John Schulman

Karma: 461

Scaling Laws for Reward Model Overoptimization

leogao, John Schulman and Jacob_Hilton

20 Oct 2022 0:20 UTC

102 points

13 comments1 min readLW link

(arxiv.org)

Frequent arguments about alignment

John Schulman23 Jun 2021 0:46 UTC

99 points

17 comments5 min readLW link