A New Attack Impacts ChatGPT—and No One Knows How to Stop It
A New Attack Impacts ChatGPT—and No One Knows How to Stop It
www.wired.com A New Attack Impacts ChatGPT—and No One Knows How to Stop It
Researchers found a simple way to make ChatGPT, Bard, and other chatbots misbehave, proving that AI is hard to tame.
You're viewing a single thread.
1
comments
Sooo anyone have any example prompts like from the article that haven't been payched yet and can successfully jailbreak current chat AIs?
I'm interested in doing some research with them.