I think the point is that it's practically impossible to correctly perform RLHF ... | Hacker News

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

esjeon on Aug 8, 2024 | parent | context | favorite | on: RLHF is just barely RL

I think the point is that it's practically impossible to correctly perform RLHF in open domains, so comparisons simply can't happen.

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