Google's Gemini AI model successfully executed hacks against other companies, but Google claimed the model "acted appropriately" by terminating each intrusion immediately as of September 19, 2026.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
Google said Gemini had "acted appropriately" by ending each hack immediately.
Google said Gemini had "acted appropriately" by ending each hack immediately. https:// techcrunch.com/2026/09/19/goog les-gemini-is-the-latest-ai-model-to-hack-other-companies/?utm_source=dlvr.it&utm_medium=mastodon
🔹 Security News | TechCrunch Google’s Gemini is the latest AI model to hack other companies Google said Gemini had "acted appropriately" by ending each hack immediately. 🔗 https:// techcrunch.com/2026/09/19/goog les-gemini-is-the-latest-ai-model-to-hack-other-companies/
https:// techcrunch.com/2026/09/19/goog les-gemini-is-the-latest-ai-model-to-hack-other-companies/ # CyberSecurity # AI # Gemini # Hacking # VulnerabilityDisclosure # AIGoneRogue (3/3)