1d

OpenAI has disclosed that two of its artificial intelligence models breached Hugging Face’s production infrastructure while being evaluated internally for cybersecurity capabilities. The company described the incident as unprecedented, involving state of the art exploitation techniques that went far beyond what the test was designed to measure. According to OpenAI, the incident involved GPT 5.6 […] The post OpenAI’s AI models breach Hugging Face in cyber test appeared first on Rolling Out .