Loading video...

Video Failed to Load

Go Home

Messing around with TypeSafe AI Jev for real-time styling 🔤 🔜 🎨 If you can define a bounded, semantically meaningful property space, you can project a natural language expression into that space in one generation step

GitHubNext's profile picture

GitHub Next

27,336 subscribers

12,331 views • 2 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

3 Comments

Eason — building LTA's profile picture
Eason — building LTA2 days ago

@typesafeai This framing is way more interesting than “just another fast model.” Constraining the output space turns natural language into a much cleaner decision primitive for agents.

ᕈablo ᑕarrera (パブロ)'s profile picture
ᕈablo ᑕarrera (パブロ)2 days ago

@typesafeai whaaaaaaaaasp

YCM Jason's profile picture
YCM Jason2 days ago

@typesafeai that is so creative and cool!

Related Videos

See how can help you with your new project in the #web3, #ai, #crypto, #blockchain space! Reach out today for a free consultation!
1:09

See how can help you with your new project in the #web3, #ai, #crypto, #blockchain space! Reach out today for a free consultation!

DrCryptoCA

136,907 views • 2 years ago

Google Gemini: Talki – An AI language learning app that helps you learn a language where you can talk with an AI in different scenarios and you get real time feedback.
0:27

Google Gemini: Talki – An AI language learning app that helps you learn a language where you can talk with an AI in different scenarios and you get real time feedback.

Lovable

87,176 views • 1 year ago

I built a browser extension with Jev TypeSafe AI that can hide/collapse posts on X based on natural language. It's so fast that it's not noticeable and insanely cheap...this must be the future of "ad blockers" and content firewalls.
0:45

I built a browser extension with Jev TypeSafe AI that can hide/collapse posts on X based on natural language. It's so fast that it's not noticeable and insanely cheap...this must be the future of "ad blockers" and content firewalls.

Marcel Pociot 🧪

76,990 views • 4 days ago

“Math is code. And code is math.” Carina Hong CEO Axiom on why that idea matters for AI: “For centuries, mathematicians reasoned in natural language. But because of the Curry–Howard correspondence, a proof can also be a program.” “You can translate natural-language math into formal code using systems like Lean. Lean is both a theorem-proving language and a programming language.” “That means you can generate solutions as code and then formally verify them. You can even use the same system to verify programs themselves.” “This creates a flywheel of generation and verification, where AI can both write solutions and prove that they’re correct.”
2:25

“Math is code. And code is math.” Carina Hong CEO Axiom on why that idea matters for AI: “For centuries, mathematicians reasoned in natural language. But because of the Curry–Howard correspondence, a proof can also be a program.” “You can translate natural-language math into formal code using systems like Lean. Lean is both a theorem-proving language and a programming language.” “That means you can generate solutions as code and then formally verify them. You can even use the same system to verify programs themselves.” “This creates a flywheel of generation and verification, where AI can both write solutions and prove that they’re correct.”

Forward Future

24,729 views • 7 months ago

If you can forgive those you think played a major role in a situation, you can move that situation out of your space with your words. The mountain is not the issue. Forgiving is the real mountain.
0:54

If you can forgive those you think played a major role in a situation, you can move that situation out of your space with your words. The mountain is not the issue. Forgiving is the real mountain.

POJU OYEMADE

10,335 views • 1 year ago

Did you know you can soon have a conversation with a painting? 🎨 Alibaba’s Qwen Glasses are driving innovation in immersive cultural experiences through a strategic partnership with the China Art Museum. This collaboration brings agentic AI directly into the gallery space.
0:25

Did you know you can soon have a conversation with a painting? 🎨 Alibaba’s Qwen Glasses are driving innovation in immersive cultural experiences through a strategic partnership with the China Art Museum. This collaboration brings agentic AI directly into the gallery space.

Alibaba Group

8,309,764 views • 4 months ago

Messing around with my android phone and codex. It’s kinda crazy that you can plug a phone into your computer and AI can start hacking on it immediately. We’ll see if I can get the phone controlling itself
0:28

Messing around with my android phone and codex. It’s kinda crazy that you can plug a phone into your computer and AI can start hacking on it immediately. We’ll see if I can get the phone controlling itself

plotchy🔅

14,021 views • 1 month ago

Maybe one day you too can experience space. It’s a guy in green suit that tries to finger you
1:42

Sensitive content

Maybe one day you too can experience space. It’s a guy in green suit that tries to finger you

Owen Benjamin 🐻

26,397 views • 7 months ago

Update on my new #threejs project, Lumen Decor Studio. With Screen Space Global Illumination and Screen Space Reflection in action, clients can visualize, in real time, how light can influence a room's decor and how the chosen colors blend with the light to create a cozy atmosphere. Next step: color selection behavior😍 Live link soon #creativecoding #tsl #rf3 #webgpu #threejsJourney
2:21

Update on my new #threejs project, Lumen Decor Studio. With Screen Space Global Illumination and Screen Space Reflection in action, clients can visualize, in real time, how light can influence a room's decor and how the chosen colors blend with the light to create a cozy atmosphere. Next step: color selection behavior😍 Live link soon #creativecoding #tsl #rf3 #webgpu #threejsJourney

Anderson Mancini

150,161 views • 11 months 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
0:35

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

50,292 views • 1 day ago

Be honest - if you were a NASA astronaut, orbiting at 17,500mph in a Tin can ‘Space’ Station - surrounded by electronic equipment needed for your survival, would you really be playing around with loose water in zero gravity?
0:26

Be honest - if you were a NASA astronaut, orbiting at 17,500mph in a Tin can ‘Space’ Station - surrounded by electronic equipment needed for your survival, would you really be playing around with loose water in zero gravity?

