Occasional notes on research, methodology, and the engineering that makes models usable.
28 July 2026
Placeholder note on probing vision–language representations — what lights up inside the model, and how far that is from a clinical explanation you can trust.
14 June 2026
Why coverage guarantees change what a model is allowed to say, and what breaks when the exchangeability assumption quietly fails on hospital data.
2 April 2026
Notes from PCCD and CAST on how much fabricated content you can remove at decoding time before you have to touch the weights.
20 January 2026
Quantization, operator fusion, and the unglamorous profiling work that separates a paper number from something a clinician can actually use live.
See all blogs →