Skip to content
A marbled blue and teal ring with three eyelets on each side. A cord runs from each eyelet to a small shuttle on a sled, three to the left and three to the right, and each shuttle carries a different tool: a fin blade, a gear, a cutter, a hook, a stack of discs and a stepped block.A marbled blue and teal ring with three eyelets on each side. A cord runs from each eyelet to a small shuttle on a sled, three to the left and three to the right, and each shuttle carries a different tool: a fin blade, a gear, a cutter, a hook, a stack of discs and a stepped block.

The Conductor’s Ring

Engraved enamel, steel and cord · 2026

This is how I build now. One ring at the center holds six instruments, each by its own thread, and each does different work: they carve, turn, cut and stack, and they come from different makers. The single copper pin on the ring is the human part, the point of intent that tells all six what to make.

Blog

Field notes on building with super intelligence

  1. Are 100x Productivity Gains Really Possible With Multi-Agent Workflows?

    My commit count went from about ten a day to nearly a thousand on my busiest day. Here is what the studies, the vendors, the companies and the practitioners actually show about AI productivity, and what a 100x claim can and cannot mean yet.

  2. How Many Companies are Actually Using a Software Factory?

    Agent-written pull requests are mainstream. An agent-run software factory is a different thing. Here is what the public evidence measures, a transparent estimate of companies, and the gap between coding and delivery.

  3. Human Intelligence is Not the Ceiling, But the Floor for AI

    Many people assume AI trained on human data can at best match us. I argue the opposite: human data gets AI to roughly human level, then search, self-play, reinforcement learning against verifiable outcomes, tools and scale take it past, and nothing obvious stops it there.

  4. How I Merged 141 Pull Requests in One Day

    On Saturday, November 14, I created 145 pull requests and merged 141 across four repositories, all by directing teams of AI agents. Here are the numbers, the workflow that ran that day, what I did, and what comes next.

  5. Verification Is the New Programming

    AI agents now match senior engineers on a large share of well-specified work. The engineer's job moves from writing code to writing the verification and the deterministic workflow that make agent output trustworthy.

  6. Delegate All Your Grunt Work to AI Agents

    A year ago AI couldn't reliably operate a computer. Now it can, and it already wrote code. Three new agent products prove the change. Have you delegated all of your grunt work yet?

  7. Industrial Revolution 2.0: The One-Person Factory

    Factories made workers more productive by combining machines with divided labor, and corporations coordinated mills across cities. AI may put a whole factory under one person's direction. Here is what the evidence shows, what it doesn't, and who gets the gains.

  8. Rent the Factory or Own It?

    What Factory buying HumanLayer means for every team building with agent swarms. You can rent a software factory or own one, and the difference shows up the day your vendor is acquired.

  9. Thirty Days of Watching the Singularity

    For 30 days, Singularity Watch recorded the news with sources. AI re-proved Fermat in Lean in under 29 hours, came to lead a quarter of Anthropic's research and launched an IPO. Here are the month's ten defining moments, the pattern under them and five predictions to grade at Day 60.

Follow

Watch the factory get faster.

I publish the numbers as my SI agents improve, including the ones that fall short. Get each post by feed or email.

Get new posts