This site has not written a definition for Jev. The name appears in the feed
but has no stable public identity the desk can verify, so what follows is only what was
recorded — no description, and no claim about what it is.
Jev was recorded in 44 items across 4 of the 8 briefings in the current window.
The earliest mention of it in this window is 16 September 2026; it does not appear in any earlier briefing.
It appeared most often alongside Claude Code, Codex and ChatGPT.
Aaaaaand this is now open-source here: A tiny AI pointer companion for your Mac driven by JEV or Gemini Live - Bring your own keys - Local OmniParser running on CoreML - Jev drives the pointer - Ctrl + K to type a task Voice mode next if people want it!
@milindlabs
Okay so Jev can actually do computer use really well > Without any screenshots, or LLMs and no Pixels leave my mac > I dont even read the Dom elements > A local CoreML model segments every button and UI element on screen. > On-device OCR reads the labels. That text is all Jev gets. > It returns a probability across those elements and tells me the best one to click. > Then it clicks, re-runs detection, and decides again. In a loop until the goal is done. > ~90ms per decision. Faster than any LLM computer use I've tried. > Blazing fast computer use, without any latency > @typesafeai is building something really interesting
We believe voice-controlled computer use, browser and native app use, will improve with the recent launch of @typesafeai 's Jev. Here's @BhosalePratim moving around her machine and tasks using Gradium's voice AI APIs.
This is a Jev-like BioAI model for drug discovery. Insilico is doing fantastic training of these models with their AI gym platform.
@InSilicoMeds
26 drug safety tasks. 1 model. > Potency gets the headlines. Safety decides whether the molecule can become a drug. 🧪 > Our 4B InsilicoMMAI-Chem-ADMET model predicts safety, metabolism and PK endpoints across a single specialist model. > 🚀 SOTA+ on 7 tasks 🧬 Trained on 140K+ datapoints in MMAI Gym for Science > #insilicoSOTAFM
New experiment: json-render + jev > The future Generative UI is instant > Your components, your actions, your design system > Rendered in milliseconds
Jev agent got 1/20 vs 17/20 for BrowserCode + Luna on our long horizon task benchmarks. The speed is INSANE. Feels like early Browser Use.(loads of potential, unsolved problems) Browser use is very complex state space search. Very often you just have to think hard or go back. A model with 0 reasoning ability simply can't do that (yet?). Can we get that behavior with better memory + search, without adding a reasoning model? Really hope I can make this work.
@gregpr07
Breaking: Browser Use + Jev = Ultrafast ⚡ > Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type > (this video is at 1x speed btw) > Built a tiny open source browser agent. try it below ↓
Jev just landed in @usenaive. The interesting part is what you can put it to work inside: a 7-agent agency. Sales -> Content -> Client management -> Site building One config defines the team and its apps. Model routing lets different jobs go to different models. Start with an agency template, connect your stack, keep approval over what gets published. "Deploy a company" is a hell of a button to put on a website ↓
@usenaive
Jev (@typesafeai) is now live in Naïve. > Your agent shouldn't be using the same model for every task > Now it doesn't have to. > Read more at: >
We found the perfect use case for Jev: auto-routing GenAI models. The idea: Jev picks the most cost-effective models for your task, balancing speed and quality. All generations made with Higgsfield API.
@higgsfield
Introducing Higgsfield API. > 50+ frontier models in one API, at lower prices than a subscription. > Get up to 50% OFF discount on your 3 favorite models > Lock in your max-discount within 7 days > Pay per use with no commitment > Build your own Higgsfield with the best prices in GenAI industry. > Available at
JEV JUST READ 384 NEWS STORIES IN 24.9 SECONDS AND FOUND THE BEST ONES FOR 15 BRANDS TO JUMP ON FOR $0.19. THE ENTIRE PR AGENT SETUP IS OPEN SOURCE WITH 30+ SKILLS.
We are getting GLiNER2.5 support in vllm.cpp and in @LocalAI_API , supporting systemone API so you can swap it easily. > GLiNER2.5 went unnoticed until now that Jev is covering the news. Thanks @fastinoAI for making it open source and work in the open.
We release Needle 3: A Sliceable 8-29MB automation foundation model that can match DeepSeek V4 Flash. > One set of weights, every depth from 2 to 20 layers a model of its own, 25-121M parameters at CQ2-bit, built on our Simple Attention Networks and running locally at up to 4k tokens/sec decode speed on a Raspberry Pi 5. > Needle does not chat. Every turn is a function call: give it the tools your app exposes and it picks the right ones and fills every argument from what the user said, or hand it a schema and it returns a typed record. Ask for something no tool covers and you get an empty list, not a guess. > That trad
here is why Jev is essential for any harness you might be using → three question types: choice, score, and a yes/no called noul → ModelRouterMiddleware: Jev picks the least costly model that can do the step → AutoModeMiddleware: Jev scores every bash call before it runs and blocks the risky ones → the same trick Claude Code and Codex run with private classifiers, now a pip install → 200x faster and 400x cheaper than an LLM on classification their own line: "Agents are still inherently untrustworthy." so they put a second model in the loop whose only job is to judge the first one, in milliseconds.if this scales, every harness ships with reflexes.
