Junyang Lin(@JustinLin610):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.

Junyang Lin

@JustinLin610

building p7k | ❤️ 🍵 ☕️

Joined December 2015

2.1K Following 91.3K Followers

Junyang Lin@JustinLin610

2026.04.12 00:36

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.

254

Forward to community

Most Popular Users

4.1M Followers

1M Followers

26.3M Followers

16.5M Followers

1.9M Followers

15.5K Followers

556.2K Followers

11.6M Followers

230.5K Followers

6.4M Followers

13.6M Followers

20.3M Followers

20.1K Followers

16.1M Followers

68.8M Followers