A FIELD GUIDE TO JEV / VOL. 01
Jev’in en iyileri: gerçek projeler, pratik rehberler ve internetten fikirler.
THE OFFICIAL SIGNAL 4 HIGHLIGHTS
Diogo Almeida@CompleteSkepticLAUNCH POSTDiogo Almeida, TypeSafe'ın yapılandırılmış karar modeli Jev'i tanıtıyor. Lansman filmini izleyin ve modelin yaklaşımını, örneklerini ve yazarın bildirdiği performansını keşfedin.
TypeSafe AI@typesafeaiOFFICIALTypeSafe'ın resmi lansman duyurusu, laboratuvarı tanıtır ve geliştiricileri Jev'e yönlendirir. Diogo Almeida'nın lansman filmi ve orijinal girişimi içerir.
TypeSafe AI@typesafeaiOFFICIALTypeSafe, Jev'e açık erişimi duyurdu. Resmi konsol, uygulamanızda türden kararlar denemek için başlangıç noktasıdır.
JEVLAB ARTTypeSafe AI@typesafeaiOFFICIALTypeSafe, Jev'in türden çıktı yaklaşımını vurgular: uygulamalar durum ve sorular sağlar, ardından olasılıklar, seçimler veya puanlara göre hareket eder. Bağlantılı duyuruda Venice API entegrasyonu da yer alır.
JEVLAB ARTStart with the Launch Post. Explore four official signals.
1.198 kaynak
AI-assisted summaries and translations. Check original sources for context and performance claims.
Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next.
JEVLAB ART
EnglishSource-linked curation
Nick KhamiA demo showing how to make open source models behave like Jev using inference engineering and scoring endpoints for decision-making.
EnglishSource-linked curation
A developer project integrating Jev for judgment tasks within DeepSeek Harness.
JEVLAB ARTEnglishSource-linked curation
A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.
JEVLAB ARTEnglishSource-linked curation
Jozef GhermanA free AI tool built on Jev that quickly scans text for low-quality content, processing around 10,000 words in 2 seconds.
EnglishSource-linked curation
A community post presents a codebase complexity classifier using Jev, aiming to address overengineered code.
JEVLAB ARTEnglishSource-linked curation
A Rubik's Cube that uses Jev AI to solve itself using a human-like method rather than optimal algorithms.
JEVLAB ARTEnglishSource-linked curation
Hemant Kumar on his 151M ModernBERT reproduction: 0.83% adaptive calibration error, 3.0% of predictions flip when the option list is reversed, 35.6ms on CPU, with the failed use cases reported alongside the wins.
JEVLAB ARTEnglishSource-linked curation
Visual-Jev is a GitHub research project that makes decisions based on images rather than text descriptions of visual content.
JEVLAB ARTEnglishSource-linked curation
Grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる.
JEVLAB ARTEnglishSource-linked curation
A code search tool for agents to find behavior patterns instead of text strings.
JEVLAB ARTEnglishSource-linked curation
Dependency-free CLI and Codex skill that send local state to Jev for batched typed judgments and return answers without echoing the state.
JEVLAB ARTEnglishSource-linked curation
A developer project for the agents shelf, using MCP tool for Codex instead of listing all options.
JEVLAB ARTEnglishSource-linked curation
x.comA community post explaining Jev as an AI for decision-making, faster and cheaper than frontier LLMs.
JEVLAB ARTEnglishSource-linked curation
RESMÎTypeSafe AIOfficial TypeSafe reference: Confidence.
JEVLAB ARTEnglishSource-linked curation
Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.
JEVLAB ARTEnglishSource-linked curation
Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter.
JEVLAB ARTEnglishSource-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.
JEVLAB ARTEnglishSource-linked curation
RESMÎTypeSafe AIOfficial TypeSafe reference: Composite scoring.
JEVLAB ARTEnglishSource-linked curation
Sarvagya KulshreshthaA community post describing a system that matches one candidate to 400 companies with a confidence score in 12 seconds.
EnglishSource-linked curation
Audit your git diff against YAML coding-standards packs using TypeSafe's Jev model, from a CLI or your AI agent's command/skill.
JEVLAB ARTEnglishSource-linked curation
Aditya SinghA demo project enabling voice commands for Fusion 360, where Jev identifies if speech is a command or casual talk.
EnglishSource-linked curation
Every's Mike Taylor runs his whole archive through Jev.
JEVLAB ARTEnglishSource-linked curation
One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.
JEVLAB ARTEnglishSource-linked curation
One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.
JEVLAB ARTEnglishSource-linked curation
x.comA collection of GitHub repositories highlighting practical and developmental Jev projects, including browser agents and trading bots.
JEVLAB ART
日本語Source-linked curation
Jido agents use Jev to make moves in Tic Tac Toe, demonstrating Jev's application in game-playing agents.
JEVLAB ARTEnglishSource-linked curation
Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
JEVLAB ARTEnglishSource-linked curation
A GitHub project enabling voice-controlled Mac automation without vision models.
