@johnschulman2 : A research project related to sycophancy: define explicit features like "does the response agree with the user" as in arxiv.org/abs/23150.13548, and then construct a preference function that subtracts out their effect, as in arxiv.org/abs/2404.04475. I.e., remove some bad causal • TwiCopy

John Schulman

@johnschulman2

+ Follow

Recently started @thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music

ID: 1388977636618080256

linkhttp://joschu.net calendar_today02-05-2021 22:05:23

113 Tweet

61,61K Takipçi

922 Takip Edilen

John Schulman

@johnschulman2

4 months ago

A research project related to sycophancy: define explicit features like "does the response agree with the user" as in arxiv.org/abs/2310.13548, and then construct a preference function that subtracts out their effect, as in arxiv.org/abs/2404.04475. I.e., remove some bad causal

thumb_up_off_alt272

chat_bubble_outline6

repeat19

shareShare