Things I'm building and thinking about. A few are here, more coming soon.
How a proton beam makes the isotopes for cancer scans, why the target fluid can start to breathe on its own, and the model I built at TRIUMF to predict it.
Every body pulls on every other. One simple law, no tidy answer, and a live GPU simulation you can run in your browser.
Forecasting sounds simple, but real business data is messy. A tour of the real-world challenges that make time series forecasting hard: missing data, sparsity, volatility, external drivers, multiple seasonality, and hierarchy.
When generalization quietly costs you, the hidden tax of reaching for the abstraction too early.
Notes on agentic systems, edge ML, and recovering the hidden structure in messy real-world signal.