Skip to content

/writing

// a record of judgment, not a chronological dump

// the thesis

The Gutenberg Moment for CodeDecember 3, 2025

Why LLMs compress the builder timeline and make reliable delivery discipline more important, not less.

Fire for the Rest of UsMay 23, 2026

Vibe coding gave developers AI leverage. I took the same principles out of the editor and into my own life and career, and the lessons transfer.

Why ADHD Brains Are Built for AI CodingFebruary 5, 2026

The one system I could never make reliable was my own ADHD brain. AI agents turned out to be the scaffolding I'd needed all along. Why the wiring that broke normal work is built for this one.

Convergent Architecture: Three Domains, One PrincipleFebruary 15, 2026

Infrastructure, software architecture, and agent systems converge on one rule: durable context matters more than disposable execution.

AgentOps Is Context OrchestrationFebruary 14, 2026

The reliable-agent problem is what context survives, loads, and guides the next execution.

The Knowledge Flywheel: How AI Teams Compound IntelligenceFebruary 12, 2026

How AI delivery gets safer over time: capture session learnings, promote what works, and inject context into the next run.

// method

12-Factor AgentOpsNovember 30, 2025
Spec-Driven Development: Why Your AI Agent Needs a BlueprintFebruary 12, 2026
The Validation Bottleneck: Why AI Output Quality Is the New CI/CDFebruary 12, 2026
Building vibe-check: 1,563 Lines I DeletedNovember 29, 2025

// devlogs

Devlog #1: What Running 8 Parallel AI Agents Taught MeJanuary 12, 2026
Devlog #2: How to Actually Use Your .claude/ DirectoryJanuary 15, 2026
Devlog #3: From Vibe Coder to Vibe EngineerJanuary 21, 2026
Devlog #4: Why Your AI Coding Specs Keep FailingJanuary 29, 2026
Devlog #5: When the Platform Catches UpFebruary 6, 2026

// personal pattern

From WoW Raids to AI AgentsNovember 30, 2025
Shadow Integration: What Gaming Taught Me About Reading AI OutputFebruary 12, 2026

// full archive (23)