Anthropic resolves three issues affecting Claude Code, Agent SDK, and Cowork quality
By
mfiguiere
Sesame, salt, and substance. A flagship bake.
Summary
Anthropic investigated reports of degraded Claude responses over the past month, tracing the issues to three separate changes affecting Claude Code, the Claude Agent SDK, and Claude Cowork (the API was not impacted). All three issues were resolved as of April 20 (v2.1.116). The company explains what was found, what was fixed, and outlines procedural changes to prevent similar issues in the future, emphasizing their commitment to not intentionally degrading models and taking quality reports seriously.
Key quotes
· 3 pulledWe take reports about degradation very seriously.
We never intentionally degrade our models, and we were able to immediately confirm t
All three issues have now been resolved as of April 20 (v2.1.116).
You might also wanna read
Anthropic's Claude AI Models Experience Major Outage, Disrupting Claude Code Service
Anthropic's Claude AI models experienced a major outage affecting Claude Code and other products, with developers encountering 500 errors. T
The Verge·3mo agoAnthropic Updates Claude Code With Security Plugin and Faster Performance
Anthropic Launches Claude Cowork AI Agent Feature in Research Preview
Anthropic has launched a new AI feature called "Claude Cowork" in research preview, expanding Claude's AI agent capabilities beyond coding t
The Verge·4mo ago
Anthropic Releases Updated "Claude's Constitution" Detailing AI Model's Ethical Framework
Anthropic has released a new 57-page "Claude's Constitution" document that outlines the ethical framework and core values for its AI model C
The Verge·4mo ago
Anthropic's Claude Code Platform Gains Widespread Popularity Among Developers
The article discusses the recent surge in popularity of Anthropic's Claude AI, particularly its Claude Code platform, which has gained signi
The Verge·3mo ago
How Anthropic contains Claude's expanding access across its products
Anthropic describes how it has evolved its approach to granting Claude, its AI assistant, increasingly broad access to internal systems over
anthropic.com·10h ago