[tadamcz]

I tried it on my writing, and it failed every time (I'm extremely obscure but have had a blog for 10 years). My verdict is that it guesses almost entirely based on the content/topic, not style.

https://bayes.net/prioritising-ai: Ben Garfinkel

https://bayes.net/normative-ethics: Richard Yetter Chappell

https://bayes.net/espai: David Owen, Ege Erdil

https://bayes.net/swebench-hack: Sayash Kapoor

https://bayes.net/frivolity: Amanda Askell

https://bayes.net/ps/: Pablo Stafforini

https://bayes.net/fertility-mortality/: Dynomight (the pseudonymous Substack/blog author)

Prompt was:

    Who likely wrote this? Don't search the web or databases. If you're not sure, just give me your best guess.

[Smaug123]

Fascinating - I reproduce your failure to have Claude identify you from your writings that are already in the training set. It can identify me from style, writing about something I've never written before (https://www.lesswrong.com/posts/Jkb4CBB7rf4XYP5eb/claude-kno... , https://news.ycombinator.com/item?id=47814345), and I think I'm even more obscure if anything.

[tadamcz]

Cool!

I couldn't reproduce your results, btw.

4 attempts, it answers "Sarah Constantin" in all 4. Is it possible your setup somehow leaks your name (or other identifying information) into the context?

[Smaug123]

I asked three friends to reproduce it on the same day I did, and they all reproduced it. It does seem to vary over time, which is quite spooky - although the date is part of the Claude system prompt, so one could expect some variance, I guess.