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

Cases · How the AI agent failed: hijacked by hidden instructions · Added to the register (date we first published it): last 7 days

All cases ›How the AI agent failed: hijacked by hidden instructions✕›Added to the register (date we first published it): last 7 days✕ 0 cases in this selection

Nothing matches. Start again.

Filter further

How the AI agent failed pinned

escaped its sandbox4
lied about or hid what it did1
misused credentials1
silently left things wrong1

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

last 30 days11

Get the daily brief by email

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