January 27, 2026
Architecting Reliable AI Agents for Production
What happens when your AI agent hallucinates a legal citation or a refund policy? Concrete ways to architect for reliability when deploying autonomous agents.
Thoughts on AI, engineering, and building things.
January 27, 2026
What happens when your AI agent hallucinates a legal citation or a refund policy? Concrete ways to architect for reliability when deploying autonomous agents.
January 20, 2026
A simplified answer to when knowledge graphs add value to RAG systems versus when they just add unnecessary complexity.
January 17, 2026
You might be asking 'can we build it?' but the real question is 'should we?' A cost breakdown of building vs subscribing to managed platforms.
January 5, 2026
Old ML techniques are finding new life with modern tooling. Curriculum learning - gradually increasing task difficulty - is proving valuable for training RL agents.
January 3, 2026
A structured approach to move your organization from unfocused AI initiatives to measurable business impact within 90 days.
January 10, 2024
Excited for the year ahead with my team Giovanni Superti-Furga and Josef Schenk!
July 18, 2022
My first experiments with DALL-E 2 - generating robot birds, renaissance cat paintings, and pizza sunsets.
January 10, 2020
How I sideloaded custom watch faces onto a Moto 360 paired with an iPhone by building a custom USB cable and using ADB.