Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Jev is the future

Jack Cheng

12,036 subscribers

1,132,711 views • 1 month ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

37 Comments

Jack Cheng1 month ago

For more about how this model works, check out @hammer_mt’s vibe check

Levi Lais1 month ago

I’m now convinced Jarvis was using Jev

Mike Taylor1 month ago

Ha I guess this is how you caught up to @danshipper in token usage

Jack Cheng1 month ago

@danshipper Most of that usage was from the other demo I’m working on 😈

Vlad Terin1 month ago

Built with Jev-Browser: Jev at 1× speed, drawing live in Excalidraw. No cuts. 1x demo. Just an agent that can actually see what it’s doing 👀 It can also do it in live collab session multiple tabs with an orchetrator

Allie the Icon1 month ago

Oh I LOVE this, I have been dreaming of somebody building something like this with Jev! Love the finger gesture tracking too!

Randy Counsman1 month ago

Bwahaha I’m so excited to mess with Jev

Nathan LeClaire1 month ago

wicked demo

secret asian man1 month ago

Minority Report MS Paint 😮

Carlos E. Perez1 month ago

Don't know what to make of this jev business.

Kieran Klaassen1 month ago

you are the future

em1 month ago

what am i looking at.

Mike Taylor1 month ago

@tldraw 👀

Anon1 month ago

share src pls!

Brian Jordan1 month ago

siiick

necropheus 🇦🇷☀️1 month ago

I NEED to know how you did this because it could be useful to me

Monish Annabheemoju1 month ago

Short takes travel when the audience already feels the gap. For you, is Jev the future of agents, of product UX, or of making classification cheap enough to put everywhere?

COURT1 month ago

This makes me think Jev is going to be absolutely perfect to point it at a library of shadCN components. Then tell Astra “build me a dashboard” Jev automatically is called and knows to use every relevant component from my library inside the page the Astra builds. No more fighting with the AI to get it to use my specific custom library.

Arthur Siu1 month ago

@danshipper What is the best practice to do this? I just got into my trail account!

Jack Cheng1 month ago

@danshipper Honestly just talk to Fable for ideas. The examples of it playing video games really help me see what it could do too

Hermann Saah1 month ago

Absolutely

Hambone Wise1 month ago

I just set this up for editing and it works just as well in instantaneously

Dan Fessler1 month ago

Wait how are you enumerating permutations of actions and parameters for those actions? Wouldn’t that just blow up the choices to an unusable amount?

Jack Cheng1 month ago

Fable worked it out for me, and my understanding is that the model gets a few small separate questions per sentence so it's only a handful of picks. App records where I'm pointing when I say "put" and "that" and "there" so jev is just confirming. It doesn't work perfectly by any means but I was trying to see if it was even possible

Louis Libre ⚡️1 month ago

compujev use

Gates 🦞1 month ago

Please teach me the way!!!

Sky991 month ago

How's the cost?

Jack Cheng1 month ago

Dirt cheap! To run it for a couple minutes like this was, I think, less than a penny?

William Wolf1 month ago

bro what is this wizardry

mirai1 month ago

Awesome demo

Justin.md1 month ago

whoa i have to do this

Brian Jordan1 month ago

@steveruizok

Mike1 month ago

@kieranklaassen I’m having so much fun with it! This is so cool.

AI Mastery Guide1 month ago

jev everywhere lately fr

Reindent1 month ago

Such a cool demo! Thanks for sharing, Jev opens so many new possibilities

Sky991 month ago

This is the best use case I've seen so far!

Grow1 month ago

jev is the future.... hahahah god

Related Videos

Introducing the Jev completions API and Jev Playground. Replace your outdated LLMs with the future of text generation. Also, Jev is now available in our AI gateway, have fun!

Introducing the Jev completions API and Jev Playground. Replace your outdated LLMs with the future of text generation. Also, Jev is now available in our AI gateway, have fun!

Alexandre Pesant

62,515 views • 1 month ago

Jev is a classifier Example: I asked Jev what color is this iPhone Jev gives me this: - 80% orange - 10% red - 10% blue The total is 100. I set 5 options: blue, orange, red, green, and yellow. The question and the options are the schema. Jev does not say "This is orange." It says it is 80% sure. Jev is a decision model

Jev is a classifier Example: I asked Jev what color is this iPhone Jev gives me this: - 80% orange - 10% red - 10% blue The total is 100. I set 5 options: blue, orange, red, green, and yellow. The question and the options are the schema. Jev does not say "This is orange." It says it is 80% sure. Jev is a decision model

The Startup Ideas Podcast (SIP) 🧃

12,999 views • 1 month ago

This week on TezTalks Radio, we catch up with Jev Bjorsell from ecadlabs to talk about Tezos' ongoing evolution at the protocol level. Jev shares how Tezos is maturing into the kind of infrastructure that quietly powers the future—reliable, secure, and invisible by design.

