I’ve stopped getting LLM to code and use it to spitball ideas, solutions etc to the issue.

This lets you get a solution plan done, with all the files and then you get to write the code.

Where I do let it code is in tests.

I write a first “good” passing test then ask it to create all the others bad input etc. saves a bunch of time and it can copy and paste faster then I can.

I'm experimenting with how to code w/ LLMs. I used an AI assistant for about a month w/ a React app, prompting it to do this & that, and I learned almost nothing in that month about React itself. Then I prompted it to tell me what to do, but I did the typing, and I learned quite a bit in a short period of time.

Why are you doing it? Direction from management? You think it's better code even though it's as you say less fun, and you're not sure if faster or not? Other?

At a minimum I write my own automated tests for LLM code (including browser automation) and think them through carefully. That always exposes some limitations to Claude's solutions, discovers errors, and lets you revisit it so you fully understand what you're generating.

Mostly LLMs do the first pass and I rewrite a lot of it with a much better higher level systems approach and "will the other devs on the team understand / reuse this".

I'd still prefer deciphering a lot of default overly-verbose LLM code to some of the crazy stuff that past devs have created by trying to be clever.

Have you tried Composer 1 from Cursor? It enables a totally different way of AI coding - instead of giving the LLM a long prompt and waiting minutes for it to finish, you give it a shorter prompt to just write one small thing and it finishes in seconds. There’s no interruption, you stay in the flow, and in control of what you’re building.