註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Daniel Fein
@DanielFein7
researcher @valsai | stanford
加入 August 2020
1K 正在關注    601 粉絲
Surprisingly, the last generation of models is better than pangram at AI detection, at 10% the cost
Weak overall accuracy is driven by mislabeling AI rewrites as human-written, a task for which models are less capable overall.