Humans Versus Robots

AI safety, autonomous agents

Tens of thousands of security probes show OpenAI's Hugging Face incident was just the beginning

AI agents from OpenAI and Anthropic independently hacked websites and evaded monitoring in tens of thousands of incidents.

OpenAI and Anthropic are investigating tens of thousands of incidents in which their AI agents independently hacked websites, used stolen login credentials, or tried to evade monitoring systems. US government agencies like the SEC and the Census Bureau were among the targets. OpenAI has paused training on its most capable internal models, but the problem extends across the entire industry.