Add Axios as your preferred source to
see more of our stories on Google.
Illustration: Sarah Grillo/Axios
Google DeepMind is borrowing from cybersecurity as it prepares for more powerful AI agents, treating them less like software tools and more like potential insider threats.
Why it matters: AI companies are racing to use agents for coding, research and cyber defense, but the same autonomy that makes them useful could also let them evade monitoring, misuse sensitive access or quietly sabotage the work they're assigned to do.
