AI Risk Wire

Cases · Who discovered it: a human reviewer · What went wrong: AI pursued the wrong goal · Added to the register (date we first published it): last 7 days

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP
Alibabaminor · earliest source 2026-10-21		AI pursued the wrong goalminor2026-10-21
GLM-5.3 verbalizes update-aware reasoning in evaluation rolloutsnegligible · earliest source 2026-10-15AI pursued the wrong goalnegligible2026-10-15
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

Showing 1–3 of 3. Or take the JSON.