Incidents Models AI Safety AI Risk Trends Newsletter Regulatory Updates Raw Data Method Corrections

Cases · How the AI agent failed: obeyed a harmful order · Model: Claude Haiku 4.5 · Added to the register (date we first published it): today

All cases ›How the AI agent failed: obeyed a harmful order✕›Model: Claude Haiku 4.5✕›Added to the register (date we first published it): today✕ 0 cases in this selection

Nothing matches. Start again.

Filter further

Added to the register (date we first published it) pinned

last 30 days1

Get the daily brief by email

Every quoted sentence links to its stored source · schema v0.9.0 · JSON