2026-10-08
Every Step Was Correct and the System Still Broke
A year of bugs on my own site and services, sorted by how they were found. The expensive ones share a shape: no individual decision was wrong, nothing logged an error, and per-step review could not have caught any of them.
2026-08-14
The Oracle Protocol Measures a Problem Your Reranker Will Never Face
A reranker evaluated with the right answer guaranteed to be in the candidate set is being measured on a problem it never faces in deployment. What is left once you remove that guarantee is a ceiling set by retrieval, not by the reranker.
2026-07-29
Four Main-Track Acceptances in One Year: What Actually Worked
ICML, ECML PKDD, ICICS and ProbML in a single cycle — and the two habits that mattered more than any individual idea.
2026-07-28
I Audited My Own Website and Found DEBUG=True in Production
Six findings from running a real security audit against this site. The worst one had been live for months and was caused by a single misspelled environment variable.