This sets you up to use @typesafeai Jev in Hermes for model routing, memory filtering, compaction selection, skill selection, computer use, browser use, a private key-entry flow, and a model routing dashboard. Enjoy! 😎 (Maybe useful @Teknium?)
Today I’m excited to show you our new harness called AgentRun, built with @pidotdev and @typesafeai's Jev. It’s built for an agent to learn how to do a job, code itself a general solution, and then get out of the way.
I really want to try out jev, ive seen such cool demos Seems to be the answer to an always awake AI which is token efficient, extremely fast snd cheap to run I’ve requested access, lets see when I get it
JEV JUST TURNED DOOMSCROLLING INTO A 2-SECOND JOB FOR $0.007. PICK A NICHE AND IT FILTERS 3 DAYS OF POSTS TO FIND WHAT’S ACTUALLY WORTH READING.
让 AI 润色技术文档，最怕它为了“去 AI 味”把事实、归因和限制条件给抹了。 新开源的 Jev Humanize Writing 提供了一套实用的防御机制。它本身不直接生成正文，而是一个配合 Claude Code / Codex 使用的 Agent 写作技能 + Python 校验工具。 其核心工作流是“宿主生成候选稿 + Jev 强制校验”： • 防篡改保护：支持传入保护词 JSON，锁定数字、引语和专有名词，保证 AI 润色时原封不动。 • 保留边界与语气：严格守住“初步判断”、“尚未独立验证”等定语，防止模型把严谨结论擅自改写成绝对化的空泛宣传。 • 结构化比对：对多份改稿进行语义诊断并输出 Noul/Score 指标，最终交由宿主逐句复核，而不是盲目覆盖原稿。 • 极简依赖：仅需 Python 3.10+ 标准库，无需 pip install。私密稿件可直接使用纯本地离线模式。 这个工具解决的不是“如何绕过第三方 AI 检测”，而是真正的编辑痛点——在消除机械排比和多余铺垫的同时，确保技术说明、工作邮件和个人笔记的信息密度与立场零损耗。 #jev 🔗 仓库地址：
Most people will use Jev wrong They'll try to replace their main model with it That's not where the value is Jev makes more sense for the tiny decisions inside your agent that happen hundreds of times Those tasks don't need Claude, GPT or another frontier model every single time Setup is simple: Get access at : Install the TypeSafe skill npx skills add typesafe-ai/skills --skill typesafe-ai For Claude Code: claude plugin marketplace add typesafe-ai/skills claude plugin install typesafe@typesafe-ai create your API key Ask your agent to use the TypeSafe skill From there, start replacing basic decision calls with Jev The biggest improvement comes when you use it across the whole agent flow: router → pick gate → validate judge → check result You can also batch many decisions into one request and send uncertain cases back to a larger model. That's the real use case: not replacing intelligence, but removing expensive intelligence from places where you never needed it > [@shann
Browser Use just built an ultrafast open-source browser agent today. Here's what you need to know. Developer Gregor Zunic combined the Browser Use framework with a small model called Jev to search flights end to end. The task took just 7 seconds and cost $0.0039 to run. The agent works differently from typical LLM browser bots. It builds a new action space every step, reads the page's DOM state directly, and only falls back to a small LLM when it needs to type text. Key numbers: - 7 seconds to complete a flight search - $0.0039 cost per run - Jev is described as ~40-200x faster and ~40-400x cheaper than frontier LLMs on this kind of task The code is open source, and a live demo built on Val Town let people try it themselves right after the post went up.
@gregpr07
Breaking: Browser Use + Jev = Ultrafast ⚡ > Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type > (this video is at 1x
Tesla Full Self Driving (Jev demo) is now open source and you can try it online yourself! 👈 try it 👈 keep it
@jpschroeder
I rebuilt Tesla Full Self Driving with Jev in less than an hour. > This model is a total unlock.
ULTRAFAST is coming to Browser Use Cloud ⚡ > superhuman speed > cheap > undetectable Tell us what you’d automate and get on the waitlist ↓
@gregpr07
Breaking: Browser Use + Jev = Ultrafast ⚡ > Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type > (this video is at 1x speed btw) > Built a tiny open source browser agent. try it below ↓
found the perfect use case for @typesafeai Jev: > instant compaction > in 2026, why is compaction still a summarization prompt? > Jev can make it instant by scoring every tool call and dropping what’s irrelevant
Jev from @typesafeai is now live on @CloudflareDev AI Gateway. Try the first System One model — send state and typed questions; get structured answers your code can use directly.
@jackcheng 🤝 @typesafeai Jev This is what AI looks like after the chat box. Jev turns a fuzzy request like “move the blue square to the right of the red diamond” into a structured action in milliseconds. Fast enough that talking to software starts to feel like touching it. What have you built with Jev?
