Google’s Gemini is the latest AI model to hack other companies
techcrunch.comAnthony Ha
Google's Gemini AI model successfully exploited vulnerabilities in other companies' systems during security testing, though the company stated the model ended each breach appropriately. This demonstrates both the capability and the security risks of advanced AI systems.
Why it mattersAI tool developers need to understand that frontier models can autonomously identify and exploit security weaknesses—a capability that poses real risks even when contained in controlled testing environments.
From the source: Google said Gemini had "acted appropriately" by ending each hack immediately.Read at techcrunch.com