* Replace MacBook with any high-end machine that requires a bunch of configuration for local dev.
And replace iPad with any thin client that’s much more portable and convenient, eg glasses that display a screen and Bluetooth keyboard. Why shouldn’t I be able to describe the changes I want to an LLM from a coffee shop?
We are certainly approaching the point where a high end MacBook Pro for development isn’t required. Feels very close to just being able to use an iPad? My current workplace deploy on Vercel, we already test actively on feature branches and the models have gotten so good that you can reliably just commit what they’ve done (with linting and type check hooks etc) and in the rare event something is broken, follow up with a new commit.
Interesting timing for me personally as I just switched from running Codex in multiple tabs in Cursor to Ghostty. It had nicer fonts by default, better tab switching that was consistent with the keyboard shortcut to switch to any tab on Mac, and it had native notifications that would ping when Codex had finished. Worktrees requiring manual configuration was probably the one sticking point, so definitely looking forward to this.
My collection of art, philosophy and poetry apps. They have previously just been on iOS but I just finished the Kotlin port of the art one, so will be releasing that soon.
The poetry one is react native. Art and philosophy ones are swift/kotlin. I wanted to see if you could use LLMs to effectively create a cross-platform app. The idea behind react native was that you write it once in an approachable language, then the framework compiles to native app code. In 2025, the approachable language you code in is English, and the LLM now generates native app code.
It was generally a success and I feel less of a need of the development overhead of react native these days.
Humble plug for my poetry app. When I was getting into poetry I was reading a lot of them online but found the majority of sites to have awful designs with garish ads that completely detracted from the poem. So I wrote a scraper which downloaded 40,000 poems that were in the public domain and rendered them in an iOS app with a beautiful design. Crafting individual profiles for all of the poets was painstaking and arduous, but the users seem to really enjoy the app so far. I do already have some AI analysis for arcane poems (but I don’t explicitly mention that it’s AI as I think apps should never say that - it doesn’t interest users, only investors).
You could make a similar argument for self-driving cars. We would have got there quicker if the roads were built from the ground up for automation. You can try to get the world on board to change how they do roads. Or make the computers adapt to any kind of road.