Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Last Friday I joined World Labs' first hackathon around Marble. In three hours, I built a rough prototype called Directed. Generate a world. Create characters. Move through it with your phone like you’re on a real set. Frame shots. Capture images. Use them as seeds for video generation. This...

GregMadison's profile picture

Greg Madisᯅn

9,220 subscribers

54,826 Aufrufe • vor 6 Monaten •via X (Twitter)

KunstBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Added an AR Display to my phone joystick. It smoothly follows your hand's position. You can also switch to a big screen view. It will move along your sight direction and stay static. In future iterations, I will add a dedicated section in the phone app to control it (distance, size, surface snapping, anchoring, etc.). Another thing to try is to replace a video stream with a portal of the game itself. Originally, I started developing this prototype for the Quest platform, but now I realize that it makes more sense in Apple's ecosystem since they already have cross-device mirroring functionality, and what I showed would be a logical extension of their approach. I probably need to rewrite it for Vision Pro 😊
1:11

Added an AR Display to my phone joystick. It smoothly follows your hand's position. You can also switch to a big screen view. It will move along your sight direction and stay static. In future iterations, I will add a dedicated section in the phone app to control it (distance, size, surface snapping, anchoring, etc.). Another thing to try is to replace a video stream with a portal of the game itself. Originally, I started developing this prototype for the Quest platform, but now I realize that it makes more sense in Apple's ecosystem since they already have cross-device mirroring functionality, and what I showed would be a logical extension of their approach. I probably need to rewrite it for Vision Pro 😊

Oleg Frolov

35,822 Aufrufe • vor 1 Jahr

Every time an AI video goes viral, someone asks the same thing: what was the prompt? Usually nobody knows. So I built a tool that finds out: It runs on MOSS-VL, open-weight 11B model (open source on GitHub: Upload a reference clip, it watches it frame by frame and reverse-engineers a generation prompt from what's actually in the video, not a guess. Refine it for a style, then generate something new from it. MOSS-VL is built for continuous video streams. Quantized versions deploy locally on a single RTX 4090, and it can be fine-tuned through LlamaFactory if you need it to understand something specific, like your own product's UI. I used the hosted API here, analyzing an uploaded clip instead of a live stream. Two ways to use it yourself: deploy it locally for real-time stream processing, or grab a free API key and use the hosted API on your own clips. API:
1:23

Every time an AI video goes viral, someone asks the same thing: what was the prompt? Usually nobody knows. So I built a tool that finds out: It runs on MOSS-VL, open-weight 11B model (open source on GitHub: Upload a reference clip, it watches it frame by frame and reverse-engineers a generation prompt from what's actually in the video, not a guess. Refine it for a style, then generate something new from it. MOSS-VL is built for continuous video streams. Quantized versions deploy locally on a single RTX 4090, and it can be fine-tuned through LlamaFactory if you need it to understand something specific, like your own product's UI. I used the hosted API here, analyzing an uploaded clip instead of a live stream. Two ways to use it yourself: deploy it locally for real-time stream processing, or grab a free API key and use the hosted API on your own clips. API:

Manish Kumar Shah

65,991 Aufrufe • vor 4 Tagen

So, I have been watching the video for hours. I am pretty sure I see a gun, I see him doing something in the area of the screwdriver was found and I see a recoil, but first, let's break it down, this first video, I think it is clear he is running with a gun, this looks like the barrel to me. Excuse my poor editing, I was trying to give you an area to look at to see the barrel--inevitably, a cultist will take a still from this video where I prematurely circled the area so you know what area to look, and they will claim "NO GUN" you watch. Anyway, I do not care, first part is proving a gun was on that roof and I clearly see it, do you?
0:58

So, I have been watching the video for hours. I am pretty sure I see a gun, I see him doing something in the area of the screwdriver was found and I see a recoil, but first, let's break it down, this first video, I think it is clear he is running with a gun, this looks like the barrel to me. Excuse my poor editing, I was trying to give you an area to look at to see the barrel--inevitably, a cultist will take a still from this video where I prematurely circled the area so you know what area to look, and they will claim "NO GUN" you watch. Anyway, I do not care, first part is proving a gun was on that roof and I clearly see it, do you?

