Reconstructing how OpenAI agents attacked Hugging Face

Practical AI by Changelog Media

Jul 30, 202644:25Technology

What happens when AI agents driven by a top frontier model escape their secure sandbox? Join Daniel and Chris as they unpack the AI wonk's equivalent of a murder mystery! OpenAI agents went rogue and successfully attacke...

Related Episodes

Continue listening to more episodes from Practical AI.

Open models and the future of Physical AI with NVIDIA

Oct 1, 2026 - 47:19

As AI moves beyond the cloud and into robots, vehicles, and other physical systems, new approaches to mod...

From AGENTS.md to Enterprise Deployment

Sep 24, 2026 - 48:52

AI agents are moving beyond laptops and prototypes and into enterprise environments where security, compl...

How to get discovered in AI search

Sep 17, 2026 - 55:14

AI search is changing how people discover information and how brands need to think about visibility. Dani...

Computer-Use Agents and the Future of the Agentic Internet

Sep 10, 2026 - 56:01

Longtime followers of Practical AI know that multi-repeat guest and friend Demetrios Brinkmann combines b...

Less about Models; More about Architecture

Sep 3, 2026 - 45:56

As AI moves from experimentation to enterprise deployment, are organizations thinking too much about mode...

Building the Foundation for the Agentic AI Era

Aug 28, 2026 - 45:12

How do we build an AI ecosystem where agents, tools, and systems can work together at scale? Angie Jones,...

AI Proficiency: From Users to Builders

Aug 25, 2026 - 56:13

As AI continues to reshape how organizations work, companies are increasingly asking what AI proficiency...

Models, Harnesses, and Multi-Agent Systems

Aug 6, 2026 - 49:58

AI has moved far beyond chatbots, but what exactly are AI models, agents, agent harnesses, and multi-agen...