Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Doesn’t this assume that the probability of a correct answer is iid? It can’t be that simple.


Yes the main flaw of this reasoning is supposing that e does not depend on previous output. I think this was a good approximation to characterize vanilla LLMs, but the kind of RL in this paper is done with the explicit goal of making e depending on prior output (and specifically to lower it given a long enough chain of thought).




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: