Archive

Every published note, link, TIL, and post, in reverse chronological order.

2026

  1. Apparently 32 PRs a Week Was Conservative post
  2. My Day Job Is Unsupervising Agents post
  3. A Frustrating AI Code Smell: Every Problem Decomposes to a dataclass With Four Reasons post
  4. Completely Impractical but Delightful: An E-Reader Attached to My Phone post
  5. If AI Coding Trends Continue, I’ll Be Merging 20 PRs a Day post
  6. I Put My Dog in My Coding Agent post
  7. Dogfooding Is the New Code Review link
  8. An Update on Codex's Gremlins post
  9. There are Gremlins lurking in Codex GPT-5.5 link
  10. The Shiny Object Trap post
  11. Karpathy's LLM wiki looked familiar. Here's how to bootstrap your own in 5 minutes. post
  12. Rummaging through Claude Code's spring cleaning closet post
  13. It shouldn't take 50,000 buttons to format a bulleted list note
  14. It takes 7,500 tests, 12 languages, and 3 browsers to make text wrap around a circle post
  15. Agent-Friendly CLI Design link
  16. LLMs Are Cowboy Coding link
  17. Don't RAG Until You Have To note
  18. ML Monitoring: Keep It Simple, Keep It Compounding post
  19. Ruining the Fun of March Madness by Having AI Fill Out My Bracket post
  20. Brandolini's Law Is Flipping note
  21. Don't Replace Your Job, Replace Your Chores post
  22. "The CLI is Dead" note
  23. My AI Dev Flow in 10 Bullet Points note
  24. Agents Only Need Four Tools note
  25. Notes on Self-Hosting LLMs (Early 2026) post

2025

  1. Muon: The Magic of Three Numbers Making GPUs Go Brrr link
  2. How Claude Code actually uses CLAUDE.md files link
  3. Homelab Update: The Paternity Leave Edition post
  4. Firecrawl: A Simple Web Scraping Script note