Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more
TypeSafe Fun AdBlocker
A Manifest V3 Chrome extension that finds ad-shaped DOM elements and asks Jev, one noul question per candidate, whether each is a paid advertisement; hits above the threshold are removed.
- Category
- Cookbooks & Demos
- Published by
- Community
- Author
- realZachi
- Added
- 2026-09-22
Tagscommunityjavascriptchrome-extensionbrowserclassification
Highlights
- The content script finds candidates by tags, id and class tokens like ad or sponsored, data-ad attributes, ad-network links, and labels such as Anzeige.
- One batched request per page sends one noul question per candidate to POST /v1/systemone with model jev-latest.
- Elements with P(ad) at or above 0.70, adjustable from 0.30 to 0.95, are outlined and removed; batches cap at 30 candidates and are debounced by 600 ms.
- As of 2026-09-17: 11/11 hand-written candidates correct, 8/8 ads removed in the harness, 0 false removals, roughly 0.7-1.9 s per batch.
Quickstart
bash
TYPESAFE_API_KEY=YOUR_API_KEY npm run relay
npm run serve
# then open http://localhost:8787/test/harness.htmlWatch out
MIT-licensed. Needs Chrome developer mode and a TypeSafe API key pasted into the popup; the author calls it a demo, not a real ad blocker, and every batch costs tokens.
More like this
46GitHub stars
Local Instagram, TikTok, and LinkedIn research app where Jev makes confidence-gated typed choices over the platform and next socai operation, while deterministic Node code validates each decision and the socai CLI performs read-only browser capture.
Cookbooks & Demos#community#javascript#agents
Communityjev-social
17GitHub stars
Fifteen runnable OpenRouter recipes for Jev covering support triage, database indexing, PII scanning, moderation, lead scoring, a browser agent, and a Gmail labeler, each with a small labelled dataset and saved live results.
Cookbooks & Demos#community#javascript#openrouter
Communityjev-cookbook
3GitHub stars
A tldraw canvas controlled by voice and a webcam-tracked fingertip: every partial transcript triggers one Jev request through OpenRouter's Decisions API that decides the action, shape, colour, and place.
Cookbooks & Demos#community#javascript#browser
Communityjev-canvas
From the community
Posts from builders shipping with Jev right now.
Inferring Jev's internals from 1,000 calls
The open System One roundup
Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more
Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格
The launch post
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x Show more
Trading bot, one decision per block
I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app
Classifying 1,500 real emails
this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Fast browser use with Stagehand
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x