Paika!

Working on the Presidential AI mentions made it obvious to me how good LLM agents (particularly Claude Code) were at doing operations.

2026 will see the industry roll out large-scale cloud agent orchestration systems at large companies.

Building on my LLM eval framework, I added a much harder test - build a three node distributed S3 cluster.

Recently I’ve been interested in Reinforcement Learning, particularly in evals - how do we measure language models’ effectiveness as agents?

Vibecoding, as popularized by Andrej Karpathy, is a tricky word.

Document Status: Back of the envelope math and my brainstorming.

Over the past month I’ve been doing a crash course on machine learning as I come up to speed on AI progress.

Recently I tried out the helix editor primarily because I’ve enjoyed neovim but found the lua plugin system annoying, and helix is written in Rust (my favorite language).

With Claude Opus 4.5, coding is effectively solved.

Try the demo here I was feeling ambitious after completing the MNIST training from scratch in Rust.