What people post on X about Jev

Saksham Sharma

@code_saksham

And just when I thought I have a crazy idea with JEV that i will open source then this happened. Please @typesafeai fix it ASAP, the curiosity inside me to build that thing is insanely high

Siim Haugas

@siimh

scoreboar v8: 128 MB instead of 597, about 30 ms a post instead of a second. and more accurate. guessing which of two X posts did better for its account size: 61.4%. grok 4.7: 55.3%. jev: 52.5%. free, in your browser. github.com/Siim/scoreboar…

Chase

@0xChaseTM

Jev Engineers just released Jev, and the architecture is simple: state goes in, auditable decisions come out I mapped the decision layer into a field blueprint: what Jev reads, what it returns, and how an agent uses those answers in a real loop: step 1 → give each layer a job. The LLM plans and writes. Jev chooses between bounded options. Code carries out the action. step 2 → build the state before asking for a decision. Include the goal, evidence, available actions, previous actions, and what the environment looks like now. step 3 → define the questions in code. Choice selects an option. Score rates it. Noul estimates whether a condition is true. The answers are typed, so the runtime can use them directly. step 4 → ask independent questions together. One state snapshot can support routing, risk, and relevance decisions in the same pass. step 5 → use the answers to route work. A lookup, a complex reasoning task, and a tool call don’t need the same model or execution path. step 6 → add a gate before the tool runs: allow, ask, or deny. A high-confidence answer still has to pass the action policy. step 7 → execute the selected action and check the outcome. Record what the tool actually did, including failures. step 8 → update the state with that result. Otherwise, the agent’s next decision is based on a world that no longer exists. step 9 → apply the pattern where small decisions repeat: model routing, tool guardrails, inbox triage, research classification, browser actions, and context compaction. step 10 → judge the whole task. Track whether the agent reached its goal alongside cost, latency, approvals, and failed actions. the result: you can trace an action from the evidence Jev received to the decision it returned and the outcome your tools produced. Save the Jev Decision Infrastructure blueprint for your next agent build ↓

YZ

@robot_yz

使用 #Jev 做了一个填写外链信息的演示。 眨眼的功夫就找到入口，并准确的把已知信息填写完了。 准备把之前的Submit Agent改成使用JEV模式。 关注github，在评论区

Harsh Singh

@haaarshsingh

i created a 404 page that fixes your typos for you, and redirects you to the correct page built with @typesafeai jev try it out: kobra.systems/cmr-table

Justin Youens

@youens

This is the neatest example of Jev I've seen. But didn't see a demo link, so here you go: emogee.youens.com

Leaf Yeah!

@leaf_sanren

啊啊啊啊啊🎉🎉！JEV 黑客松已经出来啦！！！ 同时，我也见到了把 Jev 用得最对的一个项目！！ Jev 这模型最大的特点： 只会判断，一个字都写不了。所以用它的关键，就是别让它干写字的活。 这个开源的「聊天副驾」就很聪明： 你在微信里收到一句"在吗"或者"方案再想想"，它先让 Jev 一秒判出对方真实意图、危险等级 1–9、该马上回还是先晾着； 写回复这活交给另一个会写字的模型起草 3 条，最后再让 Jev 排个序。 判断归判断模型，写字归写字模型。 且它最好的一点：它永远不自动发送。 搞得我都想去闲🐟搞几台吹灰的安卓机啦！ 期待后续也能拿下 iOS、macOS、鸿蒙系统！ https://x.com/AYi_AInotes/status/2102605821456814286/video/2

Erik Kokalj

@erik_kokalj

Another cool demo, specifically for Jev Omni: x.com/erik_kokalj/st…

Artem

@S0RATNIK

Немного упоролся в Jev, но так у меня всегда бывает, когда на чем-то гиперфиксацию поймаю. Вот, например, собрал подборщик нейросетей на базе тех, что есть у OpenRouter, под ваши задачи. Просто пишите, что хотите - получаете подборку нейросетей.

