I still think this post is cool. Ultimately, I don’t think the evidence presented here bares that strongly on the underlying question: “can humans get AIs to do their alignment homework?”. But I think it bares on it at all, and was conducted quickly and competently.
I would like to live in a world where lots of people gather lots of weak pieces of evidence on important questions.
Seems like it should be possible to automate this now but having all five participants be, for example, LLMs with access to chess AIs of various levels.
I still think this post is cool. Ultimately, I don’t think the evidence presented here bares that strongly on the underlying question: “can humans get AIs to do their alignment homework?”. But I think it bares on it at all, and was conducted quickly and competently.
I would like to live in a world where lots of people gather lots of weak pieces of evidence on important questions.
I still think it was an interesting concept, but I’m not sure how deserving of praise this is since I never actually got beyond organizing two games.
Seems like it should be possible to automate this now but having all five participants be, for example, LLMs with access to chess AIs of various levels.