For a start, most of my work is about using internal APIs. But nevermind. Sometimes I come across a generic programming problem. ChatGPT get me to 80% of a solution.
Getting it from there to a 100% solution takes as long as doing it from scratch.
Just my $0.02
Even more common is getting shell/UNIX commands to do what I want. I don't have all the standard UNIX tools (cut, etc) in my head, and I definitely don't keep all the command line options in my head. GPT4 tells me what I need, and it's much quicker to confirm it via the --help or man pages than craft it myself by reading those pages.
Not something I relished spending days on. Instead I spent thirty seconds and our customers are getting a major update shipped a hell of a lot faster and I can get back to bigger things.
I had it write me a handful of sticky functions. The thought of using a search engine for all of that brought tears to my eyes.
Just searching simple things anymore is gut wrenching.
Some people could be not able to figure out that the code GPT produced is not good because they lack the skill level to review it efficiently.
Conversely, could you share an example of a nontrivial, practical programming problem ChatGPT can solve, but only if you use it right?
I'm a senior dev at a python shop and I almost never find the solutions GPT4 gives in Python to be very good. However, I've been learning some C# lately in my free time and I find those solutions to be pretty good. I have a feeling I find the C# solutions higher quality, because I'm not experienced enough to see the problems.
I would really like to know what I'm doing wrong (or if everyone else is in the same boat).