Projectsfive, across three tracks

Small, complete systems built to test what I think I understand.

Research arcs, tools, and interactive explainers. Each belongs to a track, and each has a page that says what it does, how it is built, and what I learned. Newest first.

All projects

Dated by when each one shipped.

2026·07 Bean Miles Six months of coffee, measured. I photographed 39 empty coffee bags, had LLM agents transcribe every label, and geocoded each journey: 360,761 km from farm, to roastery, to a cup in London. A 3D globe replays all six months, bag by bag. vision LLMsgeocodingglobe.gl Personal Intelligence 2026·06 LLMs in RecSys Can an LLM read behavior the way a recommender engineer reads a session? A six-part arc from prompt-based preference prediction and scaling laws to synthetic reasoning data, GRPO, generative recommenders, and a repo-backed LLM cross-encoder. LLMsMovieLenscross-encoder RecSys 2026·06 Stellar Evolution Every black hole begins as a breath of dust. An interactive, scroll-driven story of a star's whole life: gravitational collapse, the ten-million-year fusion truce, an iron core that can't burn, the supernova, and the three endings decided by mass alone. canvasJavaScriptinteractive Explorable Explanations 2026·05 Marginalia A conversational book recommender. Tell it a feeling, a question, a mood, and get back two or three books, chosen by a librarian-friend that builds a picture of your taste over time. Four personas, a prose taste portrait, and a theme constellation. PythonClaudeSQLite Personal Intelligence 2026·05 Instagram Strategist I gave Gemma 4 my Instagram reels. A two-stage multimodal pipeline that watches your reels, finds the through-line in your content, and tells you who you're really making things for. Strategy grounded in actual video, not generic advice. Gemma 4multimodalPython Personal Intelligence
Tracks

The longer questions each project belongs to.