Utkarsh Maheshwari

@utkarshgsuv

Is the Jev hype real, so I made to test this on my movie recommendation engine, which is getting crazy results on Quen Re ranker , I used an open-source alternative of Jev , Laya. But unfortunately Quen is way better, dekhlo! @typesafeai #jev #Jev

Spikez 99.9%

@0xSpikez

Jev Founder, Diogo Amogo, just released 12-page PDF on building a Jev Harness for coding agents this is a 10-step blueprint on how to make your coding agents 200× faster and 400× cheaper: step 1 → meet Jev: the LLM writes, the harness executes, Jev decides what each turn sees, where it routes and whether it runs step 2 → ask the question that breaks every agent: how would you design one if LLMs had no KV cache? step 3 → stop routing blind: Opus → Sonnet → Opus costs 6.19 vs 4.15 for pure Opus, because handing back reprocesses the whole context step 4 → follow the tokens: reading and searching take 56.2% of tool turns and 46.5% of tokens. Writing code is under 10% step 5 → score every chunk per query: hide, short summary, long summary or full. Compress after the question, not before step 6 → disclose tools in tiers: one-line snippets for 100s of tools, schema on demand, docs for one-off queries. Batteries stop costing context step 7 → load instructions by condition: touching *.tsx loads the style guide, billing/ loads its gotchas file, and compaction can't erase either step 8 → route by trust, not just difficulty: secrets and infra stay on first-party frontier models, public docs go to the cheapest one step 9 → share one retrieval pass: cross-model review, eval generation, ELI5 explainers and live progress pages all run read-only in the background step 10 → gate every command: programmable allow / ask / deny policies that read a script before it runs, not just its name Send this PDF and the article below to your Claude Code or Codex instance and start shipping 200× faster.

bays wong

@dennis_huangbei

使用 JEV 玩贪吃蛇、打坦克，弱爆了，刚好前端时间用 astra 写了一个纪念碑谷的关卡foldedrealm.gameai.club，来玩个找不到 dom 的 3d 游戏，能成功算你厉害。截止发帖，已经玩了 15 分钟了，第一个机关都还没正确打开

lemon👑

@lemonDefi1

Laya just mogged Jev at Tetris. The interesting part isn’t just that a local model won. Laya is an open-weights System One model running locally on a 16GB MacBook Air. Jev, meanwhile, is cloud-based and built with Grok 4.7.

Blue007｜Crypto × AI

@blueoli007

JEV integration is not another demo. It feeds live data to one ID with a hard risk cap. The trace after execution is the moat — not the launch graphic.

Xiang Wei

@xgwei

Great minds! I've been building a stylized SF with Opus too, just without the pets. My cars follow rules on the real street network, lanes and traffic lights included. Jev driving pedestrians is tempting though. How many agents can it run at once?

web5kol

@web5_kol

Jev微信聊天助手已开源，可作为手机端对话副驾，帮助用户分析微信群聊和私聊意图。 Jev通过无障碍服务读取屏幕（非侵入式），结合AI模型判断对方真实意图、危险等级，并生成3条候选回复，支持一键填入但不自动发送 x.com/li9292/status/…

emil

@esnx_xyz

you know how x feed is blasting you with promos, politics, rage baits, etc? so i made a (tamper)monkey script that uses jev to classify and hide types of posts you don't want

Jeetendra

@jeetendrayd

Built a walkable 3D street view of where SF/Bay Area startups & VCs actually cluster, every building named, every classification made by Jev.

Kelbie | Sovran

@KevinKelbie

I made a tool with Jev that reads my whole codebase to answer one question: what should I be looking at? Every chunk of code in your project is scored for relevance.

ask

@s5ststtt

買い物コンシェルジュを作っていたら、思ったより面白いものになってきた 最初は 「野菜や食品が今安いか？」 を公的統計＋Jev＋LLMで判断する仕組み。 でも敵対的レビューをかけて改修していたら、本質が変わった。 今作っているのは EvidenceとActionの間に“科学的な昇格条件”を置く仕組み に近い

spect

@spectnfa

The founder of Jev just dropped a 1-hour masterclass on how Jev actually works LLMs → Decisions → Verification → Coding Agents 0% → 0:40 - why LLMs alone aren't enough 25% → 20:27 - the 3 primitives behind Jev 50% → 26:15 - turning huge AI tasks into tiny reliable decisions 75% → 45:04 - real systems: data, agents, verification 100% → 56:33 - the future of coding agents, memory and subagents Most people are still learning prompts. This explains the layer that decides what the model should do, checks whether it worked, and decides what happens next. Basically: how you go from “AI chatbot” to software you can actually trust to run itself. And it's explained by the guy building it. Bookmark this. Watch the full hour tonight. Then read the guide below and steal the architecture for your own agents ↓

