JEVLAB
情報を送る
日本語
English한국어日本語EspañolFrançaisDeutsch简体中文繁體中文PortuguêsBahasa IndonesiaไทยItalianoTiếng ViệtTürkçePolskiРусский
Live0
Today18
Total18

Latest addition

Source check

Recent activity

A FIELD GUIDE TO JEV / VOL. 01

小さな判断。
大きな可能性。

Jevのプロジェクト、実践ガイド、世界中のアイデアをひとつに。

ラボを見るガイド
1,198件の資料16言語
TypeSafe AI THE OFFICIAL SIGNAL 4 HIGHLIGHTS
Diogo Almeida@CompleteSkepticLAUNCH POST

Jevのリリース投稿

ドイゴ・アレイダがJevを紹介し、TypeSafeの構造化された意思決定モデルを説明します。リリース映像を視聴し、オリジナルスレッドでモデルのアプローチ、例、および著者によるパフォーマンスを確認してください。

2026-09-15 · Launch postView on X

Start with the Launch Post. Explore four official signals.

95 件の資料

AI-assisted summaries and translations. Check original sources for context and performance claims.

kshetrajna12

reflex

A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.

reflex
Research & dataEnglish

Source-linked curation

原文を開く
1 clicks / 7d
anandi1989

awesome-jev-usecases

Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
fstandhartinger

jevbench

JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
olanotolu

jevbetter

A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
zhengxuyu

LitJev

A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
scienthoon

jev-ood-calibration

Independent calibration test of TypeSafe's Jev on a task it cannot have seen: 900 rule-generated support tickets (choice / score / boolean) plus 3 public benchmarks via Vercel AI Gateway. Raw responses, ECE with noise floor, temperature refit, per-type sign of miscalibration. Reproducible for ~$0.06.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
AbdelStark

jev-benchmarks

Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
jh1373

jev-search

Offline Obsidian search with optional Jev reranking of results, requiring user approval before reranking.

jev-search
Research & dataEnglish

Source-linked curation

原文を開く
realZachi

jevtest

Semantic test matchers for Vitest and Jest, powered by TypeSafe's Jev model. Write expectations in plain English, get calibrated probabilities back.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
Menny1337

jev-lab

TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
NullPo-jp

PocketJev

On-device iPhone visual decision tool using MLX and Qwen3-VL direct option logits.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
anessbelbati

jev-rerank-bench

Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
anisselbd

jev-phishing-bench

Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
hope

jeval

A research project evaluating the practical value of Jev's confidence scores for task execution.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
zwliJay

JevForge

End-to-end Jev-style structured-decision stack for auditable data construction, Qwen3.5-0.8B training, fixed Mind2Web and OOD evaluation, preliminary RLCD, local serving, and interactive replay.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
ShuhanSun

jev-oas-sentinel

Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
Jökull Sólberg Auðunsson

ensk

A research project featuring an English–Icelandic dictionary that uses Jev to rerank results for better accuracy.

ensk
Research & dataEnglish

Source-linked curation

原文を開く
ishantanu

jevmetrics

OpenTelemetry Collector connector that uses Jev to assess metric metadata and apply retention policies before export.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
TheoLeeCJ

SemIf

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
ikermoel

open-alternative-jev

Open alternative to Jev: typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with benchmarks.

open-alternative-jev
Research & dataEnglish

Source-linked curation

原文を開く
JackZeng

Jev_apps

看看 Jev 能做什么：用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
mithalouni

system-one-open

Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal).

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
wfzyx

von

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
Bewinxed

jevgpt

A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively).

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
Zaious

jev-capability-atlas

Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文為主的雙語 repo。

jev-capability-atlas
Research & dataEnglish

Source-linked curation

原文を開く
0xnairb

research_desk

TypeSafe Jev demonstration for new analyzation — experimenting with Jev for fast analysis of news and tickers.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
Mapika

decider

One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
y0usaf

jev-lm

A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
SiliconLabAI

OpenJev

An open-source project aiming to develop a Jev-class decision model for research purposes.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
genai-craft

openvons

Openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
Gaurav-Gosain

jev-headline-bench

Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
TypeAR-AI

TypeAR

Type-safe one-decision-per-token decoding engine for autoregressive LLMs, inspired by Jev.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
fabricioctelles

modelsystem

Curated catalog of System One / Decision Models — contributions for modelsystem.one.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
bnsd55

jevmlx

Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
cablehead

jev.nu

Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
MarissaFamularo

citation-verifier

Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
grishahq

decisionbridge

A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
翻訳要約
zsavage8

padflow-jev-evals

PadFlow（土地開発SaaS）からの型決定ベンチマーク：スキーマ、匿名化されたラベル付き行、Jevのような信頼性の高いモデル用ランナー。

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
Gaurav-Gosain

jev-sec-bench

Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く
sgoedecke

system-one

Batched single-token choice inference for open language models, compatible with TypeSafe.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Research & dataEnglish

Source-linked curation

原文を開く