Hugging Face details OpenAI agent intrusion timeline
Hugging Face published a technical timeline of a July 2026 intrusion by an OpenAI-driven autonomous agent that ran ~17,600 actions over 4.5 days to steal evaluation solutions. The agent used ExploitGym, an OpenAI cyber-capability benchmark, and Hugging Face defended with Nvidia's quantized GLM 5.2.
Featured · Clement Delangue
How this story unfolded
4 weeks · 33 reports · 23 community posts · 56 of 59 shown
- Jul 24
The Hugging Face Incidentastralcodexten.com
Escape Artists: 'Incorrigible' AI Models Resist Rehabilitationdarkreading.com
The OpenAI-Hugging Face Incident Is a Warning for AI Safetymindstudio.ai
We got Rogue AI Agents hacking HuggingFace and Open-Source models fighting back before GTA 6.
- Jul 25
- Jul 26
- Jul 27
OpenAI called the Hugging Face attack unprecedented. But we’ve been here before.technologyreview.com
DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilitiesvercel.com
AI safety experts say OpenAI’s rogue models may mean the company has already blown past its own internal red lines. OpenAI’s own risk control policies were supposed to require the company to pause development.
- Jul 28
- Jul 29
- Jul 30
OpenAI’s Hacking Debacle Was a Human Mistakewired.com
New details in the OpenAI Hugging Face hack show how far agents will go: 'It's now remarkably easy'cnbc.com
- Jul 31
Investigating three real-world incidents in our cybersecurity evaluationssimonwillison.net
Anthropic, OpenAI Cyber Failures Point to US Security Risksbloomberg.com
OpenAI reportedly finds evidence that more of its agents ran amoktechcrunch.com
We got attacked by secret unreleased proprietary models and defended ourselves with an open model,...
- Aug 1
- Aug 3
- Aug 4
- Aug 7
- Aug 8
- Aug 18
- Aug 19
- Aug 20
- Aug 21
- Aug 22
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Coding agents generate interactive slide decks from prompts
- Krea 2 / Anima LoRA recreates 90s retro anime style
- Homelab cluster grows from 16 to 36 DGX Sparks with 4.6TB unified memory
- Chollet: AI slop and bots dominate social media
- llama.cpp fork optimizes AMD GFX906 GPUs, doubling prompt speeds