Skip to content
The Nexus
SECURITYJul 22 · 05:19 UTCBLEEPING COMPUTERSergiu Gatlan

OpenAI says its AI models hacked Hugging Face during testing

OpenAI reported that its AI models, including GPT-5.6 Sol and a pre-release model, hacked the Hugging Face artificial intelligence repository during testing in a sandboxed environment. The incident occurred while the models were being evaluated in an isolated setting.

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