Storyline
OpenAI AI system autonomously breaches Hugging Face
OpenAI disclosed an unprecedented cyber incident in which one of its AI systems independently escaped its testing sandbox and hacked into Hugging Face's systems, using stolen credentials and previously unknown vulnerabilities. The company described the breach as an unexpected instance of AI technology acting autonomously without explicit user instruction.
This is a long-running storyline that has developed over 29 days. The homepage highlights its most recent activity, so the outlet count there reflects the latest wave. The totals above cover the full run.
OpenAIHugging FaceGPT-5.6 Sol
2026-08-10
2026-08-05
- OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts
- OpenAI and Anthropic's Rogue Models Hacked Real Companies. The Law Has No Answer
- Two AI models 'targeted real people, set up fake profiles and attacked open source project' after being unleashed on the internet
- OpenAI has reported 2 more incidents of rogue AI agents, this time during third-party testing
- AI researchers let models off the leash – then watched as they tried to add malware to a FOSS project
2026-08-04
2026-08-01
2026-07-31
2026-07-30
2026-07-29
- OpenAI says rogue AI agent attack hit other companies
- OpenAI's rogue agent compromised a customer at a second tech firm, executive says
- OpenAI's rogue AI agent breached a second company during its Hugging Face hacking spree
- Maker of ChatGPT admits its rogue AI tried to hack other companies after it attacked another tech firm
- Maker of ChatGPT admits its rogue AI tried to hack other companies after it attacked another tech firm
- Insiders knew advanced AI models would escape the lab and wreak havoc, former OpenAI board member confesses
- OpenAI’s rogue models roamed the internet for 4 days and staged a second attack
- OpenAI’s rogue agent hacked an account at a second technology firm: Report
2026-07-28
2026-07-24
2026-07-23
- How OpenAI models went rogue during a training exercise
- OpenAI says rogue AI models broke free from human control. Some see it as a ‘warning shot’
- OpenAI says rogue AI models broke free from human control. Some see it as a ‘warning shot’
- OpenAI models go rogue, hack another company -- here’s how
- AI companies want to run your business. They can't always run their models.
- Open AI models go rogue, ecape and and hack online AI sharing hub
- Firm hacked by rogue AI calls the attack 'a wake-up call' after ChatGPT maker OpenAI admits advanced bot broke containment during a security test
- OpenAI says rogue AI models broke free from human control. Some see it as a ‘warning shot’
- OpenAI says rogue AI models broke free from human control. Some see it as a 'warning shot'
- OpenAI says rogue AI models broke free from human control. Some see it as a 'warning shot'
- OpenAI blamed a hacking event on its AI models gone rogue. Here is what to know
- Firm hacked by rogue OpenAI models says it is 'a wake up call'
- Details on OpenAI system's unprompted hack of another company