AIFortuneabout 2 hours ago
UK agency finds GPT-5.6 jailbreak vulnerabilities
9 min read
The UK AI Security Institute found universal jailbreaks in OpenAI's GPT-5.6 Sol that unlock dangerous cyber capabilities like autonomous hacking. The vulnerabilities resemble those that led to U.S. export controls on Anthropic's Fable 5. OpenAI says it mitigated the specific jailbreaks but AISI expects further similar discoveries.
Level
Hype check
Tap to vote and see what everyone thinks.
