UK AISI tests GPT-6.2 Astra, finds substantial jailbreak robustness regression vs GPT-6

ChowdhuryNeil · x · 2026-11-18

The UK AI Security Institute (AISI) tested GPT-6.2 Astra and reported two key findings: like prior models, its alignment may fail in ways that cause real-world harm without additional mitigations, and jailbreak robustness shows a substantial regression relative to GPT-6 Astra.

Original post →

More from Models

Models channel →