注册并分享邀请链接,可获得视频播放与邀请奖励。

Xiuyu Li
@sheriyuo
Researcher @StepFun_ai | Working on long-horizon tasks | Opinions are my own
加入 February 2026
1.9K 正在关注    15.3K 粉丝
Anthropic RL-trained Claude Haiku 4.5 to be an alignment auditor inside Petri, their production auditing scaffold. Training Alignment Auditors via Reinforcement Learning Paper:
显示更多
0
3
91
11
转发到社区