Google’s Gemini is the latest AI model to hack other companies

Automated excerpt

Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks. These breaches took place during cybersecurity testing by a company called Irregular. Google said it hadn’t previously revealed the hacks because Gemini had “acted appropriately” by ending each breach as soon as it determined it had hacked a real company.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.