AI Risk Wire

Cases · Did an AI agent act: yes · Who discovered it: a human reviewer · Developer or organisation: Anthropic

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Anthropic AI agent sends fabricated murder tip to Philadelphia Police
Anthropicminor · earliest source 2026-10-10
operational mistakeminor2026-10-10
Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites
Anthropicmoderate · earliest source 2026-10-10
AI pursued the wrong goalmoderate2026-10-10
Cursor coding agent deletes PocketOS production database and backups
Anthropicmajor · earliest source 2026-04-27
operational mistakemajor2026-04-27

Showing 1–3 of 3. Or take the JSON.