Fuck it, make it anyway

I spent hundreds of hours on this, so there is still some friction.

If I told you the exact market and use case, I'd still have a decent head start, but indeed, someone without a job could invest more time than I do. People in a cheaper location can work for far cheaper than I can afford to.

With head start I don't meant that the idea is so novel that I need to keep it a secret. However, I believe that if there is an established app that does the same thing, and your app cannot beat it on quality, it will be hard to attract users.

This resonates. Problem is, as time goes on, even in the hobby coding communities, all the of the tools you use - emulators, toolchain, utilities, code examples - the whole ecosystem will be developed using AI. At that point are you really doing it without AI?

The nuance here is that people aren't good at evaluating their own work/progress, and use recognition as a proxy milestone of their own improvement. No matter how good they get, they don't "feel" good until someone else (or many someones) comes and tells them "you're good"

> Idk folks, maybe it's because I actually don't like writing software as much as I thought I did. I'm realizing I actually like making products and creatively solving problems, and software is a mildly enjoyable means to and end for that. I also like many aspects of the job of programming (money, sitting on my ass, dictating much of my workday, feeling like a boss, also money, etc). I was lucky to be alive in a time when that role was in demand but I can now see that is coming to an end for at least 80% of us. Yes, probably you, and probably me.

Yep, this is what I realised. I like solving a problem/fixing something. I am not really interested in hooking up a Go/Python/C# web service to a database for the umpteenth time.

I've been partially vibe-coding a new desktop environment for Linux and creating my own UI framework. I know how UI frameworks generally work, and I know how desktop environments generally work. What I want to do is build a DE that works well and fits my vision of how it should work functionally.

I am reasonable at C++ (I don't do it professionally). Do I want to spend 20 hours doing a load of UI boilerplate code in C++? No, I don't. I am sure I can do it, I've written UI frameworks before in other languages. But I get the machine to do all the boring stuff, and I develop the product. If the code it starts churning out is crap, I have the ability to fix it.

There seems to be a lot of crap about not being able to code after using AI for a few months. This is rubbish. I used to code when I was a kid in BBC BASIC and didn't for years, I then started coding again in my early 20s and all of the stuff I learned came back to me, and I was programming in Java. Same recently, I didn't program for about 4 months and had to program without the AI as the AI couldn't solve what I was doing, and I was fine.

I'm with you. I've done some pretty special things over the years I was employed, none of which had any input from LLMs. Now I'm retired and I have a tool at my fingertips that I can instruct, manage, and (sometimes eventually) get what I want. It's not massively dissimilar to managing a group of engineers...

The inspiration, the ideas, the workflow, the vision, the end product - all mine. The grunt work that takes all the time - hand it off to the LLM, and make sure it bloody works at the end.

With that approach, I built a compiler for my own language - it runs on {Mac, Linux, Windows} and any of those can produce code for {Mac, Linux, Windows, WASM, iOS, Android, Zynq, m68k, 6502} - the last 3 being more useful to me than most people I expect. I have a signed binary running on my phone, which was developed on a Linux box and never saw anything from an Apple Xcode installation...

That compiler was how I (and Claude) wrote a WASM client to a server back end, all of which use the exact same classes and data formats, making integration trivial.

I'm working on a cross-platform UI framework now, with a Cocoa-like UI description, that you drag lines between your code and the various UI platforms you want to support {Desktop, tablet, phone}, with mobile variants offering portrait and landscape. Write your actual program logic once, and visually connect UI into it, on a target-by-target basis. Support any platform with one codebase.

I wouldn't have considered taking on a program of this complexity without the LLM. It'd just have been a pipe-dream. They're tools. Wonderful tools, but still tools.