This week on TezTalks Radio, we catch up with Jev Bjorsell from ecadlabs to talk about Tezos' ongoing evolution at the protocol level. Jev shares how Tezos is maturing into the kind of infrastructure that quietly powers the future—reliable, secure, and invisible by design.

Tezos Commons

320,777 views • 1 year ago

FaZe Jev not caring one bit about the FaZe controversy while playing Elden Ring is the most Jev thing 😭

FaZe Jev not caring one bit about the FaZe controversy while playing Elden Ring is the most Jev thing 😭

yoxic

788,593 views • 10 months ago

I am giving away $50,000 for you to compare Jev and GPT 5.6 Sol this weekend! Is Jev overhyped? I will pay for both tokens. Claim link is blow: ⬇️ Some told me Jev is fast but stupid and cannot handle complex tasks. Some told me Jev is genius. In my test, Jev is 40x cheaper and both finished the task. Please think of harder tasks and post and tag me! this is the link:

I am giving away $50,000 for you to compare Jev and GPT 5.6 Sol this weekend! Is Jev overhyped? I will pay for both tokens. Claim link is blow: ⬇️ Some told me Jev is fast but stupid and cannot handle complex tasks. Some told me Jev is genius. In my test, Jev is 40x cheaper and both finished the task. Please think of harder tasks and post and tag me! this is the link:

Xiaoyin Qu

23,565 views • 1 month ago

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

unicode

20,745 views • 1 month ago

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code era. Claude Code is still part of the assistance era - Jev is the next step Jev is x200 faster, x400 cheaper and has 0 hallucination. This is what comes after RLHF" In 17 minutes he explains why every model you use has a human-shaped flaw baked into it and why Jev is better worth more than a $500 Claude Code engineering course watch today, then read how to actually boost yourself x100 with Jev in the post below

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code era. Claude Code is still part of the assistance era - Jev is the next step Jev is x200 faster, x400 cheaper and has 0 hallucination. This is what comes after RLHF" In 17 minutes he explains why every model you use has a human-shaped flaw baked into it and why Jev is better worth more than a $500 Claude Code engineering course watch today, then read how to actually boost yourself x100 with Jev in the post below

Codez

193,792 views • 1 month ago

Jev + Opus 5.5, side by side. same agent. same task. same 60 decisions. Opus-only: $2.24 - 3m 37s Jev + Opus: $0.43 - 1m 15s the difference is who makes the small calls: which tool runs next - Jev is this output good enough - Jev is the goal met - Jev rewrite the refund handler - Opus 57 of 60 decisions never touched Opus. what you're watching: left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning. per decision: $0.032 -> $0.00025. watch the cost counters, not the output. the output is identical. full setup in the post below ↓

Jev + Opus 5.5, side by side. same agent. same task. same 60 decisions. Opus-only: $2.24 - 3m 37s Jev + Opus: $0.43 - 1m 15s the difference is who makes the small calls: which tool runs next - Jev is this output good enough - Jev is the goal met - Jev rewrite the refund handler - Opus 57 of 60 decisions never touched Opus. what you're watching: left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning. per decision: $0.032 -> $0.00025. watch the cost counters, not the output. the output is identical. full setup in the post below ↓

Mahax

19,565 views • 1 month ago

Jev versus GPT 5.6 Luna (low) in chess Jev is white, Luna is black

Jev versus GPT 5.6 Luna (low) in chess Jev is white, Luna is black

Adam Holter

67,703 views • 1 month ago

I turned Jev into an image model…? Presenting Jevinci! The paintings are pure JS, no AI image-gen. Jev predicts every pixel's color in parallel and we paint them. The more confident Jev is in a prediction, the wider the brush. (sped up 4x)

I turned Jev into an image model…? Presenting Jevinci! The paintings are pure JS, no AI image-gen. Jev predicts every pixel's color in parallel and we paint them. The more confident Jev is in a prediction, the wider the brush. (sped up 4x)

Anshu

79,919 views • 1 month ago

jev. (jev.) performing his 2022 track "where's the confetti?" on the mediumsizedbackyard🪴

jev. (jev.) performing his 2022 track "where's the confetti?" on the mediumsizedbackyard🪴

Pigeons & Planes

19,672 views • 1 year ago

Launching Jev on Command Code for free today. Jev x Command Code is super interesting. You can only use Jev in headless mode or Provider API. Also open sourced a mod "cmd-mod-jev-nudge" Use Jev for free to keep your agent running as long as the there's more work to do.

