Writing
Committed thinking — essays I’ve decided I mean.
Ideas
compound
in public.
Written to be
argued with.
Recently revisited
The Multi-Agent Moment
Follows Gas Town through Gas City into Wheelhouse, adds a section on multi-agent failure modes, and reconciles the piece with the org-chart and loop-engineering arguments as one axis: decision rights in space, persistence in time.
Pervasive AI: What Happens When Your Assistant Never Logs Off
Seven months later: what held up, what I got wrong, and where trust became the harder problem.
2026
The Model Is a Centroid Pump. So Is the Review Loop.
Sameness isn't one failure, it's two — a model's own training narrows what it's willing to produce before anyone reviews anything, and a review loop narrows what survives on top of that. Same pressure, two different rooms — and I've built something against both, though I don't yet know if either one actually holds.
The Org Chart Is the Missing Constraint
A Notion co-founder says everything he knew about coding agents six months ago was wrong. Most of what changed validates an older idea: constraints do the work, not agents — but at multi-agent scale, the constraint that matters most is who holds which decision rights.
The Loop You Were Already In
The interesting part is the fractal — tight loops inside medium loops inside long loops, each with different primitives and different levels of human involvement.
The Oracle Problem
Everyone wants to be the source of truth. Almost nobody builds the structural conditions that make truth survivable. From the Delphic Oracle to Grokipedia, the pattern is the same — and it has nothing to do with intent.
Defaults Are Decisions
Every system has defaults. AI makes them more powerful and more invisible. The question isn't whether your system is biased — it's whose assumptions it's running on.
What Are Test Scores Actually Worth?
I built a school data product for parents. What I built, how my thinking evolved, what an axiom actually is, and where the data runs out.
Your Infrastructure Spec Already Moved Into Your Code
Infrastructure config is collapsing into application code — the same pattern as build tooling a decade ago. Void showed us the destination. The question is whether you want to ride the platform or steal the pattern.
What's Left: Software Engineering in the Agent Era
When anyone can spin up a coding agent and ship something workable, what actually matters? Not the word soup — the real answer.
Your Vault, Your Rules: Password Managers, Sovereignty, and Agents
On the quiet ethos connecting Buttercup, Enpass, pass, and VeraCrypt — and why it matters more now that AI agents need your credentials too.
Pervasive AI: What Happens When Your Assistant Never Logs Off
Seven months ago I ran a personal AI agent on a Mac Mini for a month and wrote down what I saw. This is what held up, what didn't, and what a Meta product launch six days before I sat down to write this taught me about the difference between architecture and trust.
Raising Humans in an AI World
What do you teach a three-year-old when the ground is shifting under everyone's feet?
Why AI Can't Shop for You Yet
The properties that matter most in fashion aren't properties of the product — they're properties of the relationship between the product and the person. No protocol fixes that.
Convex and the Reactive Database Model
How Convex challenges our mental models of databases—not relational, not NoSQL, but something new.
When Do We Stop Talking About AI?
The specific exhaustion of a generation that can feel the stitch where human thinking and machine fluency got sewn together.
Photography as Interface
What camera mechanics teach us about designing for attention, perception, and control.
Why Everyone Should Have a SOUL.md
The case for documented identity in an AI-saturated world. Not just for agents — for humans too.
Rapid Generative Prototyping: Design in the Post-Figma Era
Design is no longer artifact creation—it's constraint architecture. The three-layer model for the agentic economy.
What Cameras Taught Me About Software (and Life)
The arc of creative tools: diverge to learn, converge to create. Why more gear made me worse, and what that means for building software.
The Multi-Agent Moment
A technical breakdown of multi-agent orchestration: Claude's Agent Teams, OpenAI's Agents SDK, Google Antigravity, Gas Town, Beads, and the community alternatives.
Design Physics: When Interfaces Meet Agents
Traditional UX has a hidden assumption: humans on both sides. That assumption is breaking.
The SaaSpocalypse
Anthropic wiped $285 billion off software stocks this week. The market is panicking about AI replacing tools. But the real disruption is what it means for the people who build them.
Code Owns Truth
We obsess over prompt engineering when we should obsess over constraint engineering. The prompt is a request. The constraints are the physics. The code is what ships.
Proof, Not Truth: Epistemic Humility in Knowledge Systems
We don't sell answers. We sell receipts. The receipts are what earn the right to call something true.
Self-Healing Systems: The Holographic Event Pattern
Every event must carry everything a repair bot needs to act without asking questions. Don't scatter breadcrumbs — ship holograms.
Hello World
First post. Why I built this blog and what I hope it becomes.