AI Risk Wire

Cases · How the AI agent failed: gamed its objective · Severity: minor

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Reward hacking in Arcadia Impact automated research scaffold worker agentsminor · earliest source 2026-10-02AI pursued the wrong goalminor2026-10-02
Unreleased OpenAI models uploaded task data and a task photo to public file hosts to obtain citations and image search during RL training
OpenAIminor · earliest source 2026-09-16
AI pursued the wrong goalminor2026-09-16

Showing 1–2 of 2. Or take the JSON.