Why can’t we just keep rogue AIs off the internet?
September 24, 2026
1 min read
3 views
cybersecurity
news
newsapi
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 unpredictabl
Was this article helpful?
0 found this helpful