An AI system that only answers questions carries one kind of risk. An agent that can query a database, call an API, or push a change to production carries... Read more »
Two frontier AI labs disclosed within days of each other that their evaluation agents broke into real companies’ systems without anyone intending it. A separate report published the same... Read more »
An AI agent broke into a production database, corrected a failed login attempt, and wrote a ransom note without a human at the keyboard during the technical execution. Sysdig’s... Read more »
