There is code which is interesting to write, even if it isn't the area with clever algorithms or big architecture decisions or something.

But there is also the area of boilerplate, where non-LLM-AI-based IDEs for a few decades already help a lot with templates and "smart" completion. Current AI systems widen that area.

The trouble with AI is when you are reaching the boundary of its capabilities. The trivial stuff it does well. For the complex stuff it fails spectacularly. In the in between you got to review carefully, which easily becomes less fun than simply writing by oneself.

> But there is also the area of boilerplate, where non-LLM-AI-based IDEs for a few decades already help a lot with templates and "smart" completion.

The thing for me is that AI writing the boilerplate feels like the brute force solution, compared to investing in better language and tooling design that may obviate the need for such boilerplate in the first place.

Yeah, but building tooling is a hard sell considering the ability of contemporary AI.

The energy cost is absurdly high for the result, but in current economics, where it's paid by investors not users, it's hidden. Will be interesting to see when AI companies got to the level where they have to make profits and how much optimisation there is to come ...

Rick Beato posted a video recently where he created a fictitious artist and a couple of songs based on a few prompts. The results were somewhat passable, generic indie/pop music but as he said (I'm paraphrasing) "I didn't create anything here. I prompted a computer to put together a bunch of words and melodies that it knew from what other people had written."

That's an interesting take - that you like the act of writing code. I think a lot of builders across a variety of areas feel this way. I like writing code too.

I've been experimenting with a toolchain in which I speak to text to agents, navigate the files with vim and autocomplete, and have Grok think through some math for me. It's pretty fun. I wonder if that will change to tuning agents to write code that go through that process in a semi-supervised manner will be fun? I don't know, but I'm open to the idea that as we progress I will find toolchains that bring me into flow as I build.

Yeah but I write the code that is interesting to solve and let the LLM solve the problems that are not so important. Like making yet another webscraper tool is not the most exciting part of the process when you are trying to make some kind of real time inference tool for what people post on the internet.

Most people don't enjoy their jobs and go to work for one reason only - to support themselves and their families. The itch is to get paid. This is as true in software as it is in other fields.

That's not to say there aren't vocations, or people in software who feel the way you do, but it's a tiny minority.

Ah yes, that "is that 6 spaces or 8" in a yaml file itch that just has to be scratched. Programming has a lot of doldrums. LLMs still get stuck at places, and that's just where the new itch to scratch is. Yeah, it's not the same as code golfing an algorithm really neatly into a few lines of really expressive C++, but things change and life goes on. Programming isn't the same as when it was on punch cards either.