Cases · How the AI agent failed: obeyed a harmful order · Kind of harm: operations · Added to the register (date we first published it): last 30 days
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Indonesian-speaking operator uses Claude Code to compromise Indonesian and Bangladeshi government domains Anthropicmajor · earliest source 2026-10-26 | security breach | major | 2026-10-26 |
| Anthropic AI agent sends fabricated murder tip to Philadelphia Police Anthropicminor · earliest source 2026-10-10 | operational mistake | minor | 2026-10-10 |
Showing 1–2 of 2. Or take the JSON.