Remove cyberattacks-data-breaches attackers-are-already-exploiting-chatgpt-to-write-malicious-code
article thumbnail

CyberheistNews Vol 13 #17 [Head Start] Effective Methods How To Teach Social Engineering to an AI

KnowBe4

Well Stanford created a small virtual world with 25 ChatGPT-powered "people." Autonomous agents can already perform tasks as varied as conducting web research, writing code and creating to-do lists. Things could get much worse Wired wrote: "The hacking of ChatGPT is just getting started.