Writing
Essays and notes on AI systems, agents, and the checks that keep them honest, newest first. The books are on their own page, and every piece is also under its topics. Follow new writing by RSS.
2026
- Voice typing on Wayland with a pair of EarPods
- A check that cannot look
- The colors a design system does not have
- Three ways coding agents draw a status bar
- A longer prompt is not a safer prompt
- Pranayama for everyday life
- Cloning my voice for an audiobook
- Operational workflow for AI coding
- Personal command language for AI
- Notation system for LLM prompts
- Personal OS with an AI agent
- What I built for multi-agent coding, and what survived