Writing
Long-form thinking on medicine, machine learning, and the space between them.
RSS Feed →Scientific & Clinical
Differential→
Reading the clinical AI literature carefully.
It Seems I've Struck a Nerve: Clinical AI Has a Measurement Problem and It Is Mostly Borne of Ignorance→
Why "nobody knows how to evaluate clinical AI" is largely false, what the existing methods already cover, and a free framework for atomized, fact based evals.
The State of Clinical AI: Scribes and an Argument from Induction on Why Frontier Labs Are Still Not Your Doctor→
Clinical AI right now is four buckets: scribes (which do a lot more than scribe now), decision support like OpenEvidence, a new breed where the AI takes part in the clinical decision (Doctronic's Utah pilot), and consumer health randos I don't count as healthcare.
Doctors in AI: What are we? What do we call ourself? WHAT HAVE THEY DONE TO US?!→
What is Clinical AI, anyway. A four-leg unicorn model (clinical, science, product, engineering), what each three-of-four archetype actually needs in structural support, and why I want the term to stay deliberately fuzzy and not get hollowed out the way Data Scientist did.
Life & Philosophy
How I Ended Up Here→
Decade-and-a-half from pop punk guitarist / bad MMA fighter / pizza delivery guy to Head of Clinical AI at Suki. Mostly luck and being early on a few things.