I use Claude Code every day on my main PC. It’s the tool I talk to when making apps for my family. It worked well without problems for several weeks. Then I wanted to use it on a second device. This is my daughter’s PC. Sometimes I work on her apps there. Same subscription, same account, everything was the same. I installed the VS Code extension and opened it. Then I saw this error: ...

My mother is eighty-seven. She lives in the countryside, by the Boseong River. She has never made an account for anything, never typed a password she chose herself, and she would not know what “the cloud” means. But tonight she is holding a Galaxy tablet, and on it she is watching her granddaughter — my daughter — as a newborn. Then at six months. Then last week. She taps a folder marked 2026, then July, and there is a video my wife shot this afternoon. ...

When you make software for yourself, ‘reliable’ is usually good enough. If it breaks, you can fix it yourself. You can log in with SSH, read the logs, and restart it. You are your own support team. But this server was not for me. I made it as a gift for an 80-year-old man. It holds his life lessons on a tablet in his living room. And one fact changes things: he cannot fix problems. Not because he isn’t smart. He is smart. But the moment a server in someone else’s home needs any technical help to keep running, it has already failed for a non-technical owner. ...

Let me tell you about the bug that made me doubt myself more than any other in this series. I’d fix something — say, a misheard word in a transcript. I’d save the corrected file to the server. I’d open the app on my phone to admire the fix. And the old, wrong word would still be sitting there. So I’d fix it again. Save again. Still wrong. I started to wonder if I’d forgotten how to edit a text file. ...

While working on this project, I had to transcribe and edit hundreds of audio files — 145 at first, later almost 400 — using a paid AI service. Each file cost real money. The whole job took hours, sometimes even overnight. If you’ve ever started a long task where each step costs money, you know the worry. Three problems can happen, and I ran into all three before I learned how to prepare for them. ...

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.” ...

In the post on search I gave you the clean version: type a word, get every place it was said, tap to jump to that moment. That’s true now. But I made it sound smooth, and for a while it wasn’t. The search had a bug that wore me down — and tracking it down taught me one of the more useful lessons in this series. The symptom was maddening. You’d search a word, see a result, tap “play from here” — and the audio would start playing twenty minutes before the word you searched for. The search found the right thing. It just sent you to the wrong place in the recording. Sometimes by seconds, sometimes by twenty whole minutes. ...

In an earlier post I turned hundreds of hours of recorded Bible teaching into text. AI transcription is good, but not perfect — it mishears words, especially names and rare terms. So the obvious next step was to ask a smart language model to clean up the mistakes. These models have basically read the whole Bible, so I figured fixing a few scripture typos would be easy for them. It wasn’t. And the way it failed taught me something that goes well beyond transcripts — to anyone using AI to correct text against a trusted source. ...

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. ...