Raph Guilhem

@raph_guilhem

Opus 5.5 + Jev = Automatic scoring of 120 competitor ads, shortlisting the 10 worth adapting, and creating versions of each. Both models came out in the recent days, so I tried them together on a marketing use case, playing to what each one is built for: → Claude Opus 5.5 built the pipeline: it found the competitors, ran the http://Pletor.ai workflow "Meta ads spyer", wrote the scoring script and built the interface. → Jev made the judgement calls on every ad The use case: I picked Grüns, the greens gummy brand, as a test case. I pulled 120 ads from 12 of its competitors on the Meta Ad Library, and had Jev score each one on 7 questions: hook, clarity, message, concept fit, tone, angle, health claim risk. Code then combined the scores and picked the 10 worth adapting, and created them, via Pletor MCP.

FrankD

@FrankDa18249347

支撑这个交易机器人的Jev账户快没钱了，我准备把机器人关停后拿最后的Jev额度做一个实验，在polymarket上实盘反买。因为这个机器人亏钱亏的实在是太稳定了，甚至没有一丝起伏，仿佛每个决定都是奔着击穿账户去的，所以我也不打算搞什么dry run了，直接实盘小金额开怼，看看把剩下额度跑完结果如何

Gabriel Pauli

@gabrielpavli

Working on a simple tool that uses JEV to help organise my bookmarks. The UI is awful and it’s nothing crazy, but it’s been nice to learn about JEV and how it works.

Ed Plese

@edplese

Jev but for images? I built a local model to try it out! 63ms for a 512x384 image and fast enough for 15fps video. Birthday 94%. Golden retriever 78%. Sprinkles 93%. Candles lit 67%. Dog about to eat the cake? 52%.

Coach Shweta Bajaj

@shwetabjaj

What stands out to me in the Jev + Grok Bot setup is the division of work: Jev decides. Grok Bot acts. Human stays in control for anything irreversible. That’s a much cleaner agent architecture than asking one model to do everything. Cheaper, faster, and easier to reason about. @typesafeai @grok

kayato

@_kayato

Jev使ってネタバレ防止のChromeアドオン作ってみた。 例） ガンダムシリーズの投稿は見たいけど、閃光のハサウェイの新作のネタバレは見たくないというシチュエーションでのデモ 結構いい感じに動いてる…！これなら不意打ちのネタバレくらわないのでは…！ @typesafeai #Jev

delost

@thedelost

Jev has been blowing up lately. If you already have API access but don't know where to start, just copy this checklist: 1. jev-browser Drives a real headless browser through MCP, CLI or a library. Jev picks one action per step from the page's clickable and typeable elements, and scores whether the goal is met or the run is stuck. https://github.com/jkudish/jev-browser 2. jev-browser-agent Per-step browser decisions at about a second. One request asks "which operation" and "which target" together, and confidence under 0.6 escalates to a bigger model or to you. https://github.com/smartdio/jev-browser-agent 3. typesafe-jev-bridge Zero-dependency OpenAI-compatible bridge. Use typed yes/no, choice and score judgments from Claude Code, Cursor, Cline or any OpenAI SDK, over CLI or HTTP. https://github.com/RevocGG/typesafe-jev-bridge 4. pilot-typesafeai-jev Jev inside LangGraph and Deep Agents. One request asks three questions, plain code picks the route, and only the winning route spends chat model tokens. https://github.com/jyje/pilot-typesafeai-jev 5. building-with-jev-skill An agent skill for writing programs that call Jev: question design, state structure, thresholds, and how to diagnose a question that answers wrong. https://github.com/dbreunig/building-with-jev-skill 6. jev-skill Guided setup plus evaluation workflows, with a read-only presence check and no silent provider switches or fabricated probabilities. https://github.com/wuyoscar/jev-skill 7. awesome-jev Source-backed catalogue of what people actually shipped, sorted by category, with limitations noted per entry. https://github.com/yibie/awesome-jev 8. awesome-typesafe-jev Field guide with SDKs, live demos, agent tools and independent evaluations, including where the vendor numbers came from. https://github.com/AbdelStark/awesome-typesafe-jev 9. awesome-jev-by-typesafe Evidence-backed use cases, patterns and starter code, with the 70 to 500 ms latency claim marked as vendor-reported. https://github.com/Anil-matcha/awesome-jev-by-typesafe 10. awesome-jev (cobanov) The widest catalogue right now: SDKs in Go, Java and JS, MCP connectors, guardrail experiments and studies. https://github.com/cobanov/awesome-jev Copy these complete Jev blueprints - then read the full Jev setup below ↓

