// archive

Every dispatch.

The full log, newest first. Tagged for quick navigation.

2026

May 24

Shipping a devblog with Claude Code and Linear

Why I use Linear for a one-person project, and how superpowers skills and git worktrees make Claude Code feel like a real teammate.

May 17

How modern LLMs are trained, end to end

Building a frontier large language model today is a three-act play: a massive pretraining phase that absorbs the internet, a post-training phase that turns the resulting "completer" into a helpful assistant, and an increasingly important reinforcement-learning-on-reasoning phase that teaches the model to think before answering.

May 17

Designing the design stage: a comprehensive synthesis for an LLM-driven architecture plugin

A practical playbook for the architecture/design stage of an LLM-driven SDLC plugin: what makes design artifacts good, a file-per-artifact schema that mirrors the requirements layer, a methodology-agnostic core (ISO 42010 + arc42 + C4 + MADR + SEI), and a multi-agent pipeline with deterministic validation gates.

May 17

The physical layer of the AI revolution

Training a frontier large language model is no longer a software problem — it is a construction problem. The binding constraints have shifted from chips to power, packaging, and grid interconnects, with transformer lead times stretching past three years and over half of planned 2026 US data-center capacity reportedly delayed by electrical-equipment shortages.

May 13

Designing an LLM-Driven Requirements Generator

How to build an LLM-powered requirements generator using EARS notation, ISO 25010:2023 NFR coverage, and a multi-agent generator/critic/formatter split that avoids the failure modes empirical studies now document.

May 13

Tokens, Tokenizers, and How Claude Counts Them

How subword tokenization algorithms work under the hood, why they shape context window economics and model accuracy, and what Claude's proprietary tokenizer changes mean for your API budget.

2025

Nov 06

Why your Claude Code agents need a BOUNDARIES.md

Three weeks fighting yes-man behavior, and the small architectural guardian that finally fixed it.

Oct 28

Building an MCP server for Godot: lessons from week one

Whole-project analysis, debug interpretation, and the parts I got wrong.

Oct 19

Configurable approval modes for background tasks

A YAML pattern for auto / review / approve workflows that scales beyond a single agent.

2020

Jan 01

Test Project Fixture

A fixture post for testing project filtering.