[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.