Archive.
Writing about software, AI, and running a business. What to build, which ideas to pursue, and what I learn along the way.
All articles
-
The Job I Want Next
The job I want next combines software engineering, business judgment, and responsibility for the outcome, alongside a founder, investor, or business leader.
-
TurnKit: AI Orchestration for Ruby
TurnKit is a RubyGem for durable AI agents in Ruby, with agents, turns, system prompts, tools, skills, sub-agents, and Rails persistence.
-
The Shokunin in the Age of AI
AI made it almost free to look like a craftsperson. The Japanese idea of shokunin, lifelong devotion to a craft, is more useful now than it has ever been.
-
AI Slop Has a Place
AI slop is what you get when you let the model run without much wrangling. In R&D, that trade is often worth it: speed and cheap learning now, cleanup once the shape stops moving.
-
When Anyone Can Build, Judgment Wins
Engineering is no longer the hardest part of building software. The compounding hire now is a product thinker who chooses what to build, in what order, and why.
-
I Built a UI Kit - Just for Me
I built a private UI kit called Couch Kit so coding agents stop improvising my interfaces and I can ship consistent product UI without re-deciding every detail.
-
What Building an AI Orchestration Layer Taught Me About Prompting
I built an AI orchestration API and accidentally 10x'd my understanding of prompting.
-
No, Everyone Won't Build Their Own Software
VCs are betting everyone will build their own software. History suggests otherwise: better tools expand what builders can do, not who becomes a builder.
-
The Math of Weird Ideas: Understanding Asymmetric Bets
Most people confuse job risk with career risk. The safest-looking paths cap your upside. The weird paths? That's where the math gets interesting.
-
Ralph Wiggum Coding: Ship Features While You Sleep
Stop babysitting your AI coding agent. The Ralph Wiggum technique runs your agent in a loop until the work is done.
-
Weird Knowledge Compounds
True original thinking is rare. Not because it's hard, but because most people won't go where it lives.
-
RL (Reinforcement Learning) Explained in Plain English
You've heard 'reinforcement learning' dropped in every AI conversation. You've nodded along. Let's actually explain it.
-
Voice, Not Brand
After two decades online, I've stopped conflating 'having a voice' with 'building a brand.' They're not the same thing, and the difference matters.
-
LLM-Powered Idea Exploration: Prompting Techniques for Divergence, Analogies, and Tiny Experiments
At the starting line, you have almost nothing. Only a spark and a hunch. Here's how to use AI tools to explore ideas before you know if they'll work.