注册并分享邀请链接,可获得视频播放与邀请奖励。

Jeff Ma
@18jeffreyma
CS PhD @Harvard + researcher @Meta Created
加入 June 2013
1K 正在关注    1K 粉丝
super timely work, and a really great explanation for why models might feel "benchmaxxed"! SWE evals definitely feel extremely Markovian, which lends really well to compaction (since your codebase is essentially agent memory) real-world agent use is clearly multi-turn and partially-observable (uncovering requirements once you see your own spec assumptions challenged and overturned)
显示更多