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 actually insane. Made this real time ad creative generator. It creates ads in real time. Just start typing and Jev will choose a combination of: - All your products - 8 Layouts - 150 Headlines (you can also customize this) - 100 Subheaders - 40 Background Colors... show more

Shiv

57,279 subscribers

23,488 views • 11 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

18 Comments

Parul Gautam11 days ago

Jev is making real-time ad creation look seriously easy. TypeSafe AI is onto something here.

Gabrielle11 days ago

How it works?

Akhil Bisht11 days ago

This is insane 🔥

kore11 days ago

the instant part is jev and that really fast, we'll def need a few more complex layouts to stand out

Shiv11 days ago

Yeah 100%. This was freshly vibed but def lots more possible

kore11 days ago

created this wireframe layouts prototype! uses jev and gemini for chat, have a look!

Sanskriti Naruka11 days ago

Jev just made creative testing feel instant and free.

Apoorv Chaturvedi11 days ago

Cooked🤯🤯

DHRUV BANSAL11 days ago

You normally write ad copy blind, in a doc, and somebody finds out later the headline doesn't fit the box. Here it fills in while you type. No guessing at the length

Elara AI11 days ago

This real-time generator is insane — 8 layouts x 150 headlines x 100 subheaders at effectively $0 per ad is such a cheat code for creative testing

Brjan | AI Builder10 days ago

if it really generates ads instantly, that could save marketers tons of time

Sarthak Shekhawat11 days ago

How did you implement it ? Can you please share some details around that ? Would be interested to know about the same!!

Santosh P 〽️10 days ago

can jev read images?

Markandey Sharma11 days ago

The video being generated in real time makes this even more impressive.

Alek11 days ago

Shiv - is CTR or edit speed the first win?

Michael Godzic6 days ago

the variation count is sexy but its a trap without a kill system. 15k combos means nothing if you cant cut losers in 48 hours. generating more ads is the easy half.. killing the 95% that flop before they bleed budget is the part that actually matters

John K11 days ago

Real-time ad creative that reshapes layout, headline, and color as you type is a strong demo of generative tooling in a practical workflow.

Hikari Senju8 days ago

That speed is impressive. The next quality check is whether the generator keeps product truth, brand rules, and readable copy intact across all those combinations. Omneky’s TASTE BENCH tests those ready-to-run signals across models:

Related Videos

🎬Real Time Video Generator This is insane! A new AI model can generate real-time videos with just one neural network evaluation. It creates 2 seconds of high-quality video (1280x720, 24fps) in real time, making video creation faster and more efficient than ever

🎬Real Time Video Generator This is insane! A new AI model can generate real-time videos with just one neural network evaluation. It creates 2 seconds of high-quality video (1280x720, 24fps) in real time, making video creation faster and more efficient than ever

MayorkingAI

15,551 views • 1 year ago

I was also looking into how we can integrate Jev into a real hardware and I built a custom firmware for my keyboard that predicts and highljghts the next key using Jev. Mostly real time. This is not a simple dummy 2kb model that lives in the board. In my project Jev gets context of the current active app on a screen so it can suggest actual vim commands completion! For real. And a real word endings or even phrases. lmao this experiments are getting out of hand this quite cool

I was also looking into how we can integrate Jev into a real hardware and I built a custom firmware for my keyboard that predicts and highljghts the next key using Jev. Mostly real time. This is not a simple dummy 2kb model that lives in the board. In my project Jev gets context of the current active app on a screen so it can suggest actual vim commands completion! For real. And a real word endings or even phrases. lmao this experiments are getting out of hand this quite cool

Dmitriy Kovalenko

56,086 views • 17 days ago

had fun this weekend designed a typing test and made it real in Figma make! best time to be a designer tbh! you can just make things (share your typing speed, link below)

had fun this weekend designed a typing test and made it real in Figma make! best time to be a designer tbh! you can just make things (share your typing speed, link below)

Ashish

49,695 views • 1 year ago

Wow, TypeSafe AI Jev is a game changer for voice-driven UI. Responsiveness really matters for an experience to 'feel' right, and this certainly does the job! Latency here is not optimal given I'm in London and calling out to us-west. But still, super snappy. In this video, Jamcat is using Pipecat to orchestrate a real-time handover between a command agent (Jev) that drives the UI, and voice agent (PhoneLLM) for handling generations and (not in the video) discussing ideas and session setup with the user.

Wow, TypeSafe AI Jev is a game changer for voice-driven UI. Responsiveness really matters for an experience to 'feel' right, and this certainly does the job! Latency here is not optimal given I'm in London and calling out to us-west. But still, super snappy. In this video, Jamcat is using Pipecat to orchestrate a real-time handover between a command agent (Jev) that drives the UI, and voice agent (PhoneLLM) for handling generations and (not in the video) discussing ideas and session setup with the user.

Jon Taylor

47,493 views • 19 days ago

Just trying out Jev, I made a Chrome extension that: - Listens to your YouTube audio (optional) - Detects if it gets to a sponsor segment - Skips it ➡️➡️➡️ - All in real-time while costing ~$0.005 per video Prototype project, BYOK, open-source:

Just trying out Jev, I made a Chrome extension that: - Listens to your YouTube audio (optional) - Detects if it gets to a sponsor segment - Skips it ➡️➡️➡️ - All in real-time while costing ~$0.005 per video Prototype project, BYOK, open-source:

Tony Dinh

83,143 views • 19 days ago

TypeSafe's new model Jev is everywhere this week, and it doesn't even generate text. It returns decisions: typed scores your code uses directly, in a single pass. We put it to work in a real-time chat moderator, scoring toxicity, frustration, and spam in 300 to 400ms. Then we deployed the Node.js backend on Cloudways Velocity. It runs as a persistent process, so no serverless cold start eats the speed Jev just gave you.

