Modeling the Physical World
Andrew Diaz
Computer Vision + Prediction Infrastructure for the physical world.
"Trying to listen."
Computer Vision + Prediction Infrastructure for the physical world.
Andrew Diaz
"Retired. Now I'm doing what I love."
The Thesis
The physical world generates data that nobody is reading. A tennis player's split-step latency. A bakery customer's dwell time at the display case. A warehouse worker's route deviation. These signals are ambient, continuous, and invisible to most models trained on public datasets.
I studied electrical engineering — signal processing, the math of systems that sense and respond. A graduate course in computer system design taught me that every complex system is just a file system with well-defined interfaces. That principle scales: from operating systems to prediction pipelines to the physical world itself.
The same architecture extends everywhere. Sports is the proof of concept — the sharpest odds market in the world, the hardest place to find edge. If the pipeline works there, the machine learning is sound, and it works anywhere physical-world behavior generates signal. Restaurants. Retail. Logistics. Every venue is an unmonetized sensor network.
A deployed sports prediction model attracted $20K in external capital and returned +10% over two months — purely statistical, CatBoost on historical match data, no computer vision. Autonomous agent systems I've built — multi-agent workflows orchestrating parallel models, content engines, and decision pipelines — prove that one person with agent orchestration can now operate at the pace of a full engineering team. Different domains, same discipline: capture the signal nobody else is reading, automate the response, ship it.
The edge isn't better models. It's better data. Build the sensor.
B.S. Electrical Engineering, University of Florida
Analytics · Signal Processing · Machine Learning · Computer Systems
7 years professional poker · Applied probability
Backstory
I sold sodas out of my backpack in middle school and washed dishes professionally in high school. I've always wanted to do my own thing — hard things. I studied electrical engineering at the University of Florida, not because I wanted to be an engineer, but because technology is the present and the future, and I wanted to be literate enough to build what I saw in my head.
After college I played professional poker for seven years. Daily solver study, systematic opponent profiling, real money on every decision. That's where I learned to think in probability distributions.
Get in touch with Andrew →The Bets
I was an early investor in Solana in 2020 — turned a shoestring into a meaningful return, then watched most of it evaporate. That experience reinforced what the poker table had already taught me: finding an edge and keeping the money are two very different skills.
Now I build prediction systems. A sports model that deployed $20K in capital and returned +10% after 2 months of live real-money trading. A demand forecasting engine for a Colombian bakery — 179K transactions across 2.7 years of POS data, custom behavioral features, Two-Stage Hurdle Model. The same discipline, applied to different domains.
Sports is the proof of concept. Physical-world sensing is the market.
Where This Goes
The same discipline extends to every domain where humans generate unpriced signal.
// deployed_systems
STATUS: ALL SYSTEMS OPERATIONAL
CV Pipeline — Proprietary Data Manufacturing
Computer vision for extracting signals that don't exist in any dataset. CUDA-accelerated inference on local GPU hardware — extracting Table Proximity Index, Serve Toss Variance, and Split-Step Latency from free sports broadcasts. Proprietary data manufactured from public video for the cost of electricity.
The moat isn't the model. It's data that doesn't exist until you build the sensor.
Along Came Poly — Decision Engine
A decision engine that sizes positions under uncertainty. Currently deployed in sports prediction markets with live capital — Kelly Criterion bet-sizing, Bayesian updating, calibrated probability outputs. The framework is domain-agnostic: any domain where you can measure an edge and size a position. Sports was the first test case. It won't be the last.
Recursive Agentic Systems
Cross-project orchestration infrastructure that improves itself over time. Autonomous research loops that discover, synthesize, and distribute insights across every active project — sports prediction, demand forecasting, computer vision — without manual coordination. Inspired by Karpathy's recursive research methodology. The system that builds the builder.
The Infrastructure
Five-stage pipeline from raw sensor data to sized position. The same DAG processes sports telemetry today and retail biometrics tomorrow.
What I'm Exploring
"The first principle is that you must not fool yourself — and you are the easiest person to fool." — Richard Feynman
Let's build something at the frontier.
$ connect
ACCEPTING CONNECTIONS