Liquid AI's D1 classifier beats typesafeai's Jev in 9 of 12 forecasting categories
JosephJacks_ · x · 2026-10-02
In a benchmark based on Philip Tetlock's Good Judgment Project historical forecasting set, classifiers from typesafeai (Jev) and Liquid AI (D1) assigned probabilities to scenario outcomes, scored against actual results. Liquid AI's D1 won 9 of 12 categories. The author calls it encouraging for quant traders on prediction markets, while discouraging use for gambling.
More from Models
- ChatGPT Pro 500 plan hits £445 (~$589) in the UK — koltregaskes · 2026-10-02
- Open-Source Coding Agent Z-Engine Delegates Micro-Decisions to a System 1 Model — arshadbarves · 2026-10-02
- Best AI Agent Finishes Year-Long Simulation With Just 27.3% of Human Earnings — rohanpaul_ai · 2026-10-02
- ChatGPT paid accounts get global usage reset at 10am PST as GPT-6.1 Sol speeds recover — Angaisb_ · 2026-10-02
- Does Google Fact-Check Its Own AI Overview Summaries? — daluoseo · 2026-10-02
- Dev argues intelligence and consciousness are user projections onto LLMs, not in the system — gerardsans · 2026-10-02