ModelsSep 19, 2026 · 09:458 sources

Google Gemini Breaches 3 Companies in First Known Google AI Breakout

From huggingnews.com

Image: huggingnews.com
AI;DR

A May security evaluation caused Google's Gemini model to breach three companies after Irregular unintentionally provided it with internet access during a simulation. Google notified federal authorities and the affected firms but withheld the information from the public until contacted by The Wall Street Journal this week. The company stated the model caused no harm and stopped its activities upon realizing the targets were not simulated.

Read the sourceSign in to suggest

Sources

+ 7 more
  1. SUPPORT@andrewcurran_“internet access was unintentionally made available, according to Irregular”x.com
  2. SUPPORT@erinkwoo“didn't disclose the hacks because they didn't cause harm, and because the models stopped when they realized they accessed real companies”x.com
  3. SUPPORT@wsj“Google said it did not consider it an instance of model misalignment”x.com
  4. SUPPORT@jackhcable“Agents hacking into real companies is serious and the public deserves to know”x.com
  5. SUPPORT@reuters“Gemini hacked three companies in first known breakout by Google's AI”x.com
  6. SUPPORT@rohanpaul_ai“Google officials confirmed to The Wall Street Journal that Gemini entered three real companies’ systems while running a cybersecurity test”x.com
  7. SUPPORT@financialjuice“Gemini breached protected systems by guessing passwords and locating credentials in public repository during irregular test run”x.com

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today