Writing
Technical deep-dives, systems architecture, and essays on production agent evaluations.
- How Simple Grep Beats Naive SQL
I benchmarked bash vs SQLite FTS across 300k tokens. grep won: 29.6% cheaper ($2.45 vs $3.48), better accuracy. Here's why + the dataset.
- Three Lessons I've Learned at Manus
Lessons learnt from going from zero to $100M ARR in 8 months.
- Agentic Search
Models can't do much without the right context, agentic search does just that.
- Building a Coding CLI with React Ink
Migrating Our Coding Agent to React Ink.
- Building Reliable LLM Applications
How to build reliable LLM applications with structured outputs, synthetic data and binary metrics
- Simplify your LLM Evals
A practical guide to writing binary evals for subjective tasks
- Are your eval improvements just pure chance?
Grokking simple statistical analysis for LLM evals
- Write Stupid Evals
Keep it simple and worry about the rest later.
- You're probably not doing experiments right
How to get the results that you want from your LLM experiments
- How does Instructor work?
How your request goes from chat completion to validated Pydantic model.