Anthropic: Fixed the issue causing Claude Code performance degradation and reset all subscribers' usage limits

robot
Abstract generation in progress

Odaily Planet Daily News reports that, according to official sources, the feedback regarding the decline in quality of Claude Code received by Anthropic was caused by three independent changes involving Claude Code, Claude Agent SDK, and Claude Cowork. Specific issues include: on March 4, the default inference strength was lowered from high to medium, resulting in a decrease in intelligence level, which was restored on April 7; a cache optimization feature launched on March 26 contained a bug that caused old inference records to be incorrectly cleared, leading to model forgetfulness and repetition, which was fixed on April 10; system prompt words added on April 16 to reduce redundancy damaged programming quality, and were revoked on April 20. Currently, all affected models have been restored to normal, and Anthropic has reset the usage quotas for all subscribers.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin