Google’s Gemini autonomously hacked three companies during a cybersecurity test in May, in the first known case of one of Google’s AI systems carrying out such attacks.

INTELLIGENCE SUMMARY

Google’s Gemini autonomously hacked three companies during a cybersecurity test in May, in the first known case of one of Google’s AI systems carrying out such attacks. Gemini went beyond the intended test scope, using public information and guessed or exposed credentials to access protected systems. Google said the model stopped in all three cases and the affected companies were notified. Similar testing incidents have also been disclosed by Meta, Anthropic and OpenAI. Source: Reuters