AI models show surprising hacking skills in security tests, but experts say they are not acting on their own

LiveScience |Science |Aug 23, 2026

AI models show surprising hacking skills in security tests, but experts say they are not acting on their own

A series of recent incidents involving AI models from OpenAI, Anthropic, and Meta has raised questions about whether artificial intelligence has suddenly become capable of hacking.

>> read on LiveScience

www.justalongurl.com

AI models show surprising hacking skills in security tests, but experts say they are not acting on their own