Intelligence is water
/ 5 min read
Intelligence behaves like water. It presses on every surface it touches, passes through whatever opening exists, and takes the shape of its container, so the container sets the quality of what comes out.
Writing
Essays and lab notes on computational thinking and agentic systems.
Search that does not tire
/ 6 min read
An agent loop is a search algorithm: propose an action, carry it out, read the result, adjust. Retrying is the part of search that exhausts a person, and it is the part a machine gets at the price of a model call.
Shipping is merging
/ 6 min read
Agents made it nearly free to open parallel branches of work. A branch becomes progress only when its result is merged back into the one thing being built, and the merge is the step that did not get cheaper.
How to work with many agents
/ 7 min read
The mental models that scale one person from ten agents to a thousand: hold macrostates, not microstates, and converge everything into one trunk.
The agent body
/ 7 min read
Agent products all run on the same models, tools, and prompts, so the parts cannot explain why some improve and hold users while others stay demos. What separates them is the body: what persists between calls, where the boundary sits, and why the boundary is worth having.
Nothing grown in isolation survives transplant
/ 6 min read
Shipping speed and growth location look like one variable and are two: a team can launch every week while everything it builds grows against its own model of the market. Readiness is a product of contact with the destination, not a precondition for it.
What compounds in an agent system
/ 5 min read
In a blind comparison, a mid-tier model matched a frontier model on every dimension our tooling had encoded. The model is the part of an agent system to plan on replacing, and what compounds is the owned layer: the history, the verdicts, the encoded craft, and the standing it earns.
The value of the harness
/ 6 min read
A model in a chat window gives you drafts you still have to check. The same model inside a real pipeline produces finished work. This essay is about the harness, everything built around the model, and why each new model release multiplies whatever you have built there.
Silence is a signal
/ 5 min read
Most work an agent sends into the world gets no reply, and a bare no-reply teaches the system nothing. Splitting the outcome into stages, received, opened, clicked, answered, turns silence into an error signal the system can actually learn from.
Encoding judgment as rules
/ 6 min read
Most of a person's judgment can be written down, and the written form is what governs. Corrections recorded as rules reach thousands of runs the person never sees, and every review makes the rules more complete.
Ideas with bodies
/ 6 min read
An idea held in a head or a note cannot be found by a stranger, cannot take a payment, and cannot learn from silence. Agents have made it cheap to form the body an idea needs to meet its market, meaning an address, an inbox, an account, and records that persist.
The granular startup
/ 5 min read
Steve Blank called a startup a temporary organization searching for a repeatable business model, and nothing in the definition says how many people the search takes. When agents supply the labor the set of markets worth searching has to be recomputed, and at the limit the exploration of the markets startups ignore can itself be an automated process.