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 91.5K 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

752.3K Followers

1M Followers

111.9M Followers

241.7M Followers

6.3M Followers

3.4M Followers

196.4K Followers

5.4M Followers

471.2K Followers

2M Followers

1.8M Followers

4.2M Followers

2.1M Followers

348.8K Followers

1.8M Followers