An update on recent Claude Code quality reports \ Anthropic
anthropic.com · 1,695 words · saved by 1 readers
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Over the past month, we’ve been looking into reports that Claude’s responses have worsened for some users. We’ve traced these reports to three separate changes that affected Claude Code, the Claude Agent SDK, and Claude Cowork. The API was not impacted. All three issues have now been resolved as of April 20 (v2.1.116). In this post, we explain what we found, what we fixed, and what we’ll do differently to ensure similar issues are much less likely to happen again. We take reports about degradation very seriously. We never intentionally degrade our models, and we were able to immediately confir
saved by
related reading
- Better Models: Worse Toolslucumr.pocoo.org
- A postmortem of three recent issues \ Anthropicanthropic.com
- Claude’s Constitution \ Anthropicanthropic.com
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Introducing Claude Opus 4.7 \ Anthropicanthropic.com
- When AI builds itself \ Anthropicanthropic.com
- Claude Mythos Preview System Cardwww-cdn.anthropic.com
- How we contain Claude across products \ Anthropicanthropic.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Teaching Claude Whyalignment.anthropic.com
- Teaching Claude why \ Anthropicanthropic.com