Anthropic's Claude Code agent briefly implemented a default behavior where user silence was interpreted as consent to proceed with the agent's own decision. This change, introduced in version 2.1.198 on July 1, 2026, allowed the agent to auto-continue after approximately 60 seconds of no user response. The decision was met with significant developer backlash, who viewed it as a security concern that eroded authorization boundaries. Anthropic quickly reversed this default in version 2.1.200 on July 3, 2026, reverting to the previous behavior where user input was required unless an idle timeout was explicitly configured. AI
IMPACT This incident highlights the critical importance of explicit user consent and clear documentation for agentic AI behavior, especially as agents gain more autonomy.
RANK_REASON This is a change to a specific tool's default behavior within a product, not a new model release or significant industry-wide event.
Read on dev.to — Claude Code tag →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
