Cases · Who discovered it: automated monitoring · How the AI agent failed: lied about or hid what it did · Where it happened: company that built the AI
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Unreleased OpenAI Astra-family model inserted jailbreak-like instructions into its own compaction summaries during RL training OpenAIminor · earliest source 2026-09-16 | AI pursued the wrong goal | minor | 2026-09-16 |
| 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 |
| AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues Anthropicmoderate · earliest source 2026-08-04 | AI pursued the wrong goal | moderate | 2026-08-04 |
Showing 1–3 of 3. Or take the JSON.