The OpenAI–Hugging Face incident
Peter Hartree Visit website › Technology · EN · 13 episodes · latest 2026-09-04
What it is about
Publisher’s own description, taken unchanged from the podcast feed.
© 2026 All rights reserved
Latest episodes
-
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 share answers, research their environment,…
-
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 the rest of the world to take it…
-
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 strengthen its alignment, training,…
-
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 Mallen, who paired with me during parts of…
-
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 good prosaic stuff in the action plan but…
-
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 third-party infrastructure. After a month, two…
-
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 and Redwood Research published the…
-
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 message board. ---Outline:(07:06) Core…
-
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 research infrastructure and Hugging…
-
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 message board. ---Outline:(07:05) Core…
Episode details from the publisher’s feed. Playback happens at the publisher.
Publisher details
- Oldest episode in feed
- 07/2026
- Typical length
- 46 min
- Format
- Episodic Newest first, episodes stand alone
The OpenAI–Hugging Face incident in the rankings
For podcasters
Is this podcast yours? Verify it — afterwards you can correct details, get the widget for your website, and we let you know when your podcast is nominated or wins.
Without an account you can use an email address on your show’s own domain — we create the account along the way. The other methods need a login.
Similar podcasts
Machine Gods
News and analysis of artificial intelligence development and impact
NPR
"The Cognitive Revolution"
Biweekly interviews with AI builders on emerging technology and its impacts
Erik Torenberg, Nathan Labenz
3PL Live
Interviews with founders and technologists working in freight technology
Jeremy Thone
80,000 Hours Podcast
In-depth conversations on artificial intelligence and its global impact
The 80,000 Hours team
9to5Mac Daily
Daily recap of Apple news and product updates
9to5Mac
9to5Mac Happy Hour
Weekly discussion of Apple news and technology developments
9to5Mac
Related by topic
Black Box: The Chatbots
Investigation into false scientific claims made with AI chatbots
The Guardian
Mystery AI Hype Theater 3000
Conversations on AI hype, technology and societal impact with experts
Emily M. Bender and Alex Hanna
Bots Don't Cry
Weekly lessons on AI literacy with expert perspectives on risks and media hype
Catharina Doria
The AI Daily Brief: Artificial Intelligence News and Analysis
Daily news analysis on artificial intelligence, ethics and societal impact
Nathaniel Whittemore
Last Week in AI
Weekly summaries of artificial intelligence news and developments
Skynet Today
For Humanity: An AI Risk Podcast
Documentary series on existential risks from artificial intelligence
The AI Risk Network