Forecasting with decision models

Local China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.

Toy Rust CLI that scores Singapore TOTO numbers with Jev from code-computed draw stats, giving a next-draw probability and heat level.

Stock terminal that gathers live evidence via Valyu and asks Jev for the probability a stock trades higher in 30 days.

Experimental Polymarket bot: a web-search model writes an evidence brief, Jev prices P(YES), and code trades only on a configured edge.

Terminal agent for Polymarket 5-minute BTC markets that asks Jev up or down and buys once only above 0.90 confidence; dry-run default.

Polymarket BTC 5-minute up/down agent: code prices with a volatility model, Jev scores regime and vetoes anomalies; paper by default.

Datadog Labs Rust library for observability control loops where Jev recommends an action and declared guards decide if it commits.

Combines Jev judgments on row text with a tabular foundation model like TabPFN to predict outcomes from few labels.

Paper-only research tool for Polymarket BTC 5-minute Up/Down markets: Jev scores the direction, separate code decides entries.

Pre-specified study running Jev and GPT-4.1 as 300 synthetic survey respondents; question format mattered more than model.

Experiment that builds past-only Hong Kong market state and asks Jev for an up, flat or down forecast, with a standalone HTML report.

Paper-trades real Polymarket and Kalshi markets with a fake $100k, using Jev as judge fed by Claude research, against the market's price.

Calibration experiments showing Jev's Choice probabilities on fair dice and coins stay high while accuracy stays at chance.

TypeScript CLI and REST API that asks Jev to rate an occupation's AI layoff risk, trajectory and need for human accountability.

Startup-idea evaluator where Jev scores eight indie-hacker questions and code turns the weighted average into KILL, FIX or SHIP.

Hypothesis-driven experiments characterising the Jev API, intended to inform a future football prediction product.

Benchmark asking models to forecast federal motion-to-dismiss rulings from the judge's record, scored with claim-defendant Brier metrics.

Experiment testing how well Jev predicts financial markets; the author reports it does not do well, like most LLMs.