Latest writing, page 2
-
Personal OS with an AI agent
What if your AI assistant wasn’t just a chatbot you open when you need something, but a persistent daemon running your life’s operating system?
-
What I built for multi-agent coding, and what survived
In January 2026 I wired eight layers of coordination infrastructure around a codebase so that several coding agents could work on it at once. By May I was running one agent, one pull request per session, and most of the eight were gone. This is what each layer was for, which parts I still use, and why the rest went.
-
The mind has parts, and you can watch them
The emotion arrives before the thought. The fear is there first; the sentences the mind produces afterward are its explanation for a fear it already has. Most people get this backwards, and the oldest model of the mind I know of gets it right, which is the reason I use it.
-
The biases I actually catch myself in
I used to keep a long list of cognitive biases, the kind that reads like a textbook index. It was useless. The ones below are the handful I actually catch myself in, week after week, when I’m building systems or making calls I can’t easily undo. Short list, real stakes.