Launching Jev on Command Code for free today. Jev x Command Code is super interesting. You can only use Jev in headless mode or Provider API. Also open sourced a mod "cmd-mod-jev-nudge" Use Jev for free to keep your agent running as long as the there's more work to do.

Ahmad Awais

34,780 views • 1 month ago

This is why Jev is so fast.

This is why Jev is so fast.

Gaurav Sen

23,772 views • 1 month ago

'Jev' plays Pac-Man steered by Astra. 1. Astra strategizes 2. 'Jev' carries out the strategy in milliseconds It's early and hard to wrap my head around, but the potential is there to combine 'Jev' with larger reasoning models. For sure.

'Jev' plays Pac-Man steered by Astra. 1. Astra strategizes 2. 'Jev' carries out the strategy in milliseconds It's early and hard to wrap my head around, but the potential is there to combine 'Jev' with larger reasoning models. For sure.

Dan McAteer

92,139 views • 1 month ago

This is absolutely insane. A Stanford AI research group joints JEV with Claude Code to sort 100+ billion data points every 15 minutes. the trick is stupidly simple: JEV runs a cheap first pass on everything. Claude only gets the hard cases. so instead of: everything -> Claude -> $$$ it’s: everything -> JEV filters -> hard stuff -> Claude thinks the boring stuff never touches the expensive model. Claude gets a tiny pile that actually deserves deeper analysis. faster. cheaper. way less compute burned. basically, JEV sorts the mail so the genius only opens what matters. LLMs think, JEV decides Read the full Jev setup guide in the article below:

This is absolutely insane. A Stanford AI research group joints JEV with Claude Code to sort 100+ billion data points every 15 minutes. the trick is stupidly simple: JEV runs a cheap first pass on everything. Claude only gets the hard cases. so instead of: everything -> Claude -> $$$ it’s: everything -> JEV filters -> hard stuff -> Claude thinks the boring stuff never touches the expensive model. Claude gets a tiny pile that actually deserves deeper analysis. faster. cheaper. way less compute burned. basically, JEV sorts the mail so the genius only opens what matters. LLMs think, JEV decides Read the full Jev setup guide in the article below:

rody

114,820 views • 1 month ago

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Hanako

29,894 views • 1 month ago

Today we're launching Jev is our latest model, state of the art in zero-shot learning and real-time reasoning. For the next 10 hours, Jev is available live at 100% uptime. $5 per query.

Today we're launching Jev is our latest model, state of the art in zero-shot learning and real-time reasoning. For the next 10 hours, Jev is available live at 100% uptime. $5 per query.

Alex

52,389 views • 1 month ago

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code or Codex era, they are still part of the assistance era with human in the loop - JEV is what comes next for LLMs x200 faster, x400 cheaper, 0 hallucination, no human in the loop - that's JEV, this is how LLMs will look like" in 36-minute tech talk, Jev Founder explained why RLHF isn't a thing anymore and how modern LLMs will be built this talk is worth more than a Stanford Machine Learning degree watch today no matter what, then learn how to become a Jev Engineer in the article below

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code or Codex era, they are still part of the assistance era with human in the loop - JEV is what comes next for LLMs x200 faster, x400 cheaper, 0 hallucination, no human in the loop - that's JEV, this is how LLMs will look like" in 36-minute tech talk, Jev Founder explained why RLHF isn't a thing anymore and how modern LLMs will be built this talk is worth more than a Stanford Machine Learning degree watch today no matter what, then learn how to become a Jev Engineer in the article below

Codez

468,201 views • 1 month ago

Jev dropped barely a week ago and traders are already doing some wild sh*t with it. live order books. real-time signals. trading bots. entire AI hedge funds. here's what happened: > jev-trader · every ~0.3s asks Jev “buy or sell?” on Monad and trades > jev-trade · reads Hyperliquid order book -> Jev picks -> code sends the order > beebots · 3 OKX trading “bees”; every choice is Jev (paper trading by default) > QuantDinger · full AI trading OS; optional Jev gate = “should we trade at all?” > ai-hedge-fund · multi-agent “fund” with a Jev adapter for fast yes/no calls and that’s the funny part: Jev isn’t here to think. it’s here to make the call. the market moves -> Jev picks LONG / SHORT / HOLD -> code executes. no essays. no chain of thought. no expensive model debating every tiny market move. big models figure out the strategy. Jev handles the split-second calls. code makes it real.

