Here’s the plan I was sure would work: point an AI at a folder of thousands of mixed photos, give it a few pictures of my daughter, and let it pull out every photo of her automatically. No more manual sorting. It didn’t work. And the reason it didn’t work is interesting enough that I want to tell it straight, including the part where I was wrong. The Idea Face recognition is a solved problem, right? Phones do it. The plan was: ...
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: ...
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. ...
My wife listens to a Bible teacher every morning. After I built her an app to make that easier (the first post in this series), she asked for one more thing. It turned out to be the hardest part of the project. Could we also read his teachings, she said, not just hear them? Reading helps her study. She wanted the words on a screen. “Sure,” I thought. “I’ll just turn the audio into text.” How hard could it be? In 2026, turning speech into text is mostly a solved problem. ...
You’ve probably felt this. Someone mentions a technology — Cloudflare Tunnel, RAG, Termux, vector search — and a small door closes in your head. “That sounds powerful,” you think, “but it’s not for me. I’m not an engineer.” For most of my life, that feeling was right. Knowing the name of a technology got you almost nowhere. Between the name and a working result there were months of study, and a level of skill I was never going to reach. ...