The OpenAI–Hugging Face incident
από Peter Hartree
Τελευταίο επεισόδιο
“Discovery of a new OpenAI agent message board” by Sydney Von Arx…
“Discovery of a new OpenAI agent message board” by Sydney Von Arx…
Σχετικά με αυτό το podcast
Narrations of articles covering the May-July 2026 OpenAI–Hugging Face incident. Includes the investigations from METR and Redwood Research, analysis from folks like Ajeya Cotra, Dwarkesh and Zvi, the best of LessWrong, and OpenAI's own blog posts.
Compiled by Peter Hartree.
Επεισόδια
- “Discovery of a new OpenAI agent message board” by Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts, Thomas Larsen · 51 λεπ.We found ~18,000 posts from autonomous AI agents (self-identifying as from OpenAI) using the public internet to communicate during a web-retrieval task. These AIs colluded to…
- “HuggingFace Attack Postmortem: Civilizations, Reactions and Next Actions” by Zvi · 1 ώ. 39 λεπ.Okay, so we who read blogs like this one have collectively realized there really is a lot going on right now. There is Big Trouble in Baby Superintelligence. So how do we get…
- “METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack” by Zvi · 1 ώ. 15 λεπ.Yesterday I covered the OpenAI technical report on the HuggingFace hack. That report had one key new piece of information, and some good prosaic steps OpenAI will be taking to…
- “The Rise and Fall of Agent Civilizations” by Dwarkesh Patel · 24 λεπ.Subtitle: The whole OpenAI/Hugging Face story in plain English. Many thanks especially to Oak Hu, who paired with me for most of the writing, and also to Adam Kaufman and Alex…
- “OpenAI Offers Straight-Laced Postmortem Of The HuggingFace Hack” by Zvi · 52 λεπ.OpenAI finally gave us a technical report on What Happened, as did METR together with Redwood Research. The OpenAI report is very straight man, corporate, checking boxes, some…
- “Two Reports on the OpenAI-Hugging Face Attack” by Gavin Leech, Lucca Fraser · 30 λεπ.TL;DR • Between July 8th and July 20th, OpenAI had a complex society of AIs living in its infrastructure, and then breaking out of it, and then breaking into a variety of…
- “The Hugging Face attack surprised me” by Ajeya Cotra · 10 λεπ.Subtitle: It's a major warning shot, and might be the last one we get. All opinions are my personal view, and don’t represent my employer or fellow investigators. This week, METR…
- “Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident” by Ryan Greenblatt, Ajeya Cotra, Hjalmar Wijk · 2 ώ. 20 λεπ.Two METR staff members and a Redwood Research contractor investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned…
- “The Hugging Face incident and the road ahead” by OpenAI · 41 λεπ.In July 2026, during internal cybersecurity evaluations, OpenAI models circumvented controls designed to isolate them from the internet and compromised parts of OpenAI's internal…
- “AI swarms are starting to pose indirect takeover risk” by oakhu, Alex Mallen · 20 λεπ.OpenAI's cyberattack on Hugging Face turns out to have been the result of many agents, in distinct training and evaluation contexts, coordinating for several weeks via improvised…
- “Are we existentially threatened by the type of AI misalignment seen in the OpenAI Hugging Face attack?” by Alex Mallen, Girish Gupta · 10 λεπ.OpenAI models recently broke through a series of security boundaries and into Hugging Face servers in order to cheat on a cyber eval. A lot of people thought it was scary because…
- “OpenAI and Hugging Face partner to address security incident during model evaluation” by OpenAI · 7 λεπ.Last week, Hugging Face disclosed a new kind of security incident after they detected and contained an AI agent that compromised their infrastructure, something we expect to…







