JEVLAB
提交资源
简体中文
English한국어日本語EspañolFrançaisDeutsch简体中文繁體中文PortuguêsBahasa IndonesiaไทยItalianoTiếng ViệtTürkçePolskiРусский
Live1
Today18
Total18

Latest addition

Source check

Recent activity

A FIELD GUIDE TO JEV / VOL. 01

小小判断。
无限可能。

汇集 Jev 的真实项目、实用指南和来自全网的创意。

探索实验室指南
1,198项资源16种语言
TypeSafe AI THE OFFICIAL SIGNAL 4 HIGHLIGHTS
Diogo Almeida@CompleteSkepticLAUNCH POST

Jev发布帖

Diogo Almeida介绍了Jev，即TypeSafe的结构化决策模型。观看发布影片，并探索原始帖子了解该模型的方法、示例和作者报告的性能。

2026-09-15 · Launch postView on X

Start with the Launch Post. Explore four official signals.

114 项资源

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

jh1373

jev-search

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

jev-search
Research & dataEnglish

Source-linked curation

查看原文
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

查看原文
www.youtube.com

I paired Jev with Astra

A YouTube guide discussing Jev's functionality, pricing, and performance comparisons with Astra, including benchmarking and parallel decision analysis.

I paired Jev with Astra
Research & dataEnglish

Source-linked curation

查看原文
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

查看原文
Ahmad Sofi-Mahmudi

Jev Reviewer

Tool for systematic reviewers to extract information from research articles efficiently.

Jev Reviewer
Research & dataEnglish

Source-linked curation

查看原文
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

查看原文
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

查看原文
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

查看原文
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

查看原文
keltokhy

jsort

Sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev model.

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

Source-linked curation

查看原文
adhyaay-karnwal

jev-chat

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

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

Source-linked curation

查看原文
mahlernim

jev-korean-benchmark

Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence.

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

Source-linked curation

查看原文
HackSing

jev-report

发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表.

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

Source-linked curation

查看原文
译文摘要
zsavage8

padflow-jev-evals

PadFlow（土地开发SaaS）的类型化决策基准：模式、匿名化标记行和用于信心校准模型的运行器，如TypeSafe Jev。

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

Source-linked curation

查看原文
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

查看原文
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

查看原文
shamazharikh

qwen-rlcd

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

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

Source-linked curation

查看原文
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

查看原文
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

查看原文
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

查看原文
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

查看原文
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

查看原文
AntonioCoppe

jev-harness

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.

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

Source-linked curation

查看原文
razorback16

openjev

Open, Jev-compatible System One decision server on DiffusionGemma.

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

Source-linked curation

查看原文
AlbionaHoti

refgarden

A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections.

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

Source-linked curation

查看原文
copyleftdev

jev-labs

Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.

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

Source-linked curation

查看原文
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

查看原文
Nick DeJesus 🛒🎉 - Former Unpaid CTO @BTPipeline

Jevals

Jevals is a local testing environment for evaluating Jev requests and improving results through primitive operations.

Jevals
Research & dataEnglish

Source-linked curation

查看原文
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

查看原文
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

查看原文
bitnovus

jev-spam-eval

Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines.

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

Source-linked curation

查看原文
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

查看原文
fatwang2

Jev Search

A free open-source search tool powered by Jev and a search API for plain language queries.

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

Source-linked curation

查看原文
pithings

advocaat

A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.

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

Source-linked curation

查看原文
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

查看原文
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

查看原文
Marcos Martinez

jev-acento

A research project auditing Jev's performance with the Spanish language.

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

Source-linked curation

查看原文
zhihz

openjev (zhihz)

Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.

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

Source-linked curation

查看原文
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

查看原文
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

查看原文
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

查看原文
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

查看原文
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

查看原文