
Gui Builds
Working notes on engineering, AI, and building useful systems.
Recent notes
Lately, I’ve watched a familiar arc: someone has a great idea, dumps it into a coding agent, and a few days later has a working product that leads nowhere. There are exceptions, of course. But the pattern makes sense.
I’m a little late to this, but this last World Cup brought back a nice memory. Back in 2010, a couple of months before the World Cup, I started working on an iPhone game. Not long before that, I got into iOS development. Back then, there were promises out there about developers waking up rich after publishing a calculator or toy app. I learned Objective-C from the Apple docs, bought a pretty expensive Mac mini, and started experimenting. I tried a to-do app, but didn’t like it; tried a drums game, but neither made my own bar. All from the simulator, because I didn’t have an iPhone at the time.
The feature worked.
My agent is mostly a very fast, non-lazy typer.
“I changed companies to escape one person.”