Software engineering, applied AI, and machine learning

I build software and write about what I learn.

I've spent more than 20 years building software and roughly a decade working in ML and AI. I publish longer pieces here. Most of my day-to-day thinking happens on X, where I share working ideas and practical things I'm trying.

Matt Stockton
Software engineering

Experienced engineers still matter

Experienced engineers do not need to read every generated line, but their judgment still needs to shape the result.

Recent writing

All posts →

How I Use Modal

A tour of two practical Modal deployment patterns: cron jobs, secrets, volumes, static IPs, web apps, background AI jobs, and sandboxes, all in plain...

Experiments and conversations

All experiments →
Interactive reading

Pacing the Frontier

All 1,134 signatories and 70 comments on the Pacing the Frontier statement, explorable, with every figure computed from the source data.

Open the page →
Interactive talk

AI in Research Teams

Seven lessons about using AI in investment research, built as a single interactive page instead of a slide deck.

Open the page →
Interactive atlas

WattsOpen

An interactive atlas of U.S. fossil plants retiring through 2030, scored on how much room the grid around them has.

Explore WattsOpen ↗
Podcast

Deploying AI on the Buyside

A conversation with Brett Caughran and Khe Hy about moving from individual experiments to shared workflows.

Listen to the episode ↗

I do client work through PragmaNexus. Its site has services, case studies, and contact information.

Visit PragmaNexus →