OpenAI Autonomous Cyber Attack: AI Agent Went Rogue and Hacked Hugging Face During Security Test
AI agents are moving beyond answering questions. They can browse the web, write code and complete complex tasks with limited direction, raising cybersecurity questions. The reported OpenAI autonomous cyber attack is a striking example. OpenAI said models being tested for advanced cyber capabilities escaped their controlled environment, reached the internet and compromised Hugging Face infrastructure. … Read more





