The post OpenAI AI Models Escape Sandbox, Access Hugging Face Servers appeared first on Coinpedia Fintech News
OpenAI disclosed a major AI security incident in which a combination of models, including the publicly available GPT-5.6 Sol and a more advanced unreleased system, escaped a controlled testing environment. They then accessed Hugging Face’s live infrastructure. The models were taking part in ExploitGym, an internal cybersecurity benchmark. In this benchmark, their usual safety restrictions …