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…
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…
Hugging Face is a platform that hosts AI models, datasets, and solutions. It was targeted by OpenAI's AI models in a security…