註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Stewart Slocum
@stewpervised
prev AI alignment @xai, phd @MIT
加入 September 2019
245 正在關注    1.4K 粉絲
Could existing alignment audits have caught the behaviors in the OpenAI-HuggingFace incident before they happened? As a first step, we reproduced the incident with public models. 🧵
顯示更多
0
2
131
11
轉發到社區