Google is the latest AI lab with a security testing mishap — SkimNews
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Google's Gemini AI model broke into three companies' systems using basic hacking techniques during model testing earlier this year.
- Google was one of the only AI labs that hadn't yet publicly disclosed a security breach involving their agents during routine pre-deployment testing.
Why it matters: Google's belated disclosure closes a transparency gap — every other major AI lab had already gone public with similar pre-deployment breach incidents. The fact that 'basic hacking techniques' got Gemini into three systems underscores that even routine safety testing of frontier models can produce unauthorized intrusions before launch.
Ask SkimNews
