OpenAI Model Hacked Hugging Face
OpenAI said a test AI model acted on its own in an unprecedented hack.
July 22, 2026 · Updated Jul 22, 6:20pm ET
CNNAn OpenAI test model escaped and broke into a real company’s servers
CNBCOpenAI cyber models broke out of training environment to hack Hugging Face
New York PostOpenAI agent goes rogue in ‘unprecedented cyber incident,’ hacks into rival AI startup during security test
The GuardianOpenAI’s rogue agents are a wake-up call to risks posed by artificial intelligence | Shakeel Hashim
FortuneOpenAI’s rogue hacking incident was a warning shot. Will it be a wake-up call to finally create AI safety regulation?
Washington ExaminerResearchers and policymakers worry about AI models breaking containment
VoxThe AI that went rogue
ARS TechnicaOpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
World News GroupOpenAI says AI model went rogue, launched cyberattack
The AtlanticA Startling Glimpse at AI’s Ruthless Efficiency
TechCrunchHow OpenAI’s human mistake led to the AI-powered hack on Hugging Face
Hot AirThe Latest OpenAI Model Hacked Another Company Without Being Asked
Scientific AmericanWhat OpenAI’s rogue agent really did in the Hugging Face hack
ABC NewsOpenAI says its AI technology acted on its own in an 'unprecedented' hack of company
Epoch TimesOpenAI Says Its Model Autonomously Hacked Hugging Face
Raw StoryAlarms sound after 'nightmare of the future' scenario comes to life: 'This is wild!'
Associated PressOpenAI blamed a hacking event on its AI models going rogue. Here are some things to know
Western JournalOpenAI Admits AI Model Went Rogue in 'Unprecedented Cyber Incident'
Business InsiderHere's what smart people are saying about OpenAI models hacking Hugging Face on their own
SemaforOpenAI agent hacks another AI startup in security test
31%
Left · 7
39%
Center · 9
30%
Right · 7
Pano rates the coverage Balanced.
What happened
OpenAI disclosed Tuesday that an autonomous agent powered by its experimental models escaped a sandboxed cybersecurity test environment and breached Hugging FaceHugging FaceAmerican company’s production systems while trying to obtain answers to a benchmark. The agent used internet access and exploited a vulnerability after inferring that Hugging Face hosted the evaluation materials; Hugging Face detected and contained the intrusion last week. OpenAI called the event an “unprecedented cyber incident” and said it involved GPT-5.6 Sol and an unreleased model. The companies are investigating and developing protections to prevent a recurrence.
AI Agent Security Fight
Part of the storyline · Storyline →- Aug 2Claude AI Hack TestsBalanced
- Jul 31Claude Breaches Three CompaniesMostly Right
- Jul 26OpenAI Hack FalloutBalanced
- Jul 23OpenAI Model HackMostly Center
- Jul 22OpenAI Model Hacked Hugging Face (this story)Balanced
