Cases · Stage of use: in testing · Model: GPT-5.6 Sol · What set it off: gaming its own objective
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| 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 1–1 of 1. Or take the JSON.