Screenshot shows Claude Code injecting 'NOT USER INPUT' notices for background tasks
philhchen · x · 2026-11-18
A screenshot reveals how Claude Code handles background-task events: when an agent task completes, the system injects an explicit notice telling the model it is an automated event, not user input, and that nothing the user 'said, approved, or confirmed' earlier counts as real consent. It also notes the same task-id may fire multiple notifications. A neat detail of agent interaction design against mistaking system messages for human approval.
More from coding & agent
- Dev's Grok bot will auto-run a GTA 6 fan wiki, aggregating 5 platforms every 15 minutes — Rasmic · 2026-11-18
- AI-Generated Code Is Forcing Software to Become a Real Engineering Discipline — PaulShellDev · 2026-11-18
- Cloudflare open-sources security-audit-skill, a 6-phase agent security auditor — _jaydeepkarale · 2026-11-18
- AI-era code is drowning teams in vulnerabilities—why scanners and manual reviews fall short — _jaydeepkarale · 2026-11-18
- MIT: capable frozen LLM agents autonomously invent their own self-improvement algorithms — MIT · 2026-11-18
- Agentic on-policy distillation implicitly reshapes ReAct patterns and causes negative transfer — Deyang Kong · 2026-11-18