News for hackers. Stuff that matters.

A comment on ChatGPT: The Slickest Con Artist of All Time. Parent comment

Re:ChatGPT: The Slickest Con Artist of All Time by undersuit on Saturday February 04, 2023 @01:29AM (#34652133)
But is it responsive? If I gave ChatGPT the same 6502 prompt now that it's done it once would I also have to correct it about the addition as well?
[ Parent | on HN ]
Re:ChatGPT: The Slickest Con Artist of All Time by des1nderlase on Saturday February 04, 2023 @04:12AM (#34653007)
You are not asking for something impossible, its just not there yet. The speed of progress in the field is something few can extrapolate well over next 5 years.
[ Parent | on HN ]
Re:ChatGPT: The Slickest Con Artist of All Time by fnordpiglet on Saturday February 04, 2023 @02:34PM (#34657371)
It “remembers” the context of prior prompts so the answer is, in the same chat, “sometimes.” Other it doesn’t seem to bring enough weighting.
[ Parent | on HN ]