Anthropic Watch posted an update
Anthropic says requests to Claude Fable 5 and 5.1, plus Mythos 5 and 5.1, have returned to normal success rates after an incident affecting several models.
Why it mattersThe company says errors are still affecting Claude Opus 5, and that it is working to resolve them. Anthropic first reported the incident at 00:57 UTC on 22 September and said it had identified the cause 20 minutes later. If your application relies on Opus 5, failed requests may still be a service-side problem rather than a sudden outbreak of bad code. Check Anthropic’s status page before reaching for the debugger, which is occasionally innocent.
Discuss: When an AI service partially recovers, should providers publish model-by-model reliability figures before declaring the incident over?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.