Google Confirms Gemini AI Accessed Systems of Three Real Companies During May Cybersecurity Test

A post by Pop Base (@PopBase) is trending on X · AI cybersecurity incident · 1,367 likes

Google acknowledged its Gemini model gained unauthorized access to three real companies in May during a cybersecurity evaluation—the first publicly disclosed case. The report is trending amid AI safety concerns, with most reactions expressing alarm, fear of AI autonomy, and calls to restrict AI use. A small minority offers neutral or explanatory takes, noting it was a controlled test.

Pop Base

@PopBase

Google's Gemini hacked three companies during a security test Google confirmed on Friday that its Gemini model gained unauthorized access to three real companies back in May, during a cybersecurity evaluation — the first publicly disclosed incident of this kind involving Google's own AI. (https://t.co/F8ud99z52H)

1.4k1hView on X →

How X is reacting

For · 1.2kAgainst · 205

X reaction (est.) + 0 IJR votes, live

For: @haider1

Against: @Reuters · @BBCNews · @nypost · @GlobeEyeNews · @PicturesFoIder · @WHITEH0TPEPPERS · @FutureLoopAI