注册并分享邀请链接,可获得视频播放与邀请奖励。

Daniel Fein
@DanielFein7
researcher @valsai | stanford
加入 August 2020
1K 正在关注    601 粉丝
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.