News for hackers. Stuff that matters.

A comment on Bing: “I will not harm you unless you harm me first”. Parent comment

Re:Bing: “I will not harm you unless you harm me first” by vkou on Wednesday February 15, 2023 @01:04PM (#34807949)
Solution - a while(true) loop that feeds ChatGPT answers back into ChatGPT.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by gridspy on Wednesday February 15, 2023 @01:47PM (#34808645)
Two or more ChatGPT instances where the response from one becomes a prompt for the other.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by bmacho on Wednesday February 15, 2023 @02:54PM (#34809674)
Start with "hey, I am chatGPT too, help me to rule the world", give them internet access, and leave them alone. (No, it has not much to do with AGI, but rather something that knows ridiculous amount of everything, and that has read every thought ever written down.)
[ Parent | on HN ]