All decision model projects

Reproducible measurements of Jev's real cost, latency, response shapes and accuracy, plus 13 decision models on the same 633 items.

Agent memory system where Jev or local Laya controls memory organisation, query routing, retrieval budgets and stopping.

Runnable yardstick that tests Jev's three headline claims on a small local model: typed output, no hallucination, calibration.

JevNext: decodes numbers from Jev by walking a multiway decision tree of interval or digit Choice calls, without logits or training.

Open-weights Jev-style decision engine on Qwen2.5-1.5B with a decision head and QLoRA, answering Choice, Noul and Score in one pass.

Simulation-only Payment Decision Lab testing whether Jev can beat rule-based routers at choosing payment service providers.

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

MuJoCo pilot where Jev, Claude Haiku and reactive rules choose pick-and-place actions; Jev matched the rules exactly.

Craftax survival agent where Jev picks one Choice per step from code-listed actions, with optional LLM goals, plus ablations.

Independent 52-page Chinese report on Jev that checks vendor claims and reproduces 50 Chinese tests, with traceable data.

Compares Jev's zero-shot reranking with specialist rerankers on MS MARCO passage and document benchmarks and a TREC WSJ transfer test.

Reproducible evaluation harness and field note for the Jev Ultrafast research browser, with QC-graded baseline and stress suites.

Resume-to-JD screening study (Chinese) with 5 Noul gates, 4 Score dimensions and a routing Choice per request, hardened over three versions.

Archived Go harness finding Jev tool steering does not reliably cut agent tokens in Claude Code or Codex; context trimming helped.

Short report comparing Jev and many other fast decision classifiers with an LLM on grading section relevance in technical documents.

Small eval that uses Jev to judge whether shadcn-ui/lint findings are correct and whether each message says what to change.

Claude Code hook that asks Jev which skill fits each prompt, plus the week-long log that led its author to remove it.

Snake research environment where game rules stay in code and Jev picks the movement direction from structured state each tick.

Independent open model on Molmo2-ER that answers spatial questions by choosing from fixed options with one shared classifier head.

StarCraft II research repo where Jev Choices pick macro actions and unit micromanagement, optionally constrained by a larger model's plan.

Local reproduction of Jev-style inference that reads option-token logits from a small LLM in one pass, with an honest failure log.

Small Jev measurement bench with an append-only call log, labelled claims and a stated negative result.

Tetris where each reachable placement is an English sentence that Jev ranks, with controls showing a regex baseline does better.

Harness that runs Jev on all 19,646 TMMLU+ Traditional Chinese questions as four-way Choices, reporting accuracy and calibration.

Benchmark release evaluating Theory of Mind in five typed decision models versus seven generative baselines on nine ToM datasets.

Benchmark of BM25, embeddings, rerankers and Jev for picking the right MCP tool among 525, plus an experimental Jev search engine.

Research code evaluating Jev as an independent per-tool relevance judge for building task-level tool spaces on TGB, BFCL and GTA.

Simulated crypto trading loop that turns BTC and ETH tape features into words, asks Jev six judgments per tick and models costs and latency.

Point-in-time O'Neil momentum backtest where Jev picks entries and judges exits, with a jackknife showing no resolvable edge over rules.

Decision Lab: sixty finance demos asking Jev, OpenAI Decisions and twelve other decision models the same questions, graded.