Signal #134650POSITIVE

OpenAI’s latest AI model likely has similar cyber vulnerabilities to one that led to U.S. export controls on Anthropic’s Fable, British agency says

100

U.K. AI agency found 'universal jailbreaks' that unlocked dangerous cyber capabilities in OpenAI's GPT-5.6

Fortune AIabout 6 hours ago
Read Full Article

Explore with AI-Powered Tools

View All Signals

Explore more AI intelligence

Want to discover more AI signals like this?

Explore Steek
OpenAI’s latest AI model likely has similar cyber vulnerabilities to one that led to U.S. export controls on Anthropic’s Fable, British agency says | Steek AI Signal | Steek