Research and benchmarks — page 6

Audit your git diff against YAML coding-standards packs using TypeSafe's Jev model, from a CLI or your AI agent's command/skill.

A chatbot from typed Jev decisions: hierarchical speculative decoding over System One probabilities.

Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction. Zero dependencies.

Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B

Test what your AI should remember. An experimental, source-aware memory admission evaluator powered by Jev, with editable cases and inspectable results.

Speed and accuracy benchmark: TypeSafe's Jev API vs the local Laya MLX typed-decision model on synthetic tasks

First independent head-to-head benchmark of System One decision models (Laya vs Jev) on byte-identical inputs

cuda-Jev — a CUDA-native Jev System One decision inference engine. Jev compatible API, examples, and reproducible benchmarks.

An OpenAI-compatible proxy that sits between your LLM and your users. It evaluates each sliding window of tokens while the response is still streaming and cuts the stream before a violating token can reach the screen.

Jev 1.13 reward-model evaluation across 8 benchmark tracks, with an interactive report and 54-row SOTA comparison

Local-first document evaluation workspaces powered by Jev

Abandoned Qwen3.5-0.8B LoRA fine-tuning experiments for Jev-like typed judgments, with datasets, adapters, evaluations, and a full retrospective.

38 zero-shot information-extraction & classification systems across 23 families — extractors, classifiers, cross-encoder rerankers and typed-decision engines, local + hosted (OpenRouter) — demos, accuracy/latency/cost benchmarks, 9-language suite, web UI

Open-source BYOK arena for Jev and other AI judges. Find failures, compare quality, cost, and latency.

Experimental Jev permission gate for Claude Code via OpenRouter, with reproducible latency and cost benchmarks

Calibrated alignment verifier for LLM responses and agent plans — powered by Jev

Pre-registered independent eval of TypeSafe Jev against a nano-class LLM, a frontier LLM, and a supervised encoder (Banking77 + CLINC150 zero-shot)

Experiments on Jev’s probability calibration, uncertainty reporting, and forecast probability preservation.

open-sourced jev-flash-router: an MCP server for TypeSafe's new Jev model. AI coding agents waste hundreds of reasoning tokens just deciding which file to edit, which route to pick, or whether a diff breaks tests. Jev evaluates state and outputs calibrated probabilities. Works with Cursor, Windsurf, & Claude Code

TypeSafe AI System One (Jev) task plugin for QuantumNous/new-api — native /v1/systemone, synchronous evaluation, token billing

MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code

Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).

Independent Jev 1.13.0 behavior study: report, controlled prompt experiments, raw results, and offline verification.

An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice