Archive

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

2026

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