Blog
Takes on AI and software. Subscribe (RSS)
- Six Models, One BundleSep 23, 2026 — Eleven weeks of building with FDF: how it changed my job, and why Fable 5.1 and Opus 5.5 made written specifications matter more, not less.
- The Attempt Got CheapSep 23, 2026 — GPT-6 Sol and Luna lead with cost per task instead of raw scores, and that moves the expensive part of agentic engineering from writing code to checking it.
- Three Years with AIJul 12, 2026 — How I went from pasting error messages into ChatGPT to making four AI agents write a fantasy novel — and why readers called it slop anyway.