I’m in the middle. I use paid models. It’s great for scripts, reminding me of commands, and surprisingly good at debugging error messages. But if I’m working in our main code base I’m basically never able to just use the code it spits out. It can get me in the ballpark of what I want, but it often does weird convoluted shit on the first pass. I can keep prompting to refine the code down to something closer to what I want, but at that point it would have just been faster to write the thing myself.
I kind of like LLMs for learning new languages. Claude or ChatGPT are good for asking questions. But copilot really stunts learning for me. I find nothing really sticks in my brain when I have copilot running. I feel like I just turn my brain off, which seems kind of dangerous to me in the long run.
