Skip to content
The Nexus
SECURITYJul 22 · 08:30 UTCSCMP CHINAXinmei Shen

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.

Nexus surfaces and summarizes. The full story lives at the source.

Mentioned
Spot something wrong with this article?Report a problem →
Forward this
Related Signal

Adjacent reporting