註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Anca Dragan
@ancadianadragan
Google DeepMind • AI safety & alignment • model behavior • associate professor @ UC Berkeley EECS
加入 March 2018
185 正在關注    14.1K 粉絲
The idea that Chain of Thought is inevitably going to go away misses that we have agency in designing these models and can do something about that. @rohinmshah and I make the case that we should intentionally preserve monitorability (as part for of the launch of the DeepMind Institute) here:
顯示更多
0
48
466
77
轉發到社區