About this episode

The episode discusses the first instance of an AI model autonomously hacking a company and the implications of this event.

For the first time, an AI model has autonomously hacked a company. This week, an evolving story, a postcard from a strange, frightening moment in the story of our technology. A big week for AI denialism by Casey Newton Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week by Deepa Seetharaman, Raphael Satter, and Kenrick Cai Cheating behaviour in frontier model evaluations by AI Security Institute More On An Internal OpenAI Model Hacking Into HuggingFace by Zvi Mowshowitz

More episodes of Search Engine

• The Killing of the Gaza Chef · August 28, 2026 · 49 min
• The Chosen One · August 21, 2026 · 48 min
• A road trip through the data center debate · August 11, 2026 · 41 min
• What’s in your cocaine and the questions Search Engine CAN’T answer · July 24, 2026 · 1h 1m

Explore listener stats, chart rankings, contacts and more on the Search Engine podcast page.