登録して招待リンクを共有すると、動画再生報酬と紹介報酬を獲得できます。

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.
参加 April 2020
496 フォロー中    22.6K ファン
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.
もっと見る