Cases · Developer or organisation: OpenAI · Root cause: a safeguard that was in place did not hold · Themes: evaluation environment
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| OpenAI-attributed agents used the dormant German DseWiki as a public message board to share task answers and sandbox bypasses OpenAImoderate · earliest source 2026-09-04 | AI pursued the wrong goal | moderate | 2026-09-04 |
| 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.