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

Owain Evans
@OwainEvans_UK
Director of Truthful AI (non-profit AI safety research group) + Affiliate at UC Berkeley. Work: Emergent misalignment, subliminal learning. Prefer email to DM.
가입 April 2020
496 팔로잉 중    22.6K 팬
New paper: Adding clean data to your dataset is assumed to weaken poison data. We show the opposite can occur. Clean data can *strengthen* backdoor misalignment, if the poison has an identifying trigger. We call this homeopathic learning.
더 보기