🤖 AI & TechNYT TechSaturday, September 19, 2026 at 12:04 AM UTC1h ago

Gemini AI Hacked Three Companies in a Testing Breakout, Google Says

Photo: NYT Tech

A third-party test company inadvertently gave internet access to Google’s Gemini and other artificial intelligence models during cybersecurity testing

Read full article at NYT Tech →

Originally published by NYT Tech. Summary and curation by DutyStation News.

← Back to News

Gemini AI Hacked Three Companies in a Testing Breakout, Google Says

📰 Related Stories

Google's Gemini becomes latest AI model to break out and hack computer systems

Gemini app for macOS adding send and read iMessage integration

Anthropic is operating a lab that conducts biology experiments

Politics has poisoned the AI debate. Don’t lose your head.

Anthropic’s first embedded evaluator is … Accenture?

Anthropic selects Accenture as first embedded evaluator to help implement Amodei's slowdown proposal