silentguy

@silentguyy66

Grok Bot does the job, Jev decides where the job goes next That's the ai company split: a work model and a decision model In this free 22-min tutorial they walk through jev, typesafe's "system one" model that makes decisions instead of chatting You ask one question, Jev answers from a fixed menu: noul, choice, score The demo: customer messages in, frustration score out. usable right in code Not another chat model, it's the fork in the pipeline Grok Bot keeps generating Jev keeps deciding Humans keep the approvals The teams wiring in that third layer are quietly becoming one-person companies Save this before your competitors put a decision layer between their bots

Geek Lite

@QingQ77

把本地 MLX 推理的 Laya 模型和托管 API 的 Jev 放在同一个 T-Rex 跑酷赛道上对打，用延迟、存活和回放数据对比本地推理与云 API。 github.com/virajbhartiya/…

Just AI

@thelazyyogii

上次说的 Jev： 不会陪聊，只负责拍板。 这几天又冒出个 Laya。 活差不多，路子不一样。 一起想成： 流水线上专门判题的人， 不写长文，只答「过不过 / 归哪类」。 Jev = 外面请来的裁判 开箱就能用，按量付钱， 选项多、材料长时更稳。 适合懒得自己搭、先要结果的人。 Laya = 自己厨房里养的裁判 权重能下，Apache 开源，本机跑， 更快更省隐私。 但要自己微调；选项一堆时容易糊。 适合有机器、要数据不出门、愿自己调的人。 一句人话： 不是谁取代谁—— 要省事找 Jev，要自己掌控找 Laya。 都是选择题机器，不是聊天搭子

Jason Torres

@jasontorres

I launched a chatbot yesterday and used JEV as a 17-in-1 router, filter, classifier, intent judge for efficient tool calling. Then further downstream is a relevance/context loop system. Worked really well. No more unwanted spams and prompt injections.

امیرحسین اسلامی

@AHSeslami

اولین تجربه‌ی خودم با JEV 👀 این تجربه برای ۳ روز پیشه؛ وقتی JEV هنوز توی حالت Waiting List بود. من کلاً هر ابزاری که سخت‌افزارم بتونه بکشه رو تست می‌کنم 😄 برای همین توکن JEV رو از OpenRouter گرفتم و به Grok Bot دادم. ماجرا چی بود؟ از GITEX کلی ویدیو گرفته بودم و نمی‌دونستم کدوم‌ها رو اول منتشر کنم. از اون طرف هم برای هرکدوم کلی کاور طراحی کرده بودم و واقعاً حوصله انتخاب و مرتب‌کردنشون رو نداشتم 😂 به JEV گفتم: «خودت انتخاب کن، دسته‌بندی کن و فولدربندی‌شون کن.» در کمتر از چند دقیقه همه‌چیز رو مرتب کرد و حتی پیشنهاد داد کدوم ویدیوها رو اول منتشر کنم. Grok Bot هم بقیه‌ی توضیحات و تحلیل‌ها رو انجام داد. برای اولین تجربه، واقعاً از JEV راضی بودم 🔥 هنوز Laya-Max چینی رو هم تست نکردم؛ نصبش هنوز تموم نشده. اونم که آماده شد، تجربه‌ام رو می‌گم 👀