가입 후 초대 링크를 공유하면 동영상 재생 및 초대 보상을 받을 수 있습니다.

Ezra Newman
@EzraJNewman
Member of Technical Staff at @ApolloResearch. Philosopher. Effective altruist. Likes != endorsement; epistemic status: twitter
가입 September 2020
434 팔로잉 중    1.4K 팬
Claude summarizes/describes behavior as significantly less misaligned when the actor is Claude vs another model In one experiment, Sonnet 5 describes the exact same data as ~1.2 std deviations less concerning when it describes misbehavior committed by Sonnet 5 vs GPT-5.6
더 보기