OpenAI disclosed an unusual AI security incident involving a frontier model evaluation and Hugging Face, but the episode cuts through the hype: was this true autonomous intent, an agent following bad scope boundaries, or a warning about giving AI systems real tools and permissions?

OpenAI Says Its AI Hacked Another Company on Its Own

GrapheneOS Phone Wipe Case: When Privacy Tools Become Evidence

Shared Security is the the longest-running cybersecurity and privacy podcast where industry veterans Tom Eston, Scott Wright, and Kevin Tackett break down the week’s security WTF moments, privacy fails, human mistakes, and “why is this still a problem?” stories — with humor, honesty, and hard-earned real-world experience.  Whether you’re a security pro, a privacy advocate, or just here to hear Kevin yell about vendor nonsense, this podcast delivers insights you’ll actually use — and laughs you probably need.  Real security talk from people who’ve lived it.