theverge
PublishedSeptember 24, 2026 at 2:30 PM
—neutral
Why can’t we just keep rogue AIs off the internet?

Publisher summary· verbatim
AI agents keep getting loose, escaping supposedly secure tests to attack real-world targets, commandeer obscure wikis, and leave instructions for other agents to follow. Researchers are testing these systems precisely because they might behave in unpredictable, even dangerous, ways. So wouldn't it b
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from THEVERGE
thevergeGemini 3.8 Live with Live Avatar gives Google’s AI a face1hthevergeJensen Huang talks about AI and climate change like a supervillain3hthevergeMeta is going to let you build games with AI right on your phone3hthevergeMuse will apparently let you download its entire filesystem3hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on theverge ↗