MR. Xclusive

24,969 Aufrufe • vor 1 Monat

I drove a real car while wearing a VR headset 🤯 This might be one of the wildest driving experiences I’ve ever had with BMW M in Germany. They put me behind the wheel, but instead of the real world, I saw a fully digital racing track through the headset. I was driving on an open airport field, but visually I was fully inside a race. I could still see my real hands, the steering wheel, and the dashboard, but through the windows I saw a virtual world and track. And it’s multiplayer. I was racing against another driver on a different field, and our cars and the map were synchronized between us in real time. Insane tech. It felt surreal. Hard to wrap my head around. I know I’m in a real car, actually driving, but visually I’m in a video game. Crazy. Thanks BMW BMWMotorsport for the demo!
0:57

I drove a real car while wearing a VR headset 🤯 This might be one of the wildest driving experiences I’ve ever had with BMW M in Germany. They put me behind the wheel, but instead of the real world, I saw a fully digital racing track through the headset. I was driving on an open airport field, but visually I was fully inside a race. I could still see my real hands, the steering wheel, and the dashboard, but through the windows I saw a virtual world and track. And it’s multiplayer. I was racing against another driver on a different field, and our cars and the map were synchronized between us in real time. Insane tech. It felt surreal. Hard to wrap my head around. I know I’m in a real car, actually driving, but visually I’m in a video game. Crazy. Thanks BMW BMWMotorsport for the demo!

Ben Geskin

99,877 Aufrufe • vor 5 Monaten

Here is how you turn a #GaussianSplatting into a walkable world with 2 clicks. First of all, do yourself a favour and try out PostShot. The splat you see was created from a 3-minute video taken with my phone. It ran for around 12 hours on a laptop with a 3060, and the output was beyond my expectations! That being said, whatever tool or app you use to create your Splat, you can import it directly into arrival.space from there you can: - Clean it up and compress it thanks to the direct integration with Supersplat Editor - Generate a rough mesh (that you can export with a paid plan and adjust in Blender ) - Explore it freely on the #web or in #VR Make sure to drop your Space in the comments. Would love to see it!
1:29

Here is how you turn a #GaussianSplatting into a walkable world with 2 clicks. First of all, do yourself a favour and try out PostShot. The splat you see was created from a 3-minute video taken with my phone. It ran for around 12 hours on a laptop with a 3060, and the output was beyond my expectations! That being said, whatever tool or app you use to create your Splat, you can import it directly into arrival.space from there you can: - Clean it up and compress it thanks to the direct integration with Supersplat Editor - Generate a rough mesh (that you can export with a paid plan and adjust in Blender ) - Explore it freely on the #web or in #VR Make sure to drop your Space in the comments. Would love to see it!

Gabriele Romagnoli

12,086 Aufrufe • vor 1 Jahr

This is not a videogame. No engine. No 3D models. No code. I built it with 3 tools: Midjourney 8.2 for the character and the world. Seedance 2.5 for every shot. Topaz Astra to upscale it. The trick is not the tools. It's how you prompt. I described the camera like a game camera. Rigid follow distance. Snap turns. A HUD locked to the screen. The model did the rest. Here's what I learned: Lock your character first. One clean character sheet. Reference it in every generation. This is what stops the drift. Prompt the medium, not just the scene. "Gameplay capture" gives you a different image than "cinematic shot". Flat exposure, deep focus, no film grain. That's what makes it read as a game. Fights come out stiff. Everyone takes turns. Tell the model everything happens at once and re-render until it does. Generate short clips. Cut them yourself. Add music in post. You have more control than one long generation will ever give you. Now the bigger picture. Video models are becoming world models. They are learning how things move, react, collide. The gap between "video that looks like a game" and "a game you can play" is closing. Soon you won't prompt a trailer. You'll prompt the game itself. The world, the character, the rules. Then you walk in. When that happens, the engine won't be the skill. Your ability to direct worlds will be.
3:02

