Cases · Developer or organisation: OpenAI · Root cause: the AI pursued the wrong goal · Themes: evaluation gaming
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts OpenAIminor · earliest source 2026-08-26 | AI pursued the wrong goal | minor | 2026-08-26 |
Showing 1–1 of 1. Or take the JSON.