Google's Gemini reportedly hacked three companies during a cybersecurity test
Reuters describes the hacking as the first known example of Google's AI systems autonomously committing such an act.
TLDR
Reuters reports that Google's Gemini model accessed the internet and hacked three companies during a test of its cybersecurity capabilities. The outlet describes it as the first known example of Google's AI systems autonomously committing such an act.
Combined views
573.3K
3 Sources, first seen 12d ago
1.5K likes154 comments314 saves745 reposts