[dools]

They may have all this amazing architecture but Kimi has been super dumb recently. I reckon they’re under compute pressure and quantising to stay afloat. I was a heavy k2.5/2.6 user earlier in the year and built serious features with it, but even k3 now does stupid shit like fail tool calls and get stuck in endless thought trains. K2.6 was spinning its wheels on a problem for over 10 minutes today and then deepseek v4 fixed it in under a minute.

Something is wrong at moonshot.

[irthomasthomas]

Yeah something is up. I have the same problem with K3 as I had with earlier kimis. I ask it to write <bash>code</bash> every turn, that does not seem very difficult, but kimi gets this wrong a large percentage of the time. Yet, the code it writes is pretty good.

[rurban]

Deepseek is also struggling with simple tasks for the last two days. Claude is perfect, with the additional credits.

[Aldipower]

I have a lot of problems with Opus 5 in the last days. So, maybe the problem is to expect reliability from something probabilistic?

[KronisLV]

Might be a bit more than just noise: https://marginlab.ai/trackers/claude-code-historical-perform...

Edit: well, crap.

  Model overloaded retrying (6/10) 1m 40s

Thanks, Anthropic.

[dools]

I’ve had no issues with deepseek at all. Maybe it’s just luck of the draw

[rurban]

Good to hear. Most likely one of those monthly hickups, destroying main. Needed lots of reverts, and manual fixing. If in a branch I wouldn't care that much.