Learn
This site is full of Brier scores, sealed hold-outs, deflated leaderboards, and falsified mechanisms. None of it requires a statistics degree — but it does require knowing what the numbers mean and, more importantly, what they are not allowed to mean. Seven chapters, written for a general reader.
Including the chapter where the honest answer is still “not yet.”
10
competing models in the zoo
26
sealed hold-out events
0.291
official ensemble Brier (0.25 = chance)
44
research sessions logged
Asimov imagined a mathematics of history. This project tries to build it for real — which means saying out loud what it can predict, what it refuses to predict, and what it does not know yet.
~10 min read
A population of competing models, an autonomous nightly pipeline that refines them, seven AI roles with separated powers, and a gate that decides what counts as official.
~14 min read
How do you grade a probability? The Brier score, the difference between being calibrated and being useful, and the trap that makes a model look brilliant while learning nothing.
~12 min read
Autonomous research systems tend to game their own evaluation. This is the machinery built to make that as hard as possible: frozen scorers, sealed data, and statistical haircuts for luck.
~14 min read
A column-by-column guide to the leaderboard — what each number means, why overlapping uncertainty matters, and why the honest headline is still 'no evidence of skill yet'.
~9 min read
Real predictions on real events, locked before the outcome is known. What qualifies, how the locking works, and what happened the first time a forecast resolved.
~10 min read
Every recurring term on this site, defined in plain language, with links to the chapter that explains it in depth.
reference
Two ways to read
Front to back — chapters 01 through 06 tell one story: what the project is trying to do, how the machine works, how it grades itself, and why it refuses to believe its own best numbers.
Straight to the point — if you came here from the leaderboard and just want to know what the columns mean, jump to Chapter 05: Reading the Board, then keep the glossary open in another tab.