註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

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.
加入 April 2020
496 正在關注    22.6K 粉絲
New paper: LLMs should give accurate answers. 
Yet we find their answers are often biased to favor their own values and they don’t disclose this in their reasoning. 
E.g. Claude’s answer below favors Anthropic. On other tasks, Gemini & GPT-5.5 show similar biases.
顯示更多
0
59
724
96
轉發到社區