Blog

Writing

Thoughts on AI systems, engineering culture, and building things that work.

Feb 10, 2026 / 22 min read

I Forked 4 cli coding agents to Run the Same Model. The scaffolding explained a 2x gap.

Deep dive into the architecture of Codex, Gemini CLI, Mistral Vibe, and OpenCode. Same model, 2x performance gap — the scaffolding is what matters.

Feb 8, 2026 / 13 min read

I benchmarked 4 CLI coding agents on an NP-hard optimization problem I solved by hand 8 years ago. One of them beat me.

Claude Code, Codex, Gemini CLI, and Mistral tackle a fiber network optimization problem. Claude Code beat my 8-year-old C++ solution by 62 points.

Jan 2, 2026 / 3 min read

I Accidentally Rebuilt OpenHands From Scratch -- Here's What I Learned

Building omniagents, a ~2000-line Python framework for multi-tenant AI coding agents, only to discover OpenHands already existed. Lessons on agent architecture, isolation, persistence, and costs.

Nov 5, 2025 / 10 min read

Evaluate Your Own RAG: Why Best Practices Failed Us

We benchmarked our production RAG system across embedding models, chunk sizes, chunking strategies, and retrieval modes. The results contradicted common wisdom.

Sep 24, 2025 / 11 min read

PrediBench: Testing AI Models on Prediction Markets

A live benchmark that tests AI models' ability to predict real-world events through prediction markets. Every day, we let AI models bet $1 on top events from Polymarket.

Jun 1, 2025 / 1 min read

Engineering-as-Code Manifesto

We're brilliant engineers — yet we wrestle with Word docs, Excel sheets, endless email chains. Time to reclaim our craft.