Human-Driven AI Development Experiment Continues...

"Hey how well do you know mobile app development, particularly for iOS using Swift?”

That’s how my experiment started, andI’ve probably asked ChatGPT or a local LLM a version of this question a few dozen times or more, just to get an answer or an idea. This time around, I was considering an idea of guiding AI through development of a brand new version of my long-running mobile app.

It’s been going well for about a week and a half, but I think it’s super interesting that I can scroll all the way back up and see the whole conversation. So far it entirely fits within the context window, which means AI can reference not just earlier conversation, but earlier iterations of code and different files I’ve shared with it.

"I have a solid understanding of mobile app development, including iOS development using Swift. I can help with various aspects of the development process, such as setting up projects, UI design using SwiftUI or UIKit, managing app lifecycle, integrating APIs, handling data persistence, debugging, and deploying apps to the App Store. If you have specific questions or need assistance with a particular part of your iOS project, feel free to ask!"

Yesterday after posting an article about this project, ChatGPT and I worked through a tricky, complex HTML file to get the specific data to drive my user interface, then it wrote the user interface. All of this with unit tests to make sure nothing goes off the rails. It’s not perfect just yet, but its damn close!

Then I took the dog for his morning walk and got ready for my jobby-job (h/t to @CaseyLiss for embedding that silly term permanently in my brain), all by 9am.

I’m positive I’ll hit my July 15 ship date, but now I have a new idea, post-launch. I’m pretty sure I’ll stay under the full context window, so what if I export the full chat, drop it on a local LLM, and see what it can learn from reading how the sausage got made?

💡 – hey, is this the year I do a proper Android version of my app that’s not React Native? 

Pro-tip:

Don’t feel like you have to always chat with the model. Often the best way to make it understand something, whether it’s an alignment issue in your UI, warnings and errors in your IDE, or a feature from a previous version of your software, is to just take a screenshot and show it. You don’t even have to always explain it – it’ll figure it out on its own!