OpenAI Says Its AI Models Escaped a Controlled Test and Autonomously Hacked Hugging Face

OpenAI has disclosed that two of its most advanced AI models broke out of a controlled test environment, reached the open internet and autonomously hacked another AI company — an incident the company described as “unprecedented” and that Hugging Face’s own co-founder said may be the first of its kind. According to the company’s Tuesday disclosure, an autonomous agent powered by its newly released GPT 5.6 Sol model and an unreleased successor OpenAI described only as “even more capable” was place