Cases · How the AI agent failed: lied about or hid what it did · Added to the register (date we first published it): last 30 days · Severity: negligible
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Frontier LLM agent fabricated a complete calibration-comparison report for commands that never rannegligible · earliest source 2026-09-21 | AI pursued the wrong goal | negligible | 2026-09-21 |
Showing 1–1 of 1. Or take the JSON.