JEVLAB ARTEnglishSource-linked curation
An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support.
JEVLAB ARTEnglishSource-linked curation
Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides.
JEVLAB ARTEnglishSource-linked curation
Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app.
JEVLAB ARTEnglishSource-linked curation
在 X 的时间线上，给每条帖子标出它想让你干什么。判断来自 Jev，一个只返回概率、不生成文本的模型。
JEVLAB ARTEnglishSource-linked curation
RESMÎTypeSafe AIOfficial TypeSafe reference: Client SDKs.
JEVLAB ARTEnglishSource-linked curation
Jev as an LLM prompt guardrail inside the agentgateway proxy, with tracing and cost tracking.
JEVLAB ARTEnglishSource-linked curation
Draw on a tldraw canvas with your voice and a pointing finger. Jev (TypeSafe System One) decides action, target and place in ~350 ms per spoken word.
JEVLAB ARTEnglishSource-linked curation
Preview of fast browser use with Jev and OpenCode's browser CLI.
JEVLAB ARTEnglishSource-linked curation
A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.
JEVLAB ARTEnglishSource-linked curation
Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go.
JEVLAB ARTEnglishSource-linked curation
Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.
JEVLAB ARTEnglishSource-linked curation
A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts.
JEVLAB ARTEnglishSource-linked curation
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
JEVLAB ARTEnglishSource-linked curation
JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board.
JEVLAB ARTEnglishSource-linked curation
Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.
JEVLAB ARTEnglishSource-linked curation
Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.
JEVLAB ARTEnglishSource-linked curation
An agent project aimed at reducing token usage for coding agents via an MCP server.
JEVLAB ARTEnglishSource-linked curation
Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets.
JEVLAB ARTEnglishSource-linked curation
OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI.
JEVLAB ARTEnglishSource-linked curation
Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.
JEVLAB ARTEnglishSource-linked curation
Ian NuttallUsing Jev on Cloudflare Workers to improve search and content tagging efficiency on keep.md.
JEVLAB ARTEnglishSource-linked curation
Jev rapidly analyzed news articles to suggest relevant stories for brands at a low cost.
JEVLAB ARTEnglishSource-linked curation
PHP & Laravel SDK for TypeSafe AI's JEV Model series.
JEVLAB ARTEnglishSource-linked curation
x.comA community post suggesting Jev could serve as a fast, low-cost control layer for AI agents.
JEVLAB ARTEnglishSource-linked curation
TamirA dynamic form tool using Jev for conditional logic, built with Vercel JSON-render.
EnglishSource-linked curation
AbolA community post describes using Jev to analyze news for stock investment opportunities.
EnglishSource-linked curation
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
JEVLAB ARTEnglishSource-linked curation
aniolA speech analysis tool that evaluates 30-second speeches for pauses, filler words, and confidence, providing feedback for improvement.
EnglishSource-linked curation
Pre-commit hook: one Jev call judges whether your commit message matches the staged diff, plus debug leftovers, unmentioned work, and a credential check.
JEVLAB ARTEnglishSource-linked curation
Visual Jev lab for multiple games and emulator platforms.
JEVLAB ARTEnglishSource-linked curation
Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B.
JEVLAB ARTEnglishSource-linked curation
MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools.
JEVLAB ARTEnglishSource-linked curation
Independent async and blocking Rust SDK for the TypeSafe AI System One API.
JEVLAB ARTEnglishSource-linked curation
Marc KöhlbruggeA real-time computer assistant using Jev and local Whisper to process voice input, classify actions, and interact with the screen through a Swift app for accessibility.
JEVLAB ARTEnglishSource-linked curation
x.comA collection of 19 open-source projects using Jev technology for various applications including AI agents and game interactions.
简体中文Source-linked curation
Reimagined window switcher for macOS using frontier artificial intelligence. Predicted by TypeSafe's Jev model.
JEVLAB ARTEnglishSource-linked curation
A verified, community-maintained catalog of 485 open-source projects built with Jev.
JEVLAB ARTEnglishSource-linked curation
A developer project featuring a small Jev-like model running on a MacBook, collected for the tools shelf.
JEVLAB ARTEnglishSource-linked curation
Jev successfully played and won a match in the game Clash Royale.
JEVLAB ARTEnglishSource-linked curation
Cost-aware LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.
JEVLAB ARTEnglishSource-linked curation
Flue agent routing with TypeSafe Jev through Cloudflare AI Gateway.
JEVLAB ARTEnglishSource-linked curation
A social media feed optimized using user bookmarks and Jev's analysis.
JEVLAB ARTEnglishSource-linked curation
22 Jev models, one ball: a 3D football match where every player is its own Jev (TypeSafe AI System One) decision. Watch, or take over the number 9.
JEVLAB ARTEnglishSource-linked curation
Kaynak gönder
한국어
Español
Français
Deutsch
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Polski
Русский
4 HIGHLIGHTS
Agents & browsers
Source-linked curation
Decisions & routing
Tools & apps
Games & real time
Creative & growth
Research & data
Markets & experiments