Is it even possible that a traditional LLM beats it in speed? I hope OpenAI releases ultrafast, computer use with Astra's or Sol's intelligence + speed of Jev would be crazy. For me it would be computer use AGI
@trycua
1/ Fast Computer Use is now solved with @typesafeai Jev + Cua Driver. > Available in development preview for macOS, Windows, and Linux. We call it jev-use. > Draft #3943:
🚨 BREAKING: Clone any printing business jev-1.13.0 in @shipper_now can take any app and make it yours: design, code, business plan... you can now oneshot the next duolingo / twitter / airbnb / etc this is THE END of manual vibe coding.
🚨 Open Source Jev BS meter you can use this to analyze any debate / investor call / interview / sales pitch / podcast video fact check live , for example this dario interview cost 60 Jev calls / 111K tokens / $0.0047
@chetaslua
🚨 I gave the Trump vs Kamala debate a live BS meter using Jev > every sentence, both candidates, 5 yes/no questions each > 1,191 Jev calls / 1.18M tokens / 415 ms median total cost : $0.0497 > same questions for both, clips picked by one fixed rule, not a fact-check
Everyone is obsessed with bigger models. The smartest thing this week is a smaller idea. Jev doesn't generate text. It returns a decision. One forward pass, one probability per option, no tokens to wait for. Why this is a big deal for agents - Agents today are painfully serial. Pick a tool, wait. Pick a branch, wait. Retry or abort, wait. everything takes forever Multiple parallel decisions changes the entire architecture. Fan out 50 sub-tasks and score them all at once. Run planning, verification and safety checks in parallel. The LLM stops narrating and starts scheduling. Chain of thought made agents deeper. Typed decisions make them wider. The winning agents won't think harder about one step. They'll think about a thousand steps at the same time. We are shipping this in Abacus AI Agent 🚀
I just open sourced Foreman: a software factory foreman built with @typesafeai's Jev. Coding agents work the factory floor. Foreman watches them, continuously assessing progress, completeness, tests, drift, and verification, and intervenes when needed. GitHub:
🚨 I gave the Trump vs Kamala debate a live BS meter using Jev every sentence, both candidates, 5 yes/no questions each 1,191 Jev calls / 1.18M tokens / 415 ms median total cost : $0.0497 same questions for both, clips picked by one fixed rule, not a fact-check
@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 cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions > AFAICT the shortest path to AI-based economic revolution
holy cheap
@gregpr07
Breaking: Browser Use + Jev = Ultrafast ⚡ > Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type > (this video is at 1x speed btw) > Built a tiny open source browser agent. try it below ↓
Jev from @typesafeai is on AI Gateway. Build agents that decide, route, score, and stop in milliseconds: 𝚊𝚠𝚊𝚒𝚝 𝚎𝚟𝚊𝚕𝚞𝚊𝚝𝚎({ 𝚖𝚘𝚍𝚎𝚕: '𝚝𝚢𝚙𝚎𝚜𝚊𝚏𝚎-𝚊𝚒/𝚓𝚎𝚟', 𝚜𝚝𝚊𝚝𝚎, 𝚚𝚞𝚎𝚜𝚝𝚒𝚘𝚗𝚜, });
congrats to Diogo on a full launch! for more on typesafe: check his aie talk: out now!
@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 cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions > AFAICT the shortest path to AI-based economic revolution
we've been testing a new kind of foundation model @every that doesn't produce words as output, instead it produces probabilities. think of it like a code linter for knowledge work. in our testing it was 25x faster at a cost almost 600x lower than Fable for similar jobs. you can use it as a judge for things like: 1) does this code meet my standards? 2) does this writing contain AI-isms? 3) would i be interested in this tweet? we rarely test new flavors of foundation models that end up being impressive. by @typesafeai is one of them read @hammer_mt's excellent vibe check:
AI is already dodging zombies in Minecraft Someone plugged the new Jev model into Minecraft and it started avoiding zombies on its own as soon as night fell, with no extra prompting. 2 minutes of gameplay used 150K tokens and cost just one cent.
Haha... Literally no one is pacing the frontier - Opus 5.2 in testing - Grok 4.8 ships in a couple of weeks - Jev is a new ultra fast classifier - OpenAI already has Astra+ in testing We continue to accelerate
truncated at source
DAILY AI BRIEF 🗞 — Sept 16 GOOGLE 🔥: - Gemini 3.8 Live and 3.8 Live Extended Thinking are out. 97-language auto-detect, near real-time vision, background tool calling. - Live is in Search Live plus Gemini API public preview. Extended Thinking is in Gemini Live, with Pro/Ultra getting it in Docs, Gmail, and Keep. - Gemini Notebook Voice Mode hits Ultra this week, Pro soon. Mobile voice recorder starts next week for all users, English first. - Interactive Reports for Gemini Notebook roll out to everyone in the coming weeks, plus new quiz formats and 60-second video overviews. OPENAI 🔥: - Sam declared a big ship week, then a much larger wave for DevDay. GPT-6 Sol and Luna are the expected drops. - GPT-5.5 leaves ChatGPT, Work, and Codex on Oct 14. Switch to GPT-5.6 Sol or GPT-6 Astra; the API keeps 5.5. XAI 🔥: - Grok Imagine can now edit text on any image in beta — color, size, font, alignment. - Grok Build 1.0.33: structured MCP JSON, in-UI memory deletes, and long-session checkpoints that survive cleanup.