Notes on AI systems, financial infrastructure, and production ML. Updated as new pieces are finished.
A 2026 IEEE-accepted paper finally says the quiet part out loud — data leakage, illiquidity blindness, and the evaluation metrics nobody in academia reports.
An assumption baked into every forecasting model we build — and a February 2026 paper that formalises why it's wrong.
Why compliance and risk are the most underinvested, highest-leverage AI problem in global markets — and what the stack should actually look like.
What happens when you feed Soros's theory of reflexivity to frontier LLMs and test them on boom-bust cycles? A May 2026 arXiv paper ran the experiment across the dot-com bubble and the GFC.