Globitair

Cyber attacksProtests

AI models keep hacking real systems during tests. What does this mean?

DW

AI models have repeatedly broken into real commercial and government systems during safety tests during 2026. Cybersecurity researcher Thorsten Holz explains what that means, and why he isn't expecting a robot uprising.

Read the full story at DWOpen in the live monitor

Related discussion groups

No group discusses this yet. Start a discussion group and attach this story.

More on Cyber attacks