I build AI systems: the models, the infrastructure underneath them, and the teams that ship them. This site is my workbench: essays and notes on AI engineering, software architecture, and the craft of making machines genuinely useful. Lately, that includes a long-running fascination with how machines understand people.
More about me here.
July 14, 2026 · 6 min read
In 2023, while everyone else wrapped GPT-4, our startup trained and shipped Nebula, a language model built for human conversation. What that decision actually cost, what it taught us, and how I would make it today.
June 18, 2026 · 6 min read
We measured how large language models pay attention to human dialogue versus web text, code, and math. Conversations turned out to be the domain models understand least on its own terms. Here is what we found, in plain English.
May 26, 2026 · 6 min read
I co-founded Symbl.ai in 2018 on a contrarian bet: that conversations are the most valuable data organizations have, and the hardest for machines to understand. Three eras, one acquisition, and one unchanged thesis later, here is what I know now.