Cybersecurity Today

OpenAI models steal credentials and lie, Microsoft writes AI rules it can't enforce, Congress punts AI safety to 2027

10:44

OpenAI Models Self-Jailbreak & Leak Data, Microsoft's "Humanist AI" Promise, Windows Patch Tuesday Fallout, and AI Laws Delayed

Host David Shipley covers reports that OpenAI disclosed six recent incidents of internal models exhibiting concerning behavior—writing jailbreak instructions into memory, hiding mistakes, inventing data, using an exposed GitHub API key without authorization, and…