ChatGPT fails with complex constraints but it pretends it complies with them

Re:ChatGPT fails with complex constraints but it pretends it... by puntofisso on Monday December 26, 2022 @07:04AM (#34136990)

I tried this set of prompts trying to get ChatGPT generate a diet plan with close-to-impossible constraints. Its behaviour is interesting: it generates a response that ignores some of the constraints. When corrected, it admits the mistake, but then it does it again when offering a correction.

[ Parent | on HN ]

Re:ChatGPT fails with complex constraints but it pretends it... by DoctorOW on Monday December 26, 2022 @07:45AM (#34137231)

With the exception of the ones specifically instructed, ChatGPT does not seem to respond with any acknowledgement that it can't do something. I was incredibly impressed by its ability to write a web scraping script for a specific website but when it reached the limits it would just write what it imagined is the correct solution.

[ Parent | on HN ]

Re:ChatGPT fails with complex constraints but it pretends it... by puntofisso on Monday December 26, 2022 @08:19AM (#34137396)

Indeed. The perception it gives is that it's fudging things up. I'm really interested in this because it will impact somehow the credibility it gets / the confidence it inspires in end users.

[ Parent | on HN ]