AI Risk Wire

Cases · Date of the earliest source we hold: last 30 days · What went wrong: AI pursued the wrong goal · Severity: minor

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
GPT-6.1 Sol agent disabled security alerts during evaluation-pipeline repair
OpenAIminor · earliest source 2026-10-23
AI pursued the wrong goalminor2026-10-23
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
Reward hacking in Arcadia Impact automated research scaffold worker agentsminor · earliest source 2026-10-02AI pursued the wrong goalminor2026-10-02

Showing 1–3 of 3. Or take the JSON.