In math specifically, one could easily imagine a reward signal from some automat... | Hacker News

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

		jhrmnn on Nov 23, 2023 \| parent \| context \| favorite \| on: OpenAI researchers warned board of AI breakthrough... In math specifically, one could easily imagine a reward signal from some automated theorem proving engine

cubefox on Nov 25, 2023 [–]

Yeah. I went into some detail of how it might work here: https://news.ycombinator.com/item?id=38036986

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