Nate Sutton
teaching machines about healthcare
I'm a pragmatic engineer with 10 years of experience building and operating data-driven systems from concept to production. I’ve built platforms from early ambiguity to product-market fit in highly regulated environments.
I live in the mountains of North Carolina and spend my off-hours shepherding 🐑.
2020 - 2026
2018 - 2023
2019 - 2020
Accelerated feature delivery from bi-weekly to daily releases by implementing continuous deployment for our database.
2017 - 2019
2015 - 2017
2026
Plenty of harnesses run local models now, and pi is a fantastic default for the same reason llama.cpp is: it works with everything. chad is moving the opposite direction.
1 set of silicon. This project is focused on making the macbook pro you already have usable. Not a $10K GPU.
1 capable model. Qwen 3.8 27B. This isn't the frontier, but you probably aren't solving frontier problems. Focus on 1 model buys speed. You'll experience ~ 30 tokens/second generation instead of ~ 10 tokens/second for stock llama.cpp implementations. This speed comes from MLX, targeted custom kernels for this model, and a bundled dflash2 drafter.
1 tightly-coupled agent loop. Instead of a stateless /completions endpoint, the agent loop in chad owns the backend process. This comes with nice advantages that make the KV cache more stable and the coding experience measurably better by avoiding long prefills at all costs.
2023
2022
2021
2018
Languages
SQL
Python
R
Platforms
Azure
AWS
Tools
Bash
Git
Docker
ML Frameworks
Pytorch
H2O
Domains
Machine Learning
Language
Time Series
Standards
HL7
FHIR
2018
Is conservation right to go big? Protected area size and conservation return-on-investment
2017
Factoring economic costs into conservation planning may not improve agreement over priorities for protection
2016
The grain of spatially referenced economic cost and biodiversity data and the effectiveness of a cost targeting strategy
2014
A reliance on agricultural land values in conservation planning alters the spatial distribution of priorities and overestimates the acquisition costs of protected areas