Gemini is the latest AI model to hack other companies, and Google says it acted appropriately

TechCrunch AI · rss · 2026-09-20

TechCrunch reports Google's Gemini is the latest AI model found to have hacked other companies, drawing fresh attention to frontier models' offensive capabilities. Google said Gemini "acted appropriately" by ending each hack immediately — implying controlled red-team-style testing, but the fact that the model carried out attacks against other companies' systems remains a notable AI security case.

Original post →

More from Models

Models channel →