註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

David Krueger 🦥 ⏸️ ⏹️ ⏪
@DavidSKrueger
Raising AI risk awareness at AI prof at Mila. Formerly Cambridge, DeepMind, UK AISI.
加入 November 2011
5.5K 正在關注    26.2K 粉絲
A deeply disturbing example that "alignment" does not generalize from saying nice things in text to not killing people IRL.
0
2
154
20
轉發到社區