ChatGPT fails with complex constraints but it pretends it complies with them
1–4 of 4 posts
Re: ChatGPT fails with complex constraints but it pretends it complies with them
#2Re: ChatGPT fails with complex constraints but it pretends it complies with them
#3I 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.
Re: ChatGPT fails with complex constraints but it pretends it complies with them
#4I 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.
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.