This is not a videogame. No engine. No 3D models. No code. I built it with 3 tools: Midjourney 8.2 for the character and the world. Seedance 2.5 for every shot. Topaz Astra to upscale it. The trick is not the tools. It's how you prompt. I described the camera like a game camera. Rigid follow distance. Snap turns. A HUD locked to the screen. The model did the rest. Here's what I learned: Lock your character first. One clean character sheet. Reference it in every generation. This is what stops the drift. Prompt the medium, not just the scene. "Gameplay capture" gives you a different image than "cinematic shot". Flat exposure, deep focus, no film grain. That's what makes it read as a game. Fights come out stiff. Everyone takes turns. Tell the model everything happens at once and re-render until it does. Generate short clips. Cut them yourself. Add music in post. You have more control than one long generation will ever give you. Now the bigger picture. Video models are becoming world models. They are learning how things move, react, collide. The gap between "video that looks like a game" and "a game you can play" is closing. Soon you won't prompt a trailer. You'll prompt the game itself. The world, the character, the rules. Then you walk in. When that happens, the engine won't be the skill. Your ability to direct worlds will be.

Ivan Flugelman — VVSVS™

215,086 Aufrufe • vor 18 Tagen

one of the most beautiful things about OpenAI is that every employee really has a voice. i wanted to capture what it feels like to work here, what our mission means to me, and why you should join us. so i made this video with Codex, shared it with the team, and they felt it was worth producing and sharing with the world. this is our mission. and it’s why i’m here.
1:43

one of the most beautiful things about OpenAI is that every employee really has a voice. i wanted to capture what it feels like to work here, what our mission means to me, and why you should join us. so i made this video with Codex, shared it with the team, and they felt it was worth producing and sharing with the world. this is our mission. and it’s why i’m here.

jason

2,230,103 Aufrufe • vor 1 Monat

IN 1994 SUN MICROSYSTEMS FILMED A WOMAN SWIPING THROUGH A TOUCHSCREEN TABLET AND VIDEO CALLING A COLLEAGUE MID TASK. THE iPAD SHIPPED 16 YEARS LATER shot on 35mm film, more than a hundred engineers and designers on it, set in the year 2004, and here's the thing almost nobody mentions it wasn't allowed to be science fiction, the team had one hard rule, only show things they actually believed could be built, so this wasn't a fantasy reel, it was a spec sheet pretending to be a movie she drags documents with her fingers, talks to the machine, pulls a file from the other side of the world, drops into a live video call without thinking about it, this is a boring afternoon for you now, it was an impossible budget in 1994 the strange part is they weren't dreaming, they were trying to build it, then the company that filmed the future quietly moved on and a different company shipped it a decade and a half later and got called visionary for it nobody stole it, they just forgot it was already designed, down to the gestures your thumbs make every morning you think the touchscreen era started when you first held a phone that felt alive, it was fully storyboarded before some of you were born watch it once and you can't unsee how little we actually invented ↓
12:18

IN 1994 SUN MICROSYSTEMS FILMED A WOMAN SWIPING THROUGH A TOUCHSCREEN TABLET AND VIDEO CALLING A COLLEAGUE MID TASK. THE iPAD SHIPPED 16 YEARS LATER shot on 35mm film, more than a hundred engineers and designers on it, set in the year 2004, and here's the thing almost nobody mentions it wasn't allowed to be science fiction, the team had one hard rule, only show things they actually believed could be built, so this wasn't a fantasy reel, it was a spec sheet pretending to be a movie she drags documents with her fingers, talks to the machine, pulls a file from the other side of the world, drops into a live video call without thinking about it, this is a boring afternoon for you now, it was an impossible budget in 1994 the strange part is they weren't dreaming, they were trying to build it, then the company that filmed the future quietly moved on and a different company shipped it a decade and a half later and got called visionary for it nobody stole it, they just forgot it was already designed, down to the gestures your thumbs make every morning you think the touchscreen era started when you first held a phone that felt alive, it was fully storyboarded before some of you were born watch it once and you can't unsee how little we actually invented ↓

