I agree with 5%. That said, I've found rubber duck debugging to be an exceptionally effective use case for ChatGPT. Often it will surprise me by pinpointing the solution outright, but I'll always be making progress by clarifying my own thinking.
841 karma · joined April 28, 2010
He starts with a sine wave and builds up abstractions until he has a Bach canon.
I've also been playing around with generative art, with mixed results. I find that I can implement some algorithms (e.g. flow fields) but then I run out of ideas for what to do next. I'm inspired by Tyler Hobbs' writings on the topic so I've been trying to recreate some of his pieces to see what I can learn.