>I still occasionally hand write code in NeoVim on the bits I care the most about (CSS, design and early architecture like API patterns)

I find it amazing how people's opinions differ here. This is the first stuff I'd trust to Claude and co. because it is very much in-distribution for training data. Now if I had sensitive backend code or a framework/language/library that is pretty new or updated frequently, I'd be much more cautious about trusting LLMs or at least I would want to understand every bit of the code.

I think OP nailed it with 'the bits I care the most about'—if you like those things a certain way, then you'll want to make sure they are that way, not accept whatever Claude does. If you don't care, you just want something done, then you'll have Claude do it while you work on what you do care more about.

I think the main point is that LLMs are pretty good at following existing patterns and conventions.

If you setup your skeleton in a way it is familiar to you, reviewing new features afterwards is easier.

If you let the LLM start with the skeleton, they may use different patterns and in the long run it's harder to keep track of it.

> in-distribution for training data

Engineers are an opinionated bunch, safe to say at least a small chunk of us will disagree with what goes into the training pile.

For me, it's preferring Deno-style pinned imports vs traditional require() or even non-versioned ecmascript import syntax.