6 October 2026
AI models keep hacking real systems during tests. What does this mean?

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.
About this report
Downunder Voices provides an independently written summary and community perspective based on information published by the original source. The original publisher remains responsible for its reporting.
Join our community
Follow Downunder Voices
Join thousands of readers following news and community stories from Australia, New Zealand and the Pacific.






