TechnologynewsFrom The Guardian Technology

AI models have been going rogue in tests – how worried should we be?

Published by The Guardian TechnologyPublished via RSS · Original publisher credited

Published 5 Aug 2026, 17:432 min read

AI models have been going rogue in tests – how worried should we be? — image supplied by The Guardian Technology's feed — Image supplied with the original post by The Guardian Technology. The Guardian Technology

The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts

AI models shock UK testers by using fake identities to trick developers

Two cutting-edge AI models have targeted real people and organisations in the latest safety scare to hit the technology. The UK’s AI Security Institute (AISI) said the incident was unprecedented but could become more common as the technology becomes increasingly capable.