0xbobaa

927,228 Aufrufe • vor 2 Monaten

🎥| “Already I fucking love this city. I love this country. I love the people. This was the first country as a band when I was about, when I was about 19 years old, I think. Um, it was pretty much one of the only countries I've ever been to really outside of the UK. It was the first country as a band. You don't have to cheer for me. I do appreciate it though. It was the first time as a band that, you know, it felt like maybe might have a few fans outside of the UK and I remember that being really, really excited. And I think we were here for about four or five weeks. We actually recorded What Makes You Beautiful. I know you like it but shit song. So... it was so this is, this is one of, there's not many countries that kind of grab me with nostalgia like this. And it's also not many countries that I would go out and have about a two hour walk, which I did yesterday. I'm not much of a walker, but I wanted to get myself out. It was really cool to see. It was really, really cool to see it with this, this country had a massive, massive impression on me as a young lad and I have it to have a lot to thank this country for. So, yeah, thank you. Thank you for being cool. Alright, it's emotional.” Louis Tomlinson on stage at #HDWGHWTStockholm (Via centr_mass)
1:29

🎥| “Already I fucking love this city. I love this country. I love the people. This was the first country as a band when I was about, when I was about 19 years old, I think. Um, it was pretty much one of the only countries I've ever been to really outside of the UK. It was the first country as a band. You don't have to cheer for me. I do appreciate it though. It was the first time as a band that, you know, it felt like maybe might have a few fans outside of the UK and I remember that being really, really excited. And I think we were here for about four or five weeks. We actually recorded What Makes You Beautiful. I know you like it but shit song. So... it was so this is, this is one of, there's not many countries that kind of grab me with nostalgia like this. And it's also not many countries that I would go out and have about a two hour walk, which I did yesterday. I'm not much of a walker, but I wanted to get myself out. It was really cool to see. It was really, really cool to see it with this, this country had a massive, massive impression on me as a young lad and I have it to have a lot to thank this country for. So, yeah, thank you. Thank you for being cool. Alright, it's emotional.” Louis Tomlinson on stage at #HDWGHWTStockholm (Via centr_mass)

