All decision model projects

Input layout optimizer that reorders rows and fields so a prefix-caching decision model judges every record in a big table faster.

Stdlib-Python guardrail and model router for LLM gateways on Jev, with an independent accuracy, calibration and latency evaluation.

Open Jev replica on Gemma 4 E2B and Gemma 3 270M served on Modal, with eight demos and a TypeSafe eval head-to-head.

Recorded benchmark of Jev versus two frontier LLMs on 100 synthetic security-triage cases, with a static dashboard.

Study finding commercial decision models including Jev give different yes/no probabilities on Taiwan statements by Chinese script.

Tic-tac-toe teaching project comparing Jev Choice, Score and Noul designs across three levels of state detail.

Static charts comparing Jev with 110 other models on Thai standardized exams for accuracy, cost, speed and calibration.

Backtest harness that tests Jev as a BUY/SELL/HOLD trader on NQ level-10 order-book data, with replay, viewer and paper-trading modes.

Lightweight reproduction of the Jev shape on a ModernBERT encoder and a diffusion LLM, comparing speed, accuracy, calibration and cost.

Short evaluation finding that Jev plays chess poorly, often calling unbalanced positions draws.

Local app testing Jev as a chess decision-maker against Stockfish, with Stockfish grading every pick.

Write-up with measurements on calibrating Jev as a code reviewer: context effects, textual tells, thresholds and noise near thresholds.

Local System One-compatible server that reads option probabilities from a small MLX LLM, with measured calibration.

R&D repo with three Jev pipelines (ticket triage, alert triage, deploy-risk gate) built from four reusable patterns.

Standalone Jev-class emotion model: one pass over a message sequence returns calibrated PAD scores, an emotion family and yes/no judgments.

Open project training a vision-enabled Jev-like model (0.8B, 9B) that judges dynamic candidate sets over images with Choice, Noul and Score.

Self-hostable calibrated decision model for images and text (Qwen3-VL-4B + LoRA) scoring 82.7 percent on public JevBench.

Gym-style environment for offline Warcraft III with deterministic stepping and fog-filtered observations, plus an agent using Jev for micro.

Independent, source-linked research on Jev with about 948 rubric-scored public repositories, recurring patterns and verified findings.

Reproducible experiments and reports on what Jev can and cannot do, from skill routing to GPQA and housing prices.

Tabular classifier that learns which slices of labeled rows and columns to send Jev or LAYA, stopping when it has enough.

Long-form analysis of what Jev is, why it is fast, how much of the hype holds up, and how hard it is to reproduce.

Chinese translation of 'Jev Engineering for coding agents', design notes on a harness where Jev makes every per-turn decision.

Japanese research deck, article and source ledger tracking TypeSafe's Jev and System One models over time.

Issue in the Orcha multi-agent orchestration project proposing to move judgment calls onto Jev to cut model cost.

Bilingual single-page essay on Jev's one-step decisions, local tests, failure modes and production limits, with a live demo.

Code examples for Codely's Spanish course on integrating Jev and other System One models into a real application with an LLM fallback.

Short tutorial repository introducing Jev as a System One model and how State, Choice, Score and Noul differ from LLM text generation.

Community Jev cookbook with 10 runnable examples, composition patterns, theory notes and a list of 120+ use cases.

Repository describing a Roblox Studio instance reviewer using typed Jev criteria with citations; README is mostly marketing.