generated code manually), I wrote the whole post by hand. I only used AI for a final pass on minor latex equation fixes and grammar errors. When I paste it into AI-checkers now, I get either low percentages or ‘mixed’ - perhaps this is a result of chatting with LLMs when scoping out the experiment? (If the objectionable part is that some ideas / sentences are undeveloped / shallow, I’d love feedback on that, though!)
I think your post looks LLM written because extensively bolding words mid sentence is much more common in LLM writing. But spot reading a few sentences I do think it looks human written, though it does feel like a lot of the terminology is chosen by an LLM.
That makes sense. I think the way I bolded was somewhat unlike typical LLM formatting, since I tended to bold entire sentences when I thought they were important, in addition to highlighting individual key concepts. This is also consistent with my other post on LW (which was not flagged).