An escalation ladder for LLM judgement
Batched mid-tier models make the calls, adversarial verifiers try to break them, and a human reads only the two places they disagreed. A cheap architecture f...
Recent Posts
What National Anthems Quietly Stopped Singing
I scored all 195 national anthems on how warlike they are, twice – the full official text against the verses people actually sing. Most countries have quietl...
Analytical Writing as Applied AI: a Method, Built From a Phone in Japan
A repeatable rubric-scored method for analytical blog posts – and what it means that I built the whole thing mobile-only with Claude Code, on holiday in Japa...
Password-Protected Drafts on a Static Site: StatiCrypt, Jekyll, and Honest Security Testing
How I added AES-encrypted preview posts to a GitHub Pages blog — with a 13-vector security test to prove it actually holds up.