|
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 5,901+ iOS/macOS developers using Codex and agents to build and ship apps. Expect practical tutorials, repeatable workflows, and hard-earned lessons from 7 shipped apps and time at Apple, Microsoft, and GoPro.
Hey Reader, Agents write better code when they can read docs instead of guessing from memory. A 2026 paper found up to a 20% improvement in first-try code accuracy when models were given the right programming context. So what do you do with that? Don’t rely on the agent to know everything from their training set. Instead, provide tools or local docs that they can reference. Your local docs should include sample code so agents can use the code correctly (the first time). If you’ve ever read...
Hey Reader, My iOS and macOS app development workflow has changed since my last GPT-5.2 Workflow video. GPT-5.4 lets me iterate on bug fixes, features, and ideas much faster than before. Watch: How I Build Apps with Codex and GPT-5.4 If you want to build apps with agents, use my app-creator skill. It can scaffold a new Xcode project and teach your agent how to create a Makefile for an existing Xcode project. 2 Tactics You Can Steal #1 Use a Learnings.md File with Your Agent Self-improvement...
Hey Reader, I’m launching early access for my new app-creator agent skill for iOS/macOS apps today! In this email: 2 Tactics You Can Steal This Weekend 5 Resources and Links Community Spotlight What does app development look like in 2026? Coding has forever changed over the last 3 months. I’m all-in on app development with Codex 5.3. It’s a workhorse. If you’re an idea person still learning the basics, you have a huge opportunity. Gone are the days when you need to know every line of code....