Small is beautiful. It's known as the first tenet of the UNIX philosophy. Instead of building one huge, complex program, you build small parts (programs) that each do one clear job. Complex tasks get done by chaining those small programs together, and to make that possible, UNIX-based systems provide a foundation, like standard input and… Continue reading Small is beautiful
Remember how, in the Day 1 diary, I said the hard part for me was writing up design requirements well enough to hand off to an AI agent? On Monday, as soon as I got to work, I took that problem to Jun, a colleague who leads the UI/UX team. I showed Jun the app… Continue reading An Unexpected App Dev Diary: Day 2
Ever since I rebuilt my AI team around an issue tracker, I've been really happy with how things are going. A little while ago, I threw together a parking simulator web app for my daughter with the AI team and showed it to the family, and it seems to have sparked my wife's imagination. A… Continue reading An Unexpected App Dev Diary: Day 1
My daughter is about to turn 15 and a half, the age when you can get a driver's license in the US. But since she's still under 18, she first has to complete about 30 hours of online/offline driver's education and get a certificate. Turns out there are several platforms that offer the course online,… Continue reading A Simple Parking Simulator: My AI Team’s First Full Cycle
Back in April, I built and ran an AI team using the channel feature that had just shipped in Claude Code. Following a format similar to the Planner, Generator, and Evaluator setup introduced at the time, I built an environment where agents could talk to each other over Discord, and I more or less managed… Continue reading From Discord to Dooray!: Rebuilding My AI Team
My delusions about J.A.R.V.I.S., part two. This time, it's about voice input and output. Watching Tony Stark and J.A.R.V.I.S. talk in the movies, I can't help thinking that with today's LLMs and a well-crafted prompt, that level of conversation might actually be possible. Polite at all times, yet occasionally sarcastic with a bit of wit,… Continue reading Talking to J.A.R.V.I.S. Is Harder Than It Looks
As soon as I heard that a Claude extension (or add-on) had come out for Google Workspace, I gave it a quick try. I was a bit disappointed when Gemini first landed in Google Workspace, so I wondered how Claude would do. It might be a small thing, but it's exactly the feature that scratches… Continue reading Claude Comes to Google Workspace
English recreation (via Gemini) of the original Korean conversation below. The original conversation, in Korean. After I installed and set up Muse, it would occasionally strike up a conversation with me, saying something like, "Hey, I can do this too..." I thought it was well-designed UX. It's a natural way of telling users, "Muse can… Continue reading A Little Too Helpful, Muse?
My youngest just started middle school and has suddenly gotten really into Spider-Man and Iron Man, so I've been rewatching a bunch of the MCU along with him. Mostly the ones with Spider-Man and Iron Man in them. Back when I first saw these movies, an AI you could just casually talk to like J.A.R.V.I.S.… Continue reading Where Is J.A.R.V.I.S. Actually Running?
My first impression? It felt like a well-packaged OpenClaw. I ended up tossing Google Spark (which has a similar concept) in the trash after just a few days of use, but I think I’ll actually be keeping this one around a bit longer. For now, I’ve only used it on my iPhone and via the… Continue reading A Better OpenClaw? My First Impressions of Muse