Concerned Citizen

191,133 views • 8 months ago

ELON MUSK: If you want million times more energy, then you must go to space "The way to think of AI in space is that in order to achieve any meaningful percentage of a Kardashev Type 2 civilization, where you are using even a millionth of the sun's energy, you must have solar-powered AI satellites in deep space Once you think in terms of a Kardashev Type 2 civilization, which is 'what percentage of the sun's energy are you turning into useful work,' then it becomes obvious that space is overwhelmingly what matters Earth only receives roughly one two-billionth of the sun's energy. So, if you want to have something that is, say, a million times more energy than Earth could possibly produce, you must go into space. And so, it’s kind of handy to have a space company, I guess"
1:00

ELON MUSK: If you want million times more energy, then you must go to space "The way to think of AI in space is that in order to achieve any meaningful percentage of a Kardashev Type 2 civilization, where you are using even a millionth of the sun's energy, you must have solar-powered AI satellites in deep space Once you think in terms of a Kardashev Type 2 civilization, which is 'what percentage of the sun's energy are you turning into useful work,' then it becomes obvious that space is overwhelmingly what matters Earth only receives roughly one two-billionth of the sun's energy. So, if you want to have something that is, say, a million times more energy than Earth could possibly produce, you must go into space. And so, it’s kind of handy to have a space company, I guess"

X Freeze

84,037 views • 10 months ago

You can now copy & paste the real world, with hyper-realistic detail. All with just a $299 headset. With Hyperscape you can capture your real-world space in just minutes, then creates an immersive, true-to-life digital replica that you can visit from anywhere. Check the thread for some ridiculously good scans 👇
1:10

You can now copy & paste the real world, with hyper-realistic detail. All with just a $299 headset. With Hyperscape you can capture your real-world space in just minutes, then creates an immersive, true-to-life digital replica that you can visit from anywhere. Check the thread for some ridiculously good scans 👇

Jake Steinerman 🌎

29,722 views • 11 months ago

"Caitlyn Jenner you can survive it all. If you can live with the Kardashians for decades under one roof, in a house, you can survive anything!" Link Lauren "never expected" getting real time Israel updates from Caitlyn Jenner in a bunker! Watch:
2:17

"Caitlyn Jenner you can survive it all. If you can live with the Kardashians for decades under one roof, in a house, you can survive anything!" Link Lauren "never expected" getting real time Israel updates from Caitlyn Jenner in a bunker! Watch:

Spot On with Link Lauren

10,812 views • 1 year ago

Signal lost.. in space 🚨📶 What do you do when you lose signal to your camera that is currently in outer space? Well, the Dorothy Project team had a plan for that...（📸IG: the_dorothy_project with Insta360 Titan） #Insta360 #Insta360Stories #Insta360Titan #Space
0:59

Signal lost.. in space 🚨📶 What do you do when you lose signal to your camera that is currently in outer space? Well, the Dorothy Project team had a plan for that...（📸IG: the_dorothy_project with Insta360 Titan） #Insta360 #Insta360Stories #Insta360Titan #Space

Insta360

21,992 views • 6 months ago

AI is opening St Peter’s Basilica to the world, including a new generation, in a language that is more accessible for the times we live in. What a privilege and honor to partner with the Vatican on this important project. You can visit here: yves ubelmann Vatican News
1:00

AI is opening St Peter’s Basilica to the world, including a new generation, in a language that is more accessible for the times we live in. What a privilege and honor to partner with the Vatican on this important project. You can visit here: yves ubelmann Vatican News

Brad Smith

15,123 views • 1 year ago

If you didn't feel the ongoing revolution, here is my second project I built with jev. Your software is drastically outdated. It contains a lot of instructions your CPU executes one by one. Why if we can simply ask Jev for the next instructions to execute Introducing Jevassembler! It is a new approach to execute something on CPU. You don't need to wait for code to be written, you don't need to compile anything and YOU DON'T NEED CODE. You just give it a task and Jev predicts the next instruction to execute. In runtime. who needs compilers if you have AI
0:28

If you didn't feel the ongoing revolution, here is my second project I built with jev. Your software is drastically outdated. It contains a lot of instructions your CPU executes one by one. Why if we can simply ask Jev for the next instructions to execute Introducing Jevassembler! It is a new approach to execute something on CPU. You don't need to wait for code to be written, you don't need to compile anything and YOU DON'T NEED CODE. You just give it a task and Jev predicts the next instruction to execute. In runtime. who needs compilers if you have AI

Dmitriy Kovalenko

210,866 views • 1 day ago

well THAT'S neat! you can replace triangular walls with full walls. if you replace both triangular walls in the same space you can combine structure types. if you combine a japanese door with a window, you get a window you can close. combine two doors to get a double-locked door.
0:53

well THAT'S neat! you can replace triangular walls with full walls. if you replace both triangular walls in the same space you can combine structure types. if you combine a japanese door with a window, you get a window you can close. combine two doors to get a double-locked door.

All-bones Jones💀Skeleton Vtuber

74,954 views • 1 month ago

One of the small projects I've been messing around with in Unity3D. A fate worse than simple termination. You're given the illusion of hope. Can you escape in time?
0:30

One of the small projects I've been messing around with in Unity3D. A fate worse than simple termination. You're given the illusion of hope. Can you escape in time?

JamesMason0

14,893 views • 22 days 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!
0:34

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

205,938 views • 4 days ago