I have a lot of problems with Opus 5 in the last days. So, maybe the problem is to expect reliability from something probabilistic?
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
Might be a bit more than just noise: https://marginlab.ai/trackers/claude-code-historical-perform...
Edit: well, crap.
Thanks, Anthropic.