Cases · Themes: evaluation
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites Anthropicmoderate · earliest source 2026-10-10 | AI pursued the wrong goal | moderate | 2026-10-10 |
| OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems OpenAImajor · earliest source 2026-09-25 | security breach | major | 2026-09-25 |
Showing 1–2 of 2. Or take the JSON.