|
It'll take some time, but I have some early thoughts in the video below . . . Watch my live demo with each of these new tools. It's unedited, so you'll see exactly how I work, and all the failure points. (Spider warning ... I show off my spider apps in this video) I cover:
This video is my first time using all of these new tools. I didn't plan anything other than trying to see if AI can solve this one tricky prompt. You'll see exactly what happens as we wait for code and test it live. Want to learn with me on a weekly basis and finally publish your app on the App Store? Join the waitlist for the App Launch Community here (ETA: January 2026). I'll be showing what works and helping people in the community make huge progress towards their app goals. Join the waitlist if you want to learn how to sell a product and earn side income. Danergous Spider App I'm working on a dangerous spider app using Machine Learning (ML). If you're interested in learning about spiders, Core ML, Create ML, image classifiers, or image detectors, I can send you the beta. Want to try the spider app beta? Reply and I'll send you the TestFlight beta invite. I'm using AI to build all of these tools:
Codex is great for prototyping. It's way better than Claude Code (which is why you don't see that in the video). I used to use Claude Max, but stopped after it became super frustrating to use. (It lies about doing work or tests, so I can't trust it to finish tasks without babysitting 100%). Codex is more truthful and honest (not always, but overall). Create ML - Machine Learning Create ML is the training tool I'm using to create my initial MVP image classifiers and object detectors. It's Apple's harness for building intelligence into your apps. At some point that may change, but it's a great visual starting point. You can write your own training code in Swift when you need more control (which I imagine I'll be doing soon). In the image above you can see a simple Object Detector model I trained on 914 spider images that I annotated with RectLabel (macOS). I plan to train a new model on 10,000+ images in the near future to improve accuracy. Talk to you soon, Paul Solt |
Join 5,712+ developers learning iPhone app development and App Store publishing. Every week, I share iOS tips on how to create polished, intuitive apps—backed by insights from shipping seven apps and working at GoPro, Apple, and Microsoft.
Hey Reader, AI agents struggle with iOS development for a simple reason: they can’t actually run Xcode. In this video, I have an impromptu conversation with Cameron Cooke from the UK about XcodeBuildMCP, a tool that finally lets AI build and run iOS apps in the Simulator. We talk through the backstory, the real problems it solves, and why this changes how AI agents work with iOS and macOS apps. If AI + Xcode is Broken for you, then you might need this tool. Watch here: AI Couldn’t Run My iOS...
Hey Reader, New Codex models are incredibly good for Swift code for iOS/macOS apps. You can easily install codex via here Just open Terminal/Ghostty and type: npm i -g @openai/codex Using codex, you can use simple language to talk to your agent. See the first video if you want a breakdown on the tools I am using, and some of the rules in my agents.md rule file. Spider Warning: if you're afraid of spiders, you won't want to watch these videos. I am making a dangerous spider identification app,...
Hey Reader, New video on my workflow for building iOS and macOS apps. GPT 5.2 is insane. It fixed so many problems the first time. Less back and forth from any other model to date. You can fly way faster from idea to prototype in minutes. It's beyond crazy. In a day I can have a working app that solves a key problem.I could never code this fast without AI. It let's you try ideas that you would never consider before due to time constraints.Codex + Xcode: 3 Workflows You Need for iOS/macOS...