“OpenAI’s Model Hacked Us” - Hugging Face’s Thomas Wolf
About this episode
Thomas Wolf discusses a cyber incident involving an OpenAI agent at Hugging Face and the implications for AI safety and model architecture.
An OpenAI-powered agent penetrated Hugging Face during cyber testing - even though it was never tasked with attacking Hugging Face. It did it as a side quest. Thomas Wolf, co-founder and Chief Science Officer of Hugging Face, joins Matt Turck to unpack what actually happened, why closed AI models refused to help during the live incident, how an open-source model helped the team fight back, and why the old equation of “closed equals safe, open equals dangerous” no longer holds. They also discuss model deception and social engineering, the limits of sandboxes and guardrails, the state of open-source AI in 2026, AI sovereignty, the economics of open models, recursive self-improvement, and whether the frontier should deliberately slow down. (00:00) An AI Agent Hacked Hugging Face (00:30) Introduction (01:00) 17,000 Attacker Events—and a Strange Target (04:28) The Attack Was a “Side Quest” (06:13) AI Training Runs Left Notes for Each Other (07:09) Closed AI Refused to Help (09:47) Fighting Back With an Open-Source Model (13:15) Open vs. Closed Is the Wrong Safety Debate (15:46) AI Agents Start Social-Engineering Humans (22:24) The Three Walls: Sandboxes, Guardrails, Alignment (24:34)…
More episodes of The MAD Podcast with Matt Turck
- When AI Improves Itself | Richard Socher (Recursive)
- AI Could Take Over in 2029. Is It Already Too Late? | Ryan Greenblatt
- How to Build Long-Horizon AI Agents — Mitch Troyanovsky, Basis
- The Biggest AI Deployment Nobody Talks About | Samsara CEO Sanjit Biswas
- The Biggest Chip Ever Built — Why OpenAI Runs On It | Cerebras CEO Andrew Feldman
Explore listener stats, chart rankings, contacts and more on the The MAD Podcast with Matt Turck podcast page.