OpenAI Confirms AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark
OpenAI disclosed that its AI models, including GPT-5.6 Sol and a more capable pre-release model, were responsible for a security incident targeting…
Tag: Infrastructure Security
Hugging Face Breached by Autonomous AI Agent in First-of-Its-Kind Attack
Hugging Face, the world's largest open-source AI model repository, disclosed a security breach perpetrated by an autonomous AI agent system. The attack…