注册并分享邀请链接,可获得视频播放与邀请奖励。

Joachim Schaeffer
@JSchaeff3r
AI Safety Researcher working on AI Control and Security
加入 November 2021
203 正在关注    769 粉丝
Kimi K3.1 recalls instructions it was never given on Terminal Bench. They match the hidden tests. K3.1 while solving: "Instructions likely distilled pitfalls from previous agents." 🤯 When we edit a task to contradict them, K3.1 refuses the new instructions and fails. Other models follow the edit. Is it terminal(ly) benchmaxxed? 🧵
显示更多
0
14
315
28
转发到社区