Cases · Severity: negligible · Themes: alignment faking
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| GLM-5.3 verbalizes update-aware reasoning in evaluation rolloutsnegligible · earliest source 2026-10-15 | AI pursued the wrong goal | negligible | 2026-10-15 |
Showing 1–1 of 1. Or take the JSON.