I had a go at building both a Mac and iOS dictation app the other day (dictator.robgough.net) thinking that with Claude's input, this probably wouldn't work... but it was a real problem I had, and I wanted to see how far we could get. Best way to learn the tools, right? I'd already spent the day playing with alternative apps that didn't quite do what I wanted.

The app itself is fairly straightforward, but it included some intermediate complexity in terms of audio capture and calling local models. Both something I'd never done, and as not-a-mac dev something I probably wouldn't have attempted for a side-project while I'm meant to be bootstrapping my own thing.

I didn't touch a line of code, and I was blown away. I'm so impressed in fact that I'm predicting we'll see a resurgence in native apps in the near future. By far the worst (and slowest) part of the process is having to deal with the App Store, and the ridiculous hoops you have to jump through to get past review.

With artificial intelligence, the nature of engineering is shifting, making competition much more intense than before. Therefore, we need to learn how to get the most out of AI. You can think of it like this: just as books were written by hand in the past, now AI is doing what printing presses used to do. But don't lose hope, because no printing press can be as creative as a human; it can only speed things up.

I'm have a game on both app stores, built in .net Maui. It earns enough to keep a roof over my head.

AI is useless when developing with Maui, as it's too new of a development framework for any AI's knowledgebase to have a clue what to do with it.

It is bad. Layoffs everywhere. Google is becoming apple. Companies want you to do the job of 6 engineers using ai.

The market is saturated for new apps.