MiMo Code: Scaling coding agents to long-horizon tasks

Interesting. I've been using their models quite a bit, through Claude Code, might try switching to this.

I also built a couple of harnesses, I wonder if I could swap this for Claude in those...

(Lots of interesting ideas in the blog post, but like all the AI developments these days, hard to be sure what's valuable without extensive experimentation.)

Would love to see some comparisons with vanilla opencode (which this builds upon)