Wide ranging quantitative thinking - side projects, techniques, and observations on navigating uncertainty

Start Here

A few pieces worth reading first.

LLM Classification Is Feature Engineering

LLMs make good classifiers but even better features

September 13, 2026

How To Measure What You Can't Label

We don’t need no stinking negatives

August 26, 2026

Watermarking runif

I break down how to (invisibly) watermark a generative process

August 20, 2026

Pokemon Individual Recourse

Or how to be the most effective Pokemon trainer

August 15, 2026

All posts →

Powered by Buttondown.