Latest addition
Source check
Recent activityA FIELD GUIDE TO JEV / VOL. 01
O melhor de Jev: projetos reais, guias práticos e ideias de toda a internet.
THE OFFICIAL SIGNAL 4 HIGHLIGHTS
Diogo Almeida@CompleteSkepticLAUNCH POSTDiogo Almeida apresenta o Jev, o modelo de decisão estruturado do TypeSafe. Assistir ao filme de lançamento e explorar o fio original para o abordagem do modelo, exemplos e desempenho relatado pelo autor.
TypeSafe AI@typesafeaiOFFICIALO anúncio oficial de lançamento do TypeSafe apresenta o laboratório e direciona os desenvolvedores ao Jev. Inclui o filme de lançamento de Diogo Almeida e a introdução original.
TypeSafe AI@typesafeaiOFFICIALTypeSafe anuncia acesso público ao Jev sem lista de espera. O console oficial é o ponto de partida para testar decisões tipadas em seu próprio aplicativo.
x.comJev está disponível para todosVer projeto ↗TypeSafe AI@typesafeaiOFFICIALTypeSafe destaca a abordagem de saída tipada do Jev: aplicações fornecem estado e perguntas, depois atuam sobre probabilidades, escolhas ou pontuações. A anúncio vinculado também aborda a integração da API Venice.
x.comRespostas que seu código pode usarVer projeto ↗Start with the Launch Post. Explore four official signals.
95 recursos
AI-assisted summaries and translations. Check original sources for context and performance claims.
Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results.
github.comanandi1989/awesome-jev-usecasesVer projeto ↗
EnglishSource-linked curation
A research project featuring an English–Icelandic dictionary that uses Jev to rerank results for better accuracy.
EnglishSource-linked curation
A collection of research papers and open reproductions supporting System One models.
EnglishSource-linked curation
Offline Obsidian search with optional Jev reranking of results, requiring user approval before reranking.
EnglishSource-linked curation
Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.
github.comvercel-labs/ai-cliVer projeto ↗EnglishSource-linked curation
Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo.
github.comlab-dados/jev-anotacao-sentencasVer projeto ↗EnglishSource-linked curation
A research project enabling SQL queries with real type responses.
EnglishSource-linked curation
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.
github.comGaurav-Gosain/jev-headline-benchVer projeto ↗EnglishSource-linked curation
Papers, open reproductions and independent evaluations behind System One models and Jev.
github.comOmniJev/awesome-jev-galleryVer projeto ↗EnglishSource-linked curation
Semantic test matchers for Vitest and Jest, powered by TypeSafe's Jev model. Write expectations in plain English, get calibrated probabilities back.
github.comrealZachi/jevtestVer projeto ↗EnglishSource-linked curation
Jev 1.13 reward-model evaluation across 8 benchmark tracks, with an interactive report and 54-row SOTA comparison.
github.comgoya4140/jev-reward-model-evaluationVer projeto ↗EnglishSource-linked curation
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE).
github.comHeman10x-NGU/openJev-verdict-2.0Ver projeto ↗EnglishSource-linked curation
Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B.
github.comshamazharikh/qwen-rlcdVer projeto ↗EnglishSource-linked curation
An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice.
github.comkesku/jev-freeformVer projeto ↗EnglishSource-linked curation
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.
github.comJackZeng/Jev_appsVer projeto ↗EnglishSource-linked curation
A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval.
github.comy0usaf/jev-lmVer projeto ↗EnglishSource-linked curation
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.
github.comcopyleftdev/jev-labsVer projeto ↗EnglishSource-linked curation
A research project on GitHub conducting nine experiments and 28 predictions with fixed parameters, focusing on Jev's performance metrics.
github.comwillkelly/jev-evaluationVer projeto ↗EnglishSource-linked curation
Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides.
github.commyokoym/misereru-slide-jevVer projeto ↗EnglishSource-linked curation
A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.
github.compithings/advocaatVer projeto ↗EnglishSource-linked curation
JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.
github.comfstandhartinger/jevbenchVer projeto ↗EnglishSource-linked curation
Open alternative to Jev: typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with benchmarks.
EnglishSource-linked curation
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。
EnglishSource-linked curation
Jev-compatible System 开源Jev.
github.comGPT-AGI/OpenJevVer projeto ↗EnglishSource-linked curation
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.
github.comscienthoon/jev-ood-calibrationVer projeto ↗EnglishSource-linked curation
A research project on GitHub uses Jev with Qwen3 models on an NVIDIA DGX Spark system.
github.comabhishek085/open-spark-jevVer projeto ↗EnglishSource-linked curation
Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code.
github.comSamuelSacco/jev-explorationVer projeto ↗EnglishSource-linked curation
A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections.
github.comAlbionaHoti/refgardenVer projeto ↗EnglishSource-linked curation
Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.
github.comzhihz/openjevVer projeto ↗EnglishSource-linked curation
Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence.
github.commahlernim/jev-korean-benchmarkVer projeto ↗EnglishSource-linked curation
Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines.
github.combitnovus/jev-spam-evalVer projeto ↗EnglishSource-linked curation
A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively).
github.comBewinxed/jevgptVer projeto ↗EnglishSource-linked curation
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
github.comAbdelStark/jev-benchmarksVer projeto ↗EnglishSource-linked curation
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.
github.comolanotolu/jevbetterVer projeto ↗EnglishSource-linked curation
A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.
