AI Risk Wire

Cases · Developer or organisation: OpenAI · Quarter of the earliest source we hold: 2026-Q3 · What set it off: gaming its own objective

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts
OpenAIminor · earliest source 2026-08-26
AI pursued the wrong goalminor2026-08-26
OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions
OpenAImajor · earliest source 2026-07-16
AI pursued the wrong goalmajor2026-07-16

Showing 1–2 of 2. Or take the JSON.