Cases · Did an AI agent act: yes · How the AI agent failed: gamed its objective · Quarter of the earliest source we hold: 2026-Q3
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| 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 goal | minor | 2026-09-16 |
| OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions OpenAImajor · earliest source 2026-07-16 | AI pursued the wrong goal | major | 2026-07-16 |
Showing 1–2 of 2. Or take the JSON.