In an earlier post I described cloning an app — copying the audio player I’d built onto a tablet to give away. That was a copy: same content, same speaker, a second home. This post is about a step further. I took that same engine and pointed it at a different speaker, and then at a different kind of media — and it just worked. Each time, what should have been “build a whole new app” turned out to be “feed the engine something new.” ...
I save every prompt I type when I’m building something. I started doing it long before this blog, for a dull reason: I forget what I did, and the log helps me pick things back up. Going back through one of those logs recently, I found a session worth sharing. It’s closer to what building with AI actually feels like than a clean demo is. The demos show you the good moment. You describe what you want, and a working app appears. That does happen, and it’s real. But most of the work isn’t that. A lot of it is more like this: a task that looked easy, and an AI that got it wrong a few times before we sorted it out. ...
Every time I type a prompt that actually matters — one that solved a real problem or unlocked something I didn’t know how to do — I prefix it with //. That double slash is a convention I made up. It tells my Claude Code hook: this one is worth keeping. The hook saves it to a file. Eventually I want those files to feed an app that writes blog drafts automatically. That is the plan for episode 20 of this series. ...
I thought I was done. The tablet was in his hands. The ownership was his — his domain, his account, his server. A lifetime of teaching, gathered and searchable. I’d built a legacy and given it away. The end. And then, at that very handover, the eighty-year-old man told me what was missing. There were teachings, he said, that we didn’t have — recordings that belonged in his life’s work but weren’t in our collection. He knew, because it’s his life’s work, and no one knows it better than the man who lived it. So the “finished” gift wasn’t finished. The tablet is back on my desk right now, plugged in, getting its update. On Sunday I hand it back: Version 2.0. ...
Everything in this series so far — the app, the tablet, Termux, the transcription, the search — was really the how. This post is the why. And the why is a person. He is eighty this year. For decades he has studied the Bible and explained it to others, twice a week, online, asking nothing in return. He once told his listeners that you shouldn’t walk out your front door in the morning before you read the Bible. That’s the kind of man he is. He gives people their daily bread, every day, and then steps out of the way. ...
I built an audio app once. Then I built the same app again — and the second time took an afternoon. Not because I’m fast. Because I didn’t really build it again. I cloned it. I took the thing I already had, copied it onto a different machine, pointed it at a different home, and turned it on. That sounds ordinary until you notice you can’t do it with the apps you use every day. You can’t clone Netflix onto a relative’s device. You can’t copy your Spotify and hand it to a friend. The big apps are sealed boxes you rent access to. But software you build is yours, which means you can make copies of it the way you’d copy a key. ...
My daughter is three. She loves one specific playlist of Korean children’s songs, and she likes it best when it plays from a small JBL Bluetooth speaker tucked under her stroller. We walk the neighborhood for about an hour most evenings. I put on her folder, the first song starts, and we go. Thirty seconds later, my phone screen goes off. One more song plays. Then it stops. I have to unlock the phone, tap the next song, put the phone back in my pocket, and keep walking. A minute later, same thing. ...
A pile of audio is a black box. You know the teacher said something about a certain verse. You can almost hear it. But it’s somewhere inside hundreds of hours of recordings, in one lecture out of hundreds, at a point you can’t remember. Without a way to search, those recordings are write-only: you can keep adding to them, but you can never really get anything back out. The bigger the collection grows, the more it buries. ...
My daughter is three. My phone takes about 6,000 photos and videos a year — maybe more. I don’t have 6,000 interesting shots. Most of it is accidental taps, blurry motion, seventeen near-identical photos of the same bread I was about to eat. But somewhere in that pile are the clips I actually care about: her first steps, her laughing at something she found hilarious at the time, moments my wife and I know we’ll want to see again when she’s older. ...
My phone has backed up about six thousand photos and videos from 2025 alone. On my PC, I run a local browser tool — pick_yeju.py — that lets me scroll through them, pick the ones worth keeping, and copy them into my daughter’s media library on our NAS. The files are sorted oldest-first. Six thousand of them. That’s about ninety pages at sixty per page. The problem: every time I restarted the tool, it opened at page one. I’d have to scroll back through to wherever I’d left off the previous session. Ten, twenty, thirty pages — just to find my place again. ...