Tw93 · Product engineer, open source creator, and writer

【2026-10-26】It has been a little over two months since I wrote the previous post, “From Mole CLI to Mole for Mac: What I Learned”. In that time Mole went from 1.13 all the way to 1.18, added AI tool cleanup and System Data cleanup, the Windows version shipped on the evening of October 14, and the GitHub repository quietly passed 72.9K stars.

【2026-10-22】Quite a few folks have been curious how I build Windows software on a Mac, and what stack Windows apps are usually built with these days. As it happens, I have been doing similar work recently, so here are some casual thoughts on choosing technology across multiple clients.

【2026-08-16】Lately I've piled up a lot of thoughts on indie development and wanted to pull them together, so this is the story of taking Mole from an open source CLI to a paid Mac app. What I was thinking at the time, and which parts actually turned out to matter.

【2026-06-07】In April I assembled a small robot dog. I posted a few clips on X while I was building it, so some of you probably saw the parts, the frame, and the final moment when it could hear a command, walk a couple of steps, and say a few lines back.

【2026-05-01】A few friends pinged me recently saying my open source tools were showing up when they asked AI questions. I hadn't done anything deliberate, so I figured: why not spend an hour structuring things properly? After doing it, I fired off a quick tweet, but the notes were messy. People seemed genuinely interested, so I decided to write it up as a proper article for reference.

【2026-04-26】Last month I ran an internal session walking product and business folks through how to get started with AI Coding. That deck eventually grew into this post. A lot of people get stuck at the very first step, the command line. Staring at a terminal that's just characters on a screen, they assume it's a programmer-only tool and they'll never figure it out. The bar is lower than it looks. If you can use a chatbot like ChatGPT, you can get going on Claude Code with a bit of time. The rest is just slowly getting comfortable handing the execution over to it.

【2026-04-06】Before AI, my way of learning was much more old school. I would read books, go through the blogs of well-known people in a field, both in China and outside China, and keep taking notes along the way. It was slow, but there was real joy in it. I still remember learning WebGL like that. Understanding it took me almost half a year of spare time, and I loved every bit of it.

【2026-04-03】After writing "The Claude Code You Don't Know" and "The AI Agents You Don't Know," I wanted to tackle a third installment. This time I pushed myself to work through how large model training actually works, and tried to write something that a non-specialist reader could follow.

【2026-03-30】My title reworks the name of a song by Omnipotent Youth Society that I loved twelve years ago. The song is about something different, but that feeling of watching a familiar world slowly get replaced does feel similar.

【2026-03-21】After studying Claude Code's architecture, I realized I still didn't understand agents well enough. Our team had already deployed agents in several projects, but I hadn't put that experience together. I went back through the literature, open-source implementations, and my own code to work through control flow, context engineering, tool design, memory, evaluation, and security.