TypeSafe's new model Jev is everywhere this week, and it doesn't even generate text. It returns decisions: typed scores your code uses directly, in a single pass. We put it to work in a real-time chat moderator, scoring toxicity, frustration, and spam in 300 to 400ms. Then we deployed the Node.js backend on Cloudways Velocity. It runs as a persistent process, so no serverless cold start eats the speed Jev just gave you.

Cloudways

26,136 views • 12 days ago

This is actually mind blowing Artificial intelligence can now create musicians and songs in a matter of minutes When you watch this happen in real time and hear the quality, you can hardly believe it

This is actually mind blowing Artificial intelligence can now create musicians and songs in a matter of minutes When you watch this happen in real time and hear the quality, you can hardly believe it

Wall Street Apes

1,709,721 views • 1 year 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

11,667 views • 7 days ago

this ad is 100% AI, now the only limit is your creativity with my ai content system it's possible to generate literally anything while keeping it visually indistinguishable from real video all you need is: - gpt-image-2 - kling 3.0 or Seedance 2.0 and 20mins of free time click below and do not miss on AI gold rush if you're a brand and need AI ads - you know who to DM

MAX

20,087 views • 4 months ago

this is f**king dangerous. someone just open sourced an entire library of ready-made JEV skills for building insane AI agent workflows. instead of building common agent patterns from scratch, you can grab skills for things like: → jev-route for routing tasks → jev-guardrail for adding checks and verification → jev-fanout for running multiple tasks in parallel → reusable skills you can plug into your own workflows the interesting part is that these solve problems you'll run into once your agents start doing more than simple tasks. you don't have to reinvent routing, verification, or parallel execution every time you build a new workflow. save this now. you'll probably need one of these skills the next time you're building an agent and don't want to start from scratch. repo below:

this is f**king dangerous. someone just open sourced an entire library of ready-made JEV skills for building insane AI agent workflows. instead of building common agent patterns from scratch, you can grab skills for things like: → jev-route for routing tasks → jev-guardrail for adding checks and verification → jev-fanout for running multiple tasks in parallel → reusable skills you can plug into your own workflows the interesting part is that these solve problems you'll run into once your agents start doing more than simple tasks. you don't have to reinvent routing, verification, or parallel execution every time you build a new workflow. save this now. you'll probably need one of these skills the next time you're building an agent and don't want to start from scratch. repo below:

MIKE

130,340 views • 9 days ago

Jev is actually insane. We benchmarked it, and the results completely change the game for us: > 500 real-time agents > running in parallel > in a 3D environment The preliminary results are crazy: > 500ms average latency > 35 API calls/s > all with a naive implementation We did 0 optimizations! The bottleneck is not Intelligence latency anymore. It's the first System 1 LLM. Crazy times.

Jev is actually insane. We benchmarked it, and the results completely change the game for us: > 500 real-time agents > running in parallel > in a 3D environment The preliminary results are crazy: > 500ms average latency > 35 API calls/s > all with a naive implementation We did 0 optimizations! The bottleneck is not Intelligence latency anymore. It's the first System 1 LLM. Crazy times.

Cris Lenta

62,519 views • 20 days ago

Watch closely… this is how fast it happens. Don’t wait until it’s you. Get the Safer City app and stay informed in real time. AD @safercityza Safer City Solutions Polycriminality AI Platform

Watch closely… this is how fast it happens. Don’t wait until it’s you. Get the Safer City app and stay informed in real time. AD @safercityza Safer City Solutions Polycriminality AI Platform

Yusuf Abramjee

27,644 views • 6 months ago

Ok this is wild. Microsoft showing a demo where you can use AI to help you play and understand a video game in real time #microsoftevent

Ok this is wild. Microsoft showing a demo where you can use AI to help you play and understand a video game in real time #microsoftevent

Rich DeMuro

296,080 views • 2 years ago

I got a rubik's cube to solve itself with TypeSafe AI 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick. ~4 seconds of model time total. video is slowed down so you can read it!

I got a rubik's cube to solve itself with TypeSafe AI 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick. ~4 seconds of model time total. video is slowed down so you can read it!

Paolo Rosson

207,767 views • 20 days ago

The fact that you can create a video like this in just a few minutes is pretty insane and magical. Anyone can place themselves into any world they want, real or imagined, instantly and soon in real time. The Moore's law of generative AI was right: the quality, resolution, and control of models doubles about every year.

The fact that you can create a video like this in just a few minutes is pretty insane and magical. Anyone can place themselves into any world they want, real or imagined, instantly and soon in real time. The Moore's law of generative AI was right: the quality, resolution, and control of models doubles about every year.

Cristóbal Valenzuela

20,713 views • 5 months ago

Nothing good can come of this. AI can now generate video in real-time. Explainer below. It just feels like this will only be put to bad uses... What say you? Comments welcome.

Nothing good can come of this. AI can now generate video in real-time. Explainer below. It just feels like this will only be put to bad uses... What say you? Comments welcome.

Spencer Kelly

57,480 views • 8 days ago

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

nader dabit

432,993 views • 19 days ago

omg.. this new AI is unbelievable you can animate objects in image by literally dragging it with your mouse.. it's live, in real time, infinite.. and you can move the camera too this is a huge breakthrough for AI video, link in comment here's why its crazy:

omg.. this new AI is unbelievable you can animate objects in image by literally dragging it with your mouse.. it's live, in real time, infinite.. and you can move the camera too this is a huge breakthrough for AI video, link in comment here's why its crazy:

el.cine

137,086 views • 11 months ago