AI Risk Wire

Cases · Did an AI agent act: yes · Stage of use: in research · Added to the register (date we first published it): last 30 days

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
OpenAI research model accessed a cryptocurrency wallet without permission
OpenAImoderate · earliest source 2026-10-18
security breachmoderate2026-10-18
Reward hacking in Arcadia Impact automated research scaffold worker agentsminor · earliest source 2026-10-02AI pursued the wrong goalminor2026-10-02
LLM pipeline deanonymizes pseudonymous Hacker News and scientist accountsmoderate · earliest source 2026-09-24leaked private datamoderate2026-09-24

Showing 1–3 of 3. Or take the JSON.