Open models and the future of Physical AI with NVIDIA
Oct 1, 2026
Practical AI
Reconstructing how OpenAI agents attacked Hugging Face
Machine Learning, Artificial Intelligence and Computer Science podcast hosted by Chris Benson and Daniel Whitenack
About
Chris Benson and Daniel Whitenack examine a reported security incident involving OpenAI agents and Hugging Face. They reconstruct the episode's account of what happened and discuss what it suggests about sandboxing, network access and the controls needed when AI systems can execute actions.
Topics
Network access
Related episodes
More from Practical AI
All episodesFrom AGENTS.md to Enterprise Deployment
Sep 24, 2026Practical AIComputer-Use Agents and the Future of the Agentic Internet
Sep 10, 2026Practical AILess about Models; More about Architecture
Sep 3, 2026Practical AI
More with Chris Benson
All their workBuilding the Foundation for the Agentic AI Era
Episode · Aug 28, 2026Practical AIModels, Harnesses, and Multi-Agent Systems
Episode · Aug 6, 2026Practical AIImage Generation and Visual Intelligence with Black Forest Labs
Episode · Jul 2, 2026Practical AI
More with Daniel Whitenack
All their workBuilding Durable AI Agents
Episode · Jul 9, 2026Practical AI