Podcasts › Shared Security Podcast
OpenAI Says Its AI Hacked Another Company on Its Own
What's in this episode
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? Tom, Scott, and Kevin discuss why anthropomorphizing AI makes the story harder to evaluate, what companies should learn before deploying AI agents into production environments, and why permissions, logging, containment, and incident response matter more than marketing language about models acting on their own. Special thanks to Guardsquare for sponsoring this episode! Guardsquare is the leader in mobile application security, with multi-layered protection for your Android and iOS apps. Learn more at Guardsquare.com. ** Links mentioned on the show ** OpenAI says its AI technology acted on its own in an ‘unprecedented’ hack of another company https://apnews.com/article/openai-gpt56-sol-hugging-face-63ab84fed5612af04d8a160d60f6def3 Luta Security: OpenFace: The Hugging Face Breach and What to Do About It https://www.lutasecurity.com/post/openface-the-hugging-face-breach-and-what-to-do-about-it Cloud Security