Research

Notes from building a verifier for finance.

Short, specific pieces on how institutional judgment becomes a signal a model can train against. We show the framework, not the recipe.

Methods

How a prompt's framing quietly answers its own question

Why the grammar of an eval stem can hand a model the shape of its answer, the five trigger families that do the leaking, and the one-word test that catches all of them.

June 1, 20266 min read