Writing on AI
-
DHH's Campfire Benchmark Is Flawed, and Still Right
DHH had agents port Campfire to Elixir, Go and Rust. The Elixir numbers are wrong, the argument holds, and none of these languages is where this ends.
-
DHH at Rails World 2026: Agents, Rust and Why I Am Moving On
DHH's Rails World 2026 keynote put agents first and rebuilt HEY on Rust. What was claimed, what is unproven, and why my new work is moving to Rust and Elixir.
-
AI Automations Worth Building: Most Do Not Need AI
Which AI automations are worth paying for, when a scheduled job or scoring rule is better, and what evals, drift and review really cost in production.
-
How to Hire an AI Engineer Who Can Verify the Work
How to hire an AI engineer in 2026: interview for evaluation, failure handling, cost and latency discipline, not model names, cheerful demos, or empty claims.
-
Compound Engineering With Codex: Keeping Agents Honest
How I keep AI-assisted engineering from becoming a pile of plausible diffs: committed instructions, bounded specs, tests, reviews, and records left behind.
-
RAG vs Fine-Tuning: Choose the Right System for Work
A practical RAG vs fine-tuning decision guide that covers retrieval quality, retraining costs, and when a prompt with structured extraction is enough.
-
Tests as Contracts for AI Coding Agents in Production
Tests are the specification an AI coding agent can execute. Real import and audio-app examples show how narrow contracts make generated code stay honest.
-
OpenAI API Integration Checklist for Production Apps
A production checklist for OpenAI API features: strict response contracts, validation, failure paths, cost limits, versioned prompts and deploy-time evals.