Keep what works.
Throw the rest.
Essays on building durable systems in an age of disposable answers — and the tools that come out of writing them. Reality isn't a noun, it's a verb. The point was never the destination. It was always the becoming.
Trinity Local
Most ideas on this site ended up in a single product. This is the first one.
Your taste, ported.
Lives inside Claude Code, Codex CLI, Gemini CLI, and Cursor. No new app. No service. No API key. Your transcripts never leave your machine.
You've already chosen between Claude, Codex, and Gemini a thousand times. Trinity reads those transcripts, learns the pattern in how you rephrase, judge, and decide — then runs hard questions through all three in your voice and picks the answer you would have picked.
- Reads transcripts already on your disk
- Runs councils across all three labs
- Chairman picks the winner in your voice
- Every override trains the local router
- Cross-provider handoff in one command
- Embedding model + index stay local
The thinking behind the build
Four pieces on what becomes durable when AI commoditizes the rest. Each one named a principle that ended up load-bearing for Trinity.
Design the Affordance
It's a design problem, not a prediction problem. Behavior is not goal-driven — it's a structural affordance. The motivation industry is 70 years of symptom management. Six moves replace the entire incentive layer.
The Architecture of Becoming
The Builder's Trinity — grit, curiosity, simplicity — and why the goal was never a flawless foundation. The goal is distributed error correction. We want our theories to die in our place.
The Gravity of Becoming
Difficulty was never the point. Depth was. Time to Wow: under five seconds. Time to Mastery: infinity. In a world of flawless AI outputs, imperfection becomes proof of humanity.
The AI-Native Way
The Bitter Lesson, restated for builders. Rules and logic you write in code don't matter long-term. The only durable strategy is a systems-level data pipeline: find the edges, save the failures, finetune, repeat. That loop is the moat.
Utopia is a Mechanism
Democracy, science, free speech — not values, algorithms. Distributed error correction. Knowledge isn't a settled state of being right; it's the dynamic process of being less wrong. Utopia is not a destination; it's a mechanism.