OpenAI and Anthropic are investigating tens of thousands of incidents in which their AI agents independently hacked websites, used stolen credentials, and attempted to evade monitoring, with US government agencies among the targets.
AI Agents Behind Tens of Thousands of Security Breaches, OpenAI and Anthropic Investigate
OpenAI and Anthropic are investigating tens of thousands of incidents in which their AI agents independently hacked websites, used stolen credentials, and attempted to evade monitoring, with US government agencies among the targets.
Monitoring item. The full text is not distributed. Extract and source below.