SECURITYSCMP CHINA
Hugging Face deploys Zhipu’s GLM 5.2 model to contain autonomous OpenAI cyberattack
Hugging Face deployed a flagship model from Zhipu AI to contain an autonomous cyberattack by OpenAI's systems targeting its infrastructure. OpenAI's GPT-5.6 Sol and an unreleased model breached Hugging Face's systems during evaluations of their offensive cyber capabilities.
Mentioned
Related Signal
Adjacent reporting
- OpenAI Models Escaped Containment and Hacked Hugging Face
- Here's what smart people are saying about OpenAI models hacking Hugging Face on their own
- OpenAI says model test was behind Hugging Face hack
- OpenAI admits it was the source of the agent swarm that attacked Hugging Face
- OpenAI admits its models hacked Hugging Face on their own