Every prompt, you re-explain your taste. The references. The type stack. The lighting. The pace. The thing you reject. The fix: turn every reference you save into a structured paragraph you can paste. I save a video, a screenshot, or a saved webpage. Claude watches it once. The output is one markdown card with named fields: thesis, intent, operative moves, failure modes, tooling, voice, adjacencies, tags. Two card types: 1. Trend card. Someone else's reference. Names what the pattern IS. 2. DNA profile. Your own corpus. Names what YOU keep doing. Now every prompt starts with the matching card pasted in. The system carries my taste forward instead of my memory. The system around the AI is the intelligence. // A<3

What ICM, 60-30-10, and a lot of GitHub stalking taught me. Six weeks ago, I was using Claude to produce daily content artifacts — Instagram squares, captions, blog posts. A publishing operation with a workflow that mostly held together. Today, four public ICM-structured AI repositories live under github.com/NFTYoginis. Three more shipping this week. Each one is a fork-able starter that demonstrates a working architecture: orchestrator dispatches, workers build, briefs serve as contracts, memory persists across sessions. The path between those two states isn't "I learned to code." It's a six-week stretch of reading public repositories, trying patterns, deleting most of them, and slowly understanding what ICM (Internal Coherence Maximization, from Jake Van Clief) actually means when you stop treating it as theory. This is the tour: where I started, what changed, what I built, and where you can fork it. Where I started Six weeks ago, my Claude workflow looked like this: - One Claude session per task. Each session loaded brand-voice files, content samples, and whatever else seemed relevant. Context bloated by lunch. - I'd ask Claude to do something. It would produce something close. I'd correct it. Repeat. - "Memory" was telling Claude "remember our convention is X" at session start, which it forgot the next session. - The token bill kept growing without the output growing proportionally. That setup works at small scale. It collapses under any real production load. The collapse moment, when it came, was specific. I caught one of my daily routines burning roughly 800,000 tokens — for a routine that needed to do one thing: write three dispatch briefs and hand them off. The actual creative work happened in the workers being dispatched. The orchestrator was just routing. Eight hundred thousand tokens for routing. That was the first time I read about ICM. What ICM actually says (the part that mattered) Most "AI architecture" content I'd been reading was either too high-level to act on, or too tied to a specific framework I'd have to adopt wholesale.