My experience has been polar opposite with GPT4. As long as I structure my thoughts and present it with what needs to be done - not like a product manager but like a development lead, it spits out stuff that works on first try. It also writes code with a lot of best practices baked in (like better error handling, comments, descriptive names, variable initialization).

Some times this presenting of problem to it means I spend anywhere from 5-10 mins actually writing the points down that describes the requirement - which would result in a working component/module (UI/backend).

We have been trialing GPT4 in my company and unfortunately almost everyone's experience is more on the lines of yours than mine. I know it shouldn't, but honestly it frustrates me a lot when I see people complain that it doesn't work :). It definitely works but it depends on the problem domain and inputs. Often people forget that it has no other context about the problem than just the input you are providing. It pays to be descriptive.