Comment by wahnfrieden

I personally use it for a lot of SwiftUI work. I parallelize it across at least 3 projects at once. I use only the largest models on highest thinking modes. I give instruction on implementation and provide reference implementations.

I also use it for adding features/feature polish that address user pain points but that I can't prioritize for my own manual work just yet. There are a variety of user requests which sometimes LLMs are able to get done very suddenly when I give it a shot quickly. For these tasks, it's ok to abandon & defer them if the LLM spins its wheels.