Writing
Notes on getting modeling right: reproducibility, differentiable models, and machine-learning rigor.
2026
- tangent/suite: scientific computing in JavaScriptWhy JavaScript is a serious option for scientific computing, and how the seven modules of tangent/suite run statistics, Bayesian inference, and structural equation modeling in the browser, with nothing to install.
- How I destroyed my own modelI built an automatic mineral prospector, then tried to break it with strict space and time holdouts. It didn't survive, and that is the point. A look at why some exploration data quietly teaches models the wrong thing.