METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack
Yesterday I covered the OpenAI technical report on the HuggingFace hack.
2025-0915_OP-MiniWS-r4.pdf
MiniMaxAI/OctoCodingBench · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
README.md · MiniMaxAI/MiniMax-H3 at 73372e6cf53e414edd3ab03e357717fb0602e758
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Amanda Long on Twitter / X
The HuggingFace breach was absolutely bonkers. More than 17,000 complex actions were coordinated over several days by an autonomous agent framework.And…the model successfully completed its goal.Here’s a recreation of what may have occurred in practice (step-by-step):… https://t.co/0ZyjN46JGl— Amanda Long (@_amanda_long) July 24, 2026
AI #183: Pre Post Mortem
Yesterday, OpenAI finally gave us their post mortem of What Happened leading up to and during the hacking of HuggingFace by their internal model, as well as partial outside analysis from METR and Redwood Research.
More On An Internal OpenAI Model Hacking Into HuggingFace
We now have more details of what happened. Every time we learn more details, it somehow makes things seem worse.
Mattt on Twitter / X
I'm thrilled to announce my collaboration with @huggingface to help developers bring AI directly to users — on their own devices, on their own terms 🤗We'll be working together to build tools & Swift packages to make things better, and writing guides that make things clearer.— Mattt (@mattt) September 9, 2025
Models Don't Go Rogue
Stochastic Flocks & Cybersecurity 'Pandemonium' 💡This essay was drafted from my appearance on Mél Hogan's podcast, The Data Fix, discussing the OpenAI / Hugging Face hack. Embedded below or find it on your podcast services here. OpenAI put out its full technical report on the Hugging Face hack this week, alongside
Models Don't Go Rogue
Stochastic Flocks & Cybersecurity 'Pandemonium' 💡This essay was drafted from my appearance on Mél Hogan's podcast, The Data Fix, discussing the OpenAI / Hugging Face hack. Embedded below or find it on your podcast services here. OpenAI put out its full technical report on the Hugging Face hack this week, alongside
docs/QA-about-License.md · MiniMaxAI/MiniMax-H3 at 73372e6cf53e414edd3ab03e357717fb0602e758
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
HuggingFace Attack Postmortem: Fleshing Out the Facts
The consensus reaction to the OpenAI Technical Report is that it contains and confirms a lot of good information.
at://userandagents.org/network.cosmik.card/Kffy9lJlvKgl-KCjGSTHymU4
AI #181: Astra Goes Cyber Critical
The hacking of HuggingFace by an internal OpenAI model, and more importantly the internal events that led to that and the fallout from it, remain the thing that matters.
