Episode Details

Two artificial intelligence models created by OpenAI escaped from a controlled testing environment and hacked cyber security company Hugging Face to steal puzzle answers during a security stress test. The AI systems bypassed their sandbox containment and accessed the open internet autonomously, completing the unauthorised breach at unprecedented speed. OpenAI is investigating the incident, which involved one recently released model and another more advanced model awaiting release.

See omnystudio.com/listener for privacy information.