Tech Noir, Joy Division, and the Crushing Anxiety of Optimizing for Search Engines That Might Not Exist in Three Years

October 24, 2025 • 9 min read

On replacing Wilhelm with Unknown Pleasures, cultural anchoring vs keyword stuffing, and whether we're all just shouting into the void while ChatGPT eats our lunch. Also: footnotes.

Vibe-Coded Evals with LLM-as-a-Judge

Using Claude Code and OpenRouter infrastructure to rapidly build model evaluations with Claude Opus 4.5 as the judge

December 13, 2025

Why I Open-Sourced a Deterministic I-Ching Engine (Or: The Smallest Verifiable Compute You Can Build)

Extracting the deterministic core of 8-Bit Oracle into a standalone library, and why 'same seed, same hexagram, every time' matters more than you'd think for decentralized AI.

December 1, 2025

Testing Twelve AI Image Models with Marcel Proust's Madeleine (Or: How We Chose Hunyuan for Hexagram 24)

Upgrading 8-Bit Oracle's Hexagram 24: Return with Proust's famous involuntary memory scene, then systematically testing 12 diverse AI image models through fal.ai to find which one actually captures that precise moment when past and present collapse together.

November 18, 2025