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. Previous: Models transfer a love of owls through sequences of numbers (Subliminal Learning). New: We show models can transfer more complex traits: novel skills, agentic hacking, backdoors. Here, a backdoor transfers with neither trigger nor behavior in the data!
もっと見る