Jev dropped barely a week ago and traders are already doing some wild sh*t with it. live order books. real-time signals. trading bots. entire AI hedge funds. here's what happened: > jev-trader · every ~0.3s asks Jev “buy or sell?” on Monad and trades > jev-trade · reads Hyperliquid order book -> Jev picks -> code sends the order > beebots · 3 OKX trading “bees”; every choice is Jev (paper trading by default) > QuantDinger · full AI trading OS; optional Jev gate = “should we trade at all?” > ai-hedge-fund · multi-agent “fund” with a Jev adapter for fast yes/no calls and that’s the funny part: Jev isn’t here to think. it’s here to make the call. the market moves -> Jev picks LONG / SHORT / HOLD -> code executes. no essays. no chain of thought. no expensive model debating every tiny market move. big models figure out the strategy. Jev handles the split-second calls. code makes it real.

kiosa

111,388 views • 1 month ago

this is unreal f*cking gold for Jev builders 20 repos people are building on Jev right now. browser agents, context tools, trading bots, even a drone 1. JEV-Ultrafast - a browser agent built for speed ↳ 2. Fast-JEV-Compaction - squeezes your context down ↳ 3. JSON-Render - UI generated on the fly ↳ 4. Typesafe-MCP - plugs Jev into any client ↳ 5. JEV-MCP - a toolkit for judgment calls ↳ 6. Semdecide - a classifier right in your terminal ↳ 7. JEV-Codex-Router - sends every task to the model that fits it ↳ 8. Winnow - clears the junk out of your context ↳ 9. JEV-Review - sorts code reviews by what needs eyes first ↳ 10. Blink - finds your way around any repo ↳ 11. Agent-Desktop - runs your desktop for you ↳ 12. Typesafe-Mario - an agent playing Super Mario ↳ 13. JEV-Drone - flies a drone ↳ 14. OneVOneJev - a shooter in your browser ↳ 15. JEV-Trader - high-frequency market making ↳ 16. Prism - spots liquidity signals ↳ 17. Neo4Jev - walks a knowledge graph ↳ 18. JEV-Curate - screens training data ↳ 19. Canny - confirms a task is really finished ↳ 20. KillMyIdea - scores a startup idea before you sink time into it ↳ start where your work is: > coding -> JEV-Review, Blink, Canny, JEV-Codex-Router > context -> Fast-JEV-Compaction, Winnow > automation -> JEV-Ultrafast, Agent-Desktop > clients and tools -> Typesafe-MCP, JEV-MCP, Semdecide > UI -> JSON-Render > trading -> JEV-Trader, Prism > data -> Neo4Jev, JEV-Curate > founders -> KillMyIdea > for fun -> Typesafe-Mario, OneVOneJev, JEV-Drone pick one, build on it this week, and you'll be the person on your team who actually knows Jev engineering when it gets asked for

this is unreal f*cking gold for Jev builders 20 repos people are building on Jev right now. browser agents, context tools, trading bots, even a drone 1. JEV-Ultrafast - a browser agent built for speed ↳ 2. Fast-JEV-Compaction - squeezes your context down ↳ 3. JSON-Render - UI generated on the fly ↳ 4. Typesafe-MCP - plugs Jev into any client ↳ 5. JEV-MCP - a toolkit for judgment calls ↳ 6. Semdecide - a classifier right in your terminal ↳ 7. JEV-Codex-Router - sends every task to the model that fits it ↳ 8. Winnow - clears the junk out of your context ↳ 9. JEV-Review - sorts code reviews by what needs eyes first ↳ 10. Blink - finds your way around any repo ↳ 11. Agent-Desktop - runs your desktop for you ↳ 12. Typesafe-Mario - an agent playing Super Mario ↳ 13. JEV-Drone - flies a drone ↳ 14. OneVOneJev - a shooter in your browser ↳ 15. JEV-Trader - high-frequency market making ↳ 16. Prism - spots liquidity signals ↳ 17. Neo4Jev - walks a knowledge graph ↳ 18. JEV-Curate - screens training data ↳ 19. Canny - confirms a task is really finished ↳ 20. KillMyIdea - scores a startup idea before you sink time into it ↳ start where your work is: > coding -> JEV-Review, Blink, Canny, JEV-Codex-Router > context -> Fast-JEV-Compaction, Winnow > automation -> JEV-Ultrafast, Agent-Desktop > clients and tools -> Typesafe-MCP, JEV-MCP, Semdecide > UI -> JSON-Render > trading -> JEV-Trader, Prism > data -> Neo4Jev, JEV-Curate > founders -> KillMyIdea > for fun -> Typesafe-Mario, OneVOneJev, JEV-Drone pick one, build on it this week, and you'll be the person on your team who actually knows Jev engineering when it gets asked for

Mr. Buzzoni

12,303 views • 1 month ago