An update on recent Claude Code quality reports
infonewsLLM-Specific
safety
Source: Simon Willison's WeblogApril 23, 2026
Summary
Claude Code, an AI coding tool, experienced quality issues over two months caused by three bugs in its underlying system (the software framework that runs the AI), not the AI models themselves. One major bug caused the system to repeatedly clear Claude's memory from idle sessions every turn instead of just once, making it seem forgetful and repetitive.
Classification
Attack SophisticationModerate
Impact (CIA+S)
availability
AI Component TargetedInference
Affected Vendors
Anthropic
Related Issues
Monthly digest — independent AI security research
Original source: https://simonwillison.net/2026/Apr/24/recent-claude-code-quality-reports/#atom-everything
First tracked: April 24, 2026 at 02:00 AM
Classified by LLM (prompt v3) · confidence: 85%