Links I send people

Library

Pages I open myself and send to others: interactive explanations of how models work, playgrounds, roadmaps, guides on agents and evals, and the best material on tracking and estimation. Each has one line on what you will see or learn there.

LLM internals

See what happens inside a transformer, from tokens to the next-token probability.

Embeddings and retrieval

How text becomes vectors, how to look at those vectors, and how retrieval is built on them.

Agents and tools

Patterns, protocols and failure modes of LLM systems that call tools and act in loops.

Evals and benchmarks

How to measure whether an LLM product works, and what public benchmarks show.

ML intuition

Small models in the browser for building a feel for training, convolution and generation.

Explorable explanations

Essays where the figures are live and the reader runs the experiment.

Computer vision

Vision and detection foundations, plus the tooling used in practice.

Tracking and estimation

Kalman filters, multi-target tracking, and how trackers are scored.

Roadmaps and courses

Structured paths, from a first map of the field to building a model from scratch.

Writing worth following

People who publish careful, first-hand notes on building with ML and LLMs.

Every link was opened on 2026-09-26.