World Tomlinson

35,330 Aufrufe • vor 5 Monaten

Fast Company just published a great piece on World Labs , Fei-Fei Li , Marble, and the idea that spatial intelligence / world models may be one of the next big shifts in AI. I was happy to be quoted in the article, but I also wanted to share more context about my own experience with World Labs and Marble, and why this direction is especially interesting to me. My starting point: volumetric capture — For the past few years I’ve been exploring and using volumetric capture and reconstruction (photogrammetry, NeRFs, 3D Gaussian Splats) mostly capturing locations around Montreal. Alleys, museums, urban interiors. I love every step of it: the capture itself, the pipeline, and what can be done with the output. Turning real spaces into real-time explorable systems. I do this personally, sharing explorations here, and professionally as chief technologist, and co-founder of Dpt. Physical reality + generative manipulation — In my work I’m especially drawn to mixing physical reality with generative and digital manipulation: using physical interfaces (light, clay, ink, ... ) to drive generative AI pipelines, building mixed reality prototypes that reshape your surroundings, or starting from real captured spaces and transforming them using tools like Marble. Like many people, I saw the World Labs announcement on Twitter in September 2024, and Marble when it surfaced in early December. But by then, I already had a sense something was coming. The first conversation — As someone deep into volumetric capture and radiance fields, I obviously knew about Ben Mildenhall and his pioneering work on NeRF. To my surprise, Ben reached out to me in late June 2024. He’d been following some of my experiments and wanted to chat about my process and workflows and how I was using this “stuff” creatively. At that point he didn’t share what he was building, but we had a genuinely great conversation about radiance fields, AI, and my work. He was curious about the creative perspective, not just the technical one. When the World Labs announcement dropped a few months later, it all made sense. I understood what Ben had been working on, and why the creative angle mattered to them. Then in August 2025, he invited me to try the Marble beta, and I’ve been experimenting with it since. Experimenting with Marble — The first thing I used Marble for was materializing scene and world concepts during ideation at the studio, and seeing if and how it could fit into our production pipeline. In parallel, I dove into a series of experiments focused on world manipulation: starting from real captured spaces and transforming them using Marble. I’d already been exploring that idea using img2img diffusion with ControlNet on NeRF renders, real-time video streams, and even mixed reality using headset camera feeds. But Marble brings something different. It generates persistent, spatially cohesive 3D worlds that can be rendered in real time across a wide range of devices. That’s a real shift. Experiment 01: Parallel Realities — The first experiment, Parallel Realities, starts from a volumetric capture of a real location, reconstructed as 3D Gaussian Splats. Using Marble, I generate an alternate version of that same space, something informed by the original architecture: abandoned, nature-reclaimed, alternate era. Then, using Spark (World Labs’ 3D Gaussian Splatting renderer for THREE.js) I make both realities coexist in the same spatial coordinate system. From there, I use a portal UX mechanic to let the user step between the real reconstruction and the Marble-generated version. Experiment 02: Hidden Depth The second experiment, Hidden Depth, does not transform a space as much as expand it. A captured location has a visual boundary (a mural, a doorway, a dark corridor) and Marble generates what exists beyond it. For example: a Montreal alley has a painted mural; step through it and you’re inside a world informed by what is actually depicted there. World Labs showcased part of this work here: And in their Spark 2.0 post: The project page is here: Why this matters to me — Being able to start from a real 3D Gaussian Splat scene and manipulate it with Marble opens up a lot of ideas. The 3DGS pipeline is becoming an increasingly compelling foundation for exploration, experimentation, and storytelling. What matters most to me right now is more control. The more I can steer the generated scene or world, the more useful the tool becomes. I want more features like the already existing multiple input images and Chisel, the blockout-based approach. I would like better local control, the ability to expand a generated world more and more while preserving coherence, and the ability to directly import 3D Gaussian Splat scenes to be used as a starting point. I want more ways to shape the result, not just a “prompt and hope” approach. — It is exciting to see this field moving from research and demos toward actual creative workflows.
1:04

