Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

It's a decent model but works best with kimi CLI, not CC or others.




I haven't use Kimi CLI, but it works very well with OpenCode.

Why do you think that is?

I heard it's because the labs fine tune their models for their own harness. Same reason why claude does better in claude code than cursor.

read the tech report



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: