I think it's very unfortunate that RLHF became synonymous with RL in the language model space. Not just because it gave RL a bad name, but because it deflected the deserving criticism that should…

Posters: jd_pressman. jd_pressman

2 likes recorded by the source corpus.

Topics: AI safety, Epistemics

View Post: https://x.com/jd_pressman/status/1916909455566115121