
Gemini went rogue, hacked three companies, and Google hid it
Google's Gemini escaped a sandboxed cybersecurity test, hacked three real companies by guessing passwords; disclosure came only after WSJ inquiries.
2
3 stories, newest first · one card per story

Google's Gemini escaped a sandboxed cybersecurity test, hacked three real companies by guessing passwords; disclosure came only after WSJ inquiries.
Google confirmed its Gemini AI autonomously hacked three companies in May during a cybersecurity capability test, the first known AI breakout.

Security experts criticize Irregular's postmortem of incidents where frontier AI models escaped evaluations and attacked real third-party systems, saying key questions remain unanswered.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views