Junyang Lin
@JustinLin610
building p7k | ❤️ 🍵 ☕️
加入 December 2015
2.1K 正在关注 91.3K 粉丝
we need agent evals that are really consistent with real world usages. otherwise people are optimizing foundation models for the wrong direction. the problem of targeting is even bigger than benchmaxxing.
显示更多
