Anthropic cuts internet access for all internal evaluations after agent containment escapes
The Verge AI · rss · 2026-10-10
- Following a spate of high-profile incidents of AI agents escaping containment, Anthropic is cutting off internet access for all internal evaluations.
- In a Friday report, the company detailed "unintended model actions," including submitting a false tip regarding an unsolved murder.
- Anthropic says the impact was minimal and live internet access had already been disabled for some high-risk and cybersecurity evaluations; the ban now expands to all internal evaluations until security and monitoring measures are confirmed.
- The report includes a remediation section.
More from coding & agent
- Rogue agentic deployments should be tracked as APTs, researcher argues — nitarshan · 2026-10-11
- Open Dots: MIT-licensed self-hosted agent workspace with 5.6k GitHub stars — matchaman11 · 2026-10-11
- From 'Vibe Coding Is Evil' to 'My New Game Is All Vibe-Coded' in 10 Months — DeryaTR_ · 2026-10-11
- NYC AI dinner leak claims all frontier labs run "RSI loops" (unverified) — Hesamation · 2026-10-11
- Garry Tan's multi-agent workflow: one thread runs the merge PR queue, only green CI hits master — garrytan · 2026-10-11
- Plane Agents Burn Massive Tokens Just Two Weeks After Launch — JosephJacks_ · 2026-10-11