I program as a hobby, personal projects because I can.

I recently set up a local llm to see what the fuss is about and other than the few ringer solutions my experience is as you described. 2min promping, 5min waiting, 3hrs debugging or just doing it myself.

I am very likely doing it wrong, and it does speed up some aspects, but I wouldn't say I trust llm code any more than my own. Until it runs and throws an error, the llm is 100% confident that it has written perfect code.

Why not just write the code yourself? To me it seems like methodically constructing the pull request by hand is probably faster than lazily prompting and re-prompting.

Felt that. I already gave DeepSeek the HTML and it still said the UI was good to go, then told me it has no vision.