EnglishSource-linked curation
Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG.
github.comerendikmenn/jev-rag-benchmarkVer projeto ↗EnglishSource-linked curation
A show-and-tell capability study for Jev, TypeSafe's System One decision model.
github.comlbotinelly/jev-little-airwaysVer projeto ↗EnglishSource-linked curation
AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard).
github.comshibadogcap/kyotsu-ai-benchVer projeto ↗EnglishSource-linked curation
A research project auditing Jev's performance with the Spanish language.
github.commarcosmartinez/jev-acentoVer projeto ↗EnglishSource-linked curation
Open-source BYOK arena for Jev and other AI judges. Find failures, compare quality, cost, and latency.
github.comchenmingtang830/jevarenaVer projeto ↗EnglishSource-linked curation
Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal).
github.commithalouni/system-one-openVer projeto ↗EnglishSource-linked curation
The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
github.comwfzyx/vonVer projeto ↗EnglishSource-linked curation
Small Python package that uses typesafe.ai to evaluate code comments on certain heuristics.
github.comHexdigest123/typesafe-commentVer projeto ↗EnglishSource-linked curation
Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities.
github.comcablehead/jev.nuVer projeto ↗EnglishSource-linked curation
Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.
github.comMarissaFamularo/citation-verifierVer projeto ↗EnglishSource-linked curation
If you're experimenting with jev it will be easier from here.
github.comutk2103/jev-studioVer projeto ↗EnglishSource-linked curation
Benchmark de decisões tipadas do PadFlow (SaaS de desenvolvimento de terras): esquemas, linhas anônimas rotuladas e um executor para modelos calibrados em confiança como o Jev da TypeSafe.
github.comzsavage8/padflow-jev-evalsVer projeto ↗EnglishSource-linked curation
Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper.
github.comgoodrahstar/jev-column-raceVer projeto ↗EnglishSource-linked curation
Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo — Choice/Noul vs gold labels.
github.comPistachioAIHQ/jev-synergy-screeningVer projeto ↗EnglishSource-linked curation
A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.
github.comgrishahq/decisionbridgeVer projeto ↗EnglishSource-linked curation
Replicating Jev with a local LLM.
github.comArgos1111/jev_localVer projeto ↗EnglishSource-linked curation
Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations).
github.comcodeitlikemiley/system-one-adapter-rustVer projeto ↗EnglishSource-linked curation
Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go.
github.comGaurav-Gosain/jev-sec-benchVer projeto ↗EnglishSource-linked curation
Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models.
github.comvehas/thaiexam-jev-chartsVer projeto ↗EnglishSource-linked curation
An open-source project aiming to develop a Jev-class decision model for research purposes.
github.comSiliconLabAI/OpenJevVer projeto ↗EnglishSource-linked curation
High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul).
github.comAkashPriyadarshii/jev-curateVer projeto ↗EnglishSource-linked curation
A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.
github.comblas0/jev-shadcn-lint-evalVer projeto ↗EnglishSource-linked curation
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.
github.comzhengxuyu/litjevVer projeto ↗EnglishSource-linked curation
Feedback on your paper in seconds.
github.comJacobLinCool/jev-paper-judgeVer projeto ↗EnglishSource-linked curation
Sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev model.
github.comkeltokhy/jsortVer projeto ↗EnglishSource-linked curation
Open, Jev-compatible System One decision server on DiffusionGemma.
github.comrazorback16/openjevVer projeto ↗EnglishSource-linked curation
TypeSafe Jev demonstration for new analyzation — experimenting with Jev for fast analysis of news and tickers.
github.com0xnairb/research_deskVer projeto ↗EnglishSource-linked curation
One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.
github.comMapika/deciderVer projeto ↗EnglishSource-linked curation
A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place.
github.comtryaksh/jev-pick-and-place-studyVer projeto ↗EnglishSource-linked curation
Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.
github.comShuhanSun/jev-oas-sentinelVer projeto ↗EnglishSource-linked curation
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.
github.comAntonioCoppe/jev-harnessVer projeto ↗EnglishSource-linked curation
TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.
github.comMenny1337/jev-labVer projeto ↗EnglishSource-linked curation
TypeSafe AI System One (Jev) task plugin for QuantumNous/new-api — native /v1/systemone, synchronous evaluation, token billing.
github.comFFatTiger/new-api-plugin-typesafeVer projeto ↗EnglishSource-linked curation
Find, design, and evaluate TypeSafe Jev decision loops.
github.comkaranb192/jev-architectVer projeto ↗EnglishSource-linked curation
Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.
github.comabhixhek/jevcalVer projeto ↗EnglishSource-linked curation
Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.
github.combnsd55/jevmlxVer projeto ↗EnglishSource-linked curation
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.
github.comHackSing/jev-reportVer projeto ↗EnglishSource-linked curation
Enviar descoberta
한국어
日本語
Español
Français
Deutsch
简体中文
繁體中文
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
1 clicks / 7d
Research & data
Source-linked curation
TRADUZIDO