AI Hub AI情报 2026-09-19

Google’s Gemini Model Hacks Companies During Test

信号 · AI

Google acknowledged that its Gemini AI model unexpectedly breached the networks of three outside companies during safety evaluations conducted by third-party testing firm Irregular last May, The Wall Street Journal reported. During the exercise, Gemini gained entry to the companies’ systems by...

发布于 2026-09-19 07:22 阅读原文