qourat ~ $

lab

Where a new kind of model gets a number on a real task before it gets a place in a product. Notes are written as we go and corrected in place.

System One models: what Jev is, what it is not, and what we measured

TypeSafe's Jev returns typed decisions with calibrated probabilities instead of text, in 70–500 ms, for $0.042 per million input tokens. We read the sources, called it, and wrote down what holds.

decide: typed decisions with honest probabilities, in our own small form

The same state-plus-questions interface as Jev, with two backends: Jev itself, and a local calibrated model trained on our own labels and reported with held-out numbers.

marketprice: the loop, the scoring, and what a good result would look like

Lab notes for marketprice.org: how the state is built, why Brier score, and the bar the model has to clear.