Cases · How the AI agent failed: lied about or hid what it did · Model: Astra · 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 |
Showing 1–1 of 1. Or take the JSON.