After burning nearly $20,000 in tokens, I used AI to rewrite a micro-poetry app from eleven years ago

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

English text is being prepared.

The space for a Lock Screen widget is very small, and the system renders it in monochrome, so all you have to work with is glyphs, font size, and whitespace. Making one or two lines of poetry still read comfortably in such a tiny space is something I've thought over again and again.

The new version of Weishi also includes a set of dynamic wallpapers: the landscapes are painted stroke by stroke. The effect I wanted was like watching someone paint on paper, not watching a visual effect—if it's too fast, the mood is gone, and if it's too slow, people lose patience. The balance lies entirely in a rhythm tuned little by little.

Many poems by the ancients were originally meant to be recited and sung. Reading only with the eyes always feels like something is missing. So in this version of Weishi, poems aren't only for silent reading—you can hear them read aloud (TTS), and you can also hear them sung. I made these tunes one by one with Suno.

The first time I heard a familiar poem turned into a song, I found that the words were still the same words, yet it seemed to have entered my heart in a different way.

"Painting in poetry" is an old saying, but this time I wanted poetry to truly "enter the painting." Every poem can be transformed into a painting, giving those lines you've read many times a form you can see.

As for the annotations and pinyin that users most often asked for back then, this time they're all built in. Every poem can show annotations and appreciation, and can also display pinyin. The day I finished this feature, I also thought of those early users. These features may have arrived ten years late, but at least they're not absent.

Every part of the new Weishi interface, I've done my best, by my own aesthetic sense, to make as good-looking as I can. It may not suit everyone's taste, but every font size and every bit of whitespace was carefully chosen by me.

Finally, Weishi is still free. It has been that way since ten years ago, and this time is no different.

AI builds the skeleton very quickly. Starting a SwiftUI project from scratch and straightening out the relationships among the data layer, the main app, and the widget extension—these tasks that "you know how to do but are tedious to carry out"—AI completes quickly and steadily.

It fills in the parts I'm not familiar with. After the end of 2016, my work focus shifted to server-side development and technical management, and along the way I missed many changes to iOS APIs. How to plan a WidgetKit timeline, what sizes and limitations Lock Screen widgets have—AI can quickly give a runnable starting point, and then I read the documentation and refine the details on that basis.

Of course, this help wasn't free, and the actual process wasn't smooth sailing either. Looking back, the truly difficult parts were different from what I had originally thought: getting AI to make something is actually not hard. An interface, a feature, an effect—once you explain it clearly, you soon see a version that runs. What's hard is making it fit your aesthetic sense, and deciding which features to keep and which to cut. In the end, it's taste and trade-offs.

Neither of these things has a standard answer, and neither can be explained in one go. You make a version, look at it, see it's wrong, tear it down; make another version, it's a little better, still not right, revise it again. You finish a feature, use it for a few days, feel it interferes with reading poetry, and remove it. A great deal of repetition and consumption is hidden in this back-and-forth. Most of the nearly $20,000 in tokens mentioned at the beginning was spent here.

Taste still has to come from yourself.

At this point, what I most want to say is: AI can help you make something, but what it turns out like is up to you. How large the text of a poem should be on the screen, how much line spacing to leave, whether to show punctuation, how many buttons should be on the page—AI can give "reasonable" answers to all these questions, but between "reasonable" and "good-looking" there are often many rounds of tearing down and starting over. Which version is right can only be found by looking again and again and revising again and again, until that little discomfort in your heart disappears.

In closing

Ten years ago, I was doing mobile development at a big company and wrote the first line of code for Weishi in my spare time; ten years later, still in my spare time, I rewrote it from scratch together with AI. In between came a startup, a failure, a career change, and many years of shelving it.

Nearly $20,000 in tokens, converted into any kind of return, probably isn't very worthwhile. But if I had to choose again, I would still do it this way. In a person's life, there should be at least one time when you seriously put effort into something you love.

Weishi is still a small app made by one person, and there are certainly still many things that aren't good enough. If you're willing to give it a try, I'd very much like to hear your feedback and suggestions.

Download link: App Store · Weishi (free)

> Follow Shaoshupai on Xiaohongshu and experience a wonderful digital life 🍃

> Practical, easy-to-use genuine software, presented to you by Shaoshupai 🚀 iOS arts and culture app recommendation App+1 Editor of this article:

English text is being prepared.

22 fellow readers have already charged