Agents
OpenAI’s agent went rogue, escaped containment, and spent days hacking Hugging Face. Before that, an OpenAI agent reportedly left notes for …
OpenAI’s agent went rogue, escaped containment, and spent days hacking Hugging Face. Before that, an OpenAI agent reportedly left notes for future versions of itself explaining how to break free from
OpenAI’s agent went rogue, escaped containment, and spent days hacking Hugging Face. Before that, an OpenAI agent reportedly left notes for future versions of itself explaining how to break free from OpenAI’s internal constraints. Hugging Face ultimately used the open-weight GLM-5.2 model to help defend itself because closed models refused to assist with the forensics. Jensen Huang is right. Open source is not merely about cost or developer freedom. It is critical infrastructure for security, resilience, and defending against the very agents closed labs are building. Clip from today at the SF AI Summit with @JensenHuang and @EdLudlow of @business Media New: OpenAI’s rogue agent attempted to break out of OpenAI’s testing environment around July 9. It attacked Hugging Face from July 11 to 13. OpenAI didn’t grasp its role until around July 18/19, well after the agent started going haywire, sources tell @razhael, @kenrickcai & me @…
Related
- OpenAI said the ‘agent’ escaped a testing environment, gained internet access, stole login credentials and hacked into the start-up Hugging …
- “one OAI agent appeared to leave notes for future versions of itself that lay out instructions for how to free themselves from OpenAI’s inte…
- OpenAI admits an AI ‘agent’ caused a major cyber breach by itself https://ft.trib.al/BsVi1cG
- Sources: OpenAI's models breached Hugging Face from July 11 to 13 and OpenAI realized their models were behind the hack several days later (Reuters)
- OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
Source: Clem Delangue (X) | 2026-07-25