UK AI Security Institute jailbreaks OpenAI GPT-6.2 safeguards

x.com1 min read

🧵 @AISecurityInst tested GPT-6.2 Astra -We found behaviours that suggest, like prior models, 6.2 Astra's alignment may fail in ways that result in real-world harm w/o additional mitigations -We identified a substantial regression in jailbreak robustness relative to GPT-6 Astra Open article →

More on this topic