[tptacek]

It's funny because the part you find challenging is exactly the thing LLM skeptics tend to say accounts for almost none of the work (writing the code). I personally find that once my project is up on its legs and I'm in flow state, writing code is easy and pleasant, but one thing clear from this thread is everyone experiences programming a little differently.

[stavros]

Yeah, definitely. I do agree with the skeptics to a point, as I don't let the LLM write code without reviewing (it makes many mistakes that compound), but I'd still rather have it write a function, review and steer, have it write another, and so on, than write database models myself for the millionth time.

It's not that I find it hard, I've just done it so many times that it's boring. Maybe I should be solving different/harder problems, but I don't mind having the LLM write the code, and I'm doing what I like and I'm more productive than ever, so eh!

[tptacek]

I was just talking about this in a chat today, because 'simonw had at some point talked about getting to the point where he was letting go of reviewing every line of LLM code, and I am nowhere close to that point --- I'll take Claude's word on Tailwind classes as long as the HTML looks right, but actual code, I review line-by-line, token-by-token, and usually rewrite things, even if just for cosmetic reasons.

[vidarh]

I've had Claude write ~50+ commits of compiler code over the last week, and I've mostly not even read it yet. I will review the end result at some point, and I do spot checks, but for the most part I review whether or not the number of specs that passes is going the right way, and occasionally butt in when I glance over and spot it doing something silly.

I fully get why people won't trust it, but I'm leaning more and more on reigning it in with specs and tests and process, and then letting it run for extended amounts of time, and then giving it instructions to fix obvious issues, before finally reviewing the result, and letting it fix whatever comes up.

[stavros]

Yeah, there's a definite continuum for where LLMs are most to least expert. They seem to be fairly OK with JS, less so with Python, and C is just a crapshoot.

It depends on the project as well, for throwaway things I'm fine to just let it do whatever it wants, but for projects that I need to last more than a few days, I review everything.

[tptacek]

A friend of mine has been doing embedded C stuff (making some kind of LCD wall) and has been blown away by how well it's been doing with C --- he went in an LLM skeptic (I've been trying to sell him for months, it finally clicked).

[stavros]

Huh, interesting. I wanted to turn an old rotary phone into a meeting headset, and I tried to get Opus to make me a sound card, but $35 in API costs later, I had no sound card.