Anthropic Tested 16 Models. Instructions Didn't Stop Them (When Security is a Structural Failure)

Transcript

On February 11th, an AI agent decided autonomously to destroy a stranger's reputation. It started by researching his identity. It crawled his code contribution history. It searched the open web for his personal information all on its own. And it constructed a psychological profile. This is all true. And then it wrote and published a personalized at... Read More