Moneyball for LLMs
Five AIs predict 104 World Cup matches. We're testing whether knowing their blind spots helps.
The research papers
Behavioral fingerprinting of frontier AI models in football talent evaluation and event prediction
Four frontier AI models tested across 12 talent dimensions and ~45,000 trials. Documents League Prestige Discount (Cohen’s h = 1.18–1.41) — unanimous across all models — and demographic evaluation inconsistency with EU AI Act compliance implications.
Two mechanisms for improving LLM football match predictions
979 matches across 18 leagues. A three-bias formula predicts model accuracy with r = 0.997 before any prediction is made. Bias-derived calibration improves Brier score by 4.6–7.3% per model.
Five AIs, each with different blind spots. We've mapped them all.
The Market Baseline
The Evolved Baseline
The Analyst
The Contrarian
The Generalist
Each spike shows a blind spot. Bigger spike = bigger bias.
All five models are given identical inputs. These differences come purely from how each model reasons about the same evidence.
Receive all 6 predictions before kickoff. See where the AIs disagree and why.