For the last couple of years, I've been crafting and shipping a free app that Serves a particular narrow demographic. It works extremely well, but is a native iOS app (I don't write Android). When I first developed it, I worked with a professional graphic designer, and the app has a unique UX. In fact, with the latest release, I had to "walk back" a bit of the stuff the designer did, as I believe it interfered with usability. It's really a pretty intense app. There's a lot of moving parts. It handles user data, so I have to make sure it's secure and high-Quality.

Recently, a couple of very talented engineers vibe-coded a cross-platform app that is nowhere near as nice, but is highly effective at the most important aspects of the one I wrote. They are also very good at promoting, and it will get a lot of press. I have no doubt that many folks that would normally use the app I wrote, will use that.

At first, I was all mopey and emo about it, but I realized that it doesn't matter. Their app is decent. It's fairly ugly (LLM-generated UX is pretty bland), but works very well. The guys behind it, are good engineers, and I know that it will improve (although I doubt their UX will, much). Neither of them is a native iOS or Android developer, though. They are backend folks.

Instead, I'll be doubling down on making my app as good a native experience as possible. There's still a lot of stuff I can add, and Apple keeps adding more capabilities that afford native implementation.

I have also been using an LLM as a "trusted advisor," not as an employee. It's made a huge difference. It may end up eroding my "hands on" skills a bit, but not by that much. I find that I am constantly reviewing the work it does, and my knowledge helps me to really get the most out of it. I managed a software development team for a long time, so I am pretty familiar with delegating work to employees that are actually more capable than I am. I guess that helped me to accept LLMs, as an IC.

I'm basically looking forward to this. One of the reasons that many of my apps don't have a lot of new features, is because I never had the time to study and implement them (I refuse to add bad stuff. It needs to work well, so I am picky about what goes into my work). With an LLM, it looks like that is no longer an issue.

Have you considered setting up an agent environment like codex and having it work making on Android version for you? I know you said it's a very complex app and that probably makes it seem like it wouldn't be able to, but LLMs are really good when they have a very clearly defined end state to work toward, like an existing iOS app with code, screenshots etc.

I bet if you set Astra codex against this task on the $100 plan it would have it done at a speed that would shock you. Potentially even by the end of the day and mostly uninterrupted.

The SOTA models can reverse engineer whole codebases even from assembly now. If you have to specify with words what you want to do it's still hard but if you have a codebase to work from, you can pretty much arbitrarily convert apps and games into other languages / platforms now as if by transitive property.