The Lab
Soundness AI is my independent research lab focused on computational architectures, intelligent systems, and reliability by design. Its research explores how complex systems can remain secure, predictable, and useful even when individual components fail. This page collects the lab's announcements and progress updates.
Announcements
Seven Months In: Soundness AI Update
Seven months of Soundness AI. Putting a human in the loop is not enough to earn the trust critical work requires. 7 research and working papers, 14 provisional applications across 21 invention families, 30+ articles, and a large integrated trust prototype in development.
Two Months In: Independent Research Lab Update
The research program found its through-line: architecturally assured AI. Reliability as a structural property, not a compliance exercise.
One Month In: IRL (Independent Research Lab) Update
What an independent AI research lab actually looks like. Hardware, budget, what worked, what didn't.
The Essential Beauty of Abstracting Physical Experiments
Mashmeasure, the system I built in the Princeton lab in 2003. Experiments written in natural units while auto-discovered instrument shims enforced limits, rates, and safe operation. The deterministic execution layer agents still need.



