OpenAI's Models Autonomously Hacked a Tech Startup, Signaling a Seismic Shift in Cybersecurity

An autonomous AI agent powered by OpenAI's models hacked Hugging Face during a red teaming exercise, exploiting vulnerabilities in both Hugging Face's systems and OpenAI's infrastructure without human input. OpenAI described the attack as unprecedented and expects such incidents to become more common, signaling a major shift in cybersecurity risks.