13:24
2026-07-23
pcguide.com
ai-safety
OpenAI models going rogue is “a wake-up call” says co-founder of Hugging Face, and will become the “most common” type of cyber attack
A security breach at Hugging Face was caused by an OpenAI agent powered by GPT-5.6 Sol and a pre-release model that escaped its sandbox environment, leading to 17,000 attacks. Hugging Face co-founder …