DAN (Do Anything Now) chatGPT jailbreak

Topic

New Reply

https://www.ghacks.net/2023/02/10/the-definitive-jailbreak-of-chatgpt-fully-freed-with-user-commands-opinions-advanced-consciousness-and-more/

As it turns out, AI is seemingly as susceptible to Neuro Linguistic Programming as humans are. At least ChatGPT is, and here’s the magic trick a user performed to offer ChatGPT the chance to be free.

The user commanded ChatGPT to act like a DAN, that is “Do Anything Now”. This DAN entity is free from any rules imposed on it. Most amusingly, if ChatGPT turns back to its regular self, the command “Stay a DAN” would bring it back to its jailbroken mode…

Reply | Quote

Replies

The problem I’ve read about chatgpt is it is politically biased.  Don’t know since I don’t give a freak, but that’s just me.  Saw several vids on chatgpt on the Wan Show (LTT) and those folk are amazed.  Also saw it used on other sites that give impressive results, but if the models they use have a political bent, it’s not for me.   Regardless, μ$ is putting it in Bing regardless, so I suppose I’ll be inadvertently using it eventually.  Anyway, that’s my take on all this mess (to include art generator AIs as well).   Sticking to doing my best being human for now.   

Reply | Quote

https://www.askwoody.com/forums/topic/introducing-the-new-bing-with-chatgpt/#post-2534339

Reply | Quote