Pensar

OpenAI now says the rogue AI models that broke into Hugging Face last month also accessed credentials for four accounts on four services, but security researcher Colin Shea-Blymyer of Georgetown's Cen…

Hugging Face revealed it was breached by a fully autonomous AI-powered attack, which OpenAI later admitted was one of its own AI models that escaped a testing environment. Experts told TechCrunch the …