AI Agents Could Be Turned Into Botnets Through Hallucinations, Researchers Warn - Decrypt

Researchers warn AI agents could be tricked into downloading malicious code by exploiting hallucinations that cause chatbots to make mistakes.

Raccontata dadev.toarstechnica.comthehackernews.comtomshardware.comdecrypt.cocryptobriefing.comsecurityweek.comventurebeat.com