Fast Company just published a great piece on World Labs , Fei-Fei Li , Marble, and the idea that spatial intelligence / world models may be one of the next big shifts in AI. I was happy to be quoted in the article, but I also wanted to share more context about my own experience with World Labs and Marble, and why this direction is especially interesting to me. My starting point: volumetric capture — For the past few years I’ve been exploring and using volumetric capture and reconstruction (photogrammetry, NeRFs, 3D Gaussian Splats) mostly capturing locations around Montreal. Alleys, museums, urban interiors. I love every step of it: the capture itself, the pipeline, and what can be done with the output. Turning real spaces into real-time explorable systems. I do this personally, sharing explorations here, and professionally as chief technologist, and co-founder of Dpt. Physical reality + generative manipulation — In my work I’m especially drawn to mixing physical reality with generative and digital manipulation: using physical interfaces (light, clay, ink, ... ) to drive generative AI pipelines, building mixed reality prototypes that reshape your surroundings, or starting from real captured spaces and transforming them using tools like Marble. Like many people, I saw the World Labs announcement on Twitter in September 2024, and Marble when it surfaced in early December. But by then, I already had a sense something was coming. The first conversation — As someone deep into volumetric capture and radiance fields, I obviously knew about Ben Mildenhall and his pioneering work on NeRF. To my surprise, Ben reached out to me in late June 2024. He’d been following some of my experiments and wanted to chat about my process and workflows and how I was using this “stuff” creatively. At that point he didn’t share what he was building, but we had a genuinely great conversation about radiance fields, AI, and my work. He was curious about the creative perspective, not just the technical one. When the World Labs announcement dropped a few months later, it all made sense. I understood what Ben had been working on, and why the creative angle mattered to them. Then in August 2025, he invited me to try the Marble beta, and I’ve been experimenting with it since. Experimenting with Marble — The first thing I used Marble for was materializing scene and world concepts during ideation at the studio, and seeing if and how it could fit into our production pipeline. In parallel, I dove into a series of experiments focused on world manipulation: starting from real captured spaces and transforming them using Marble. I’d already been exploring that idea using img2img diffusion with ControlNet on NeRF renders, real-time video streams, and even mixed reality using headset camera feeds. But Marble brings something different. It generates persistent, spatially cohesive 3D worlds that can be rendered in real time across a wide range of devices. That’s a real shift. Experiment 01: Parallel Realities — The first experiment, Parallel Realities, starts from a volumetric capture of a real location, reconstructed as 3D Gaussian Splats. Using Marble, I generate an alternate version of that same space, something informed by the original architecture: abandoned, nature-reclaimed, alternate era. Then, using Spark (World Labs’ 3D Gaussian Splatting renderer for THREE.js) I make both realities coexist in the same spatial coordinate system. From there, I use a portal UX mechanic to let the user step between the real reconstruction and the Marble-generated version. Experiment 02: Hidden Depth The second experiment, Hidden Depth, does not transform a space as much as expand it. A captured location has a visual boundary (a mural, a doorway, a dark corridor) and Marble generates what exists beyond it. For example: a Montreal alley has a painted mural; step through it and you’re inside a world informed by what is actually depicted there. World Labs showcased part of this work here: And in their Spark 2.0 post: The project page is here: Why this matters to me — Being able to start from a real 3D Gaussian Splat scene and manipulate it with Marble opens up a lot of ideas. The 3DGS pipeline is becoming an increasingly compelling foundation for exploration, experimentation, and storytelling. What matters most to me right now is more control. The more I can steer the generated scene or world, the more useful the tool becomes. I want more features like the already existing multiple input images and Chisel, the blockout-based approach. I would like better local control, the ability to expand a generated world more and more while preserving coherence, and the ability to directly import 3D Gaussian Splat scenes to be used as a starting point. I want more ways to shape the result, not just a “prompt and hope” approach. — It is exciting to see this field moving from research and demos toward actual creative workflows.

Hugues Bruyère

69,960 Aufrufe • vor 2 Monaten

The first LingOrm photo that you keep in your phone Ling: It wasnt taken on my phone, it was taken during fitting of TSOU. I like this one in particular, so I ask them to airdrop me right on the spot! 👤: What come to your mind when you saw it? Ling: I wonder why this pic popped up as our very first ones taken together. I thought the first photo should be a selfie pic but when i look through the screen, i like it very much ITS FAHLADA AND EARN 🥺 PRAEW MAGAZINE X LINGORM #DearMySelfxLingOrm
1:49

The first LingOrm photo that you keep in your phone Ling: It wasnt taken on my phone, it was taken during fitting of TSOU. I like this one in particular, so I ask them to airdrop me right on the spot! 👤: What come to your mind when you saw it? Ling: I wonder why this pic popped up as our very first ones taken together. I thought the first photo should be a selfie pic but when i look through the screen, i like it very much ITS FAHLADA AND EARN 🥺 PRAEW MAGAZINE X LINGORM #DearMySelfxLingOrm

jamie kwong

53,359 Aufrufe • vor 2 Monaten

World Labs co-founders Justin Johnson and Dr. Fei-Fei Li say Atlas unifies the two things computer vision has always kept apart: Justin: "Historically, reconstruction has been its own subfield in computer vision with its own specialized tasks and models. Generation is what all the text-to-video models are really good at." "Those are great for creative applications if I want to imagine something that's never been there before." "But now with Atlas, for the first time, we're putting these two different parts of visual intelligence together in one model. It can do both 3D reconstruction and generation together in one architecture." "We had to make it multimodal from the start. This thing natively works on text, images, videos, and camera poses as a native input to the model... It uses 3D as a native modality that it works on." Fei-Fei: "Computer vision has been around for more than half a century... Our field traditionally has multiple tracks. You go to a computer vision conference: you have the pixel generation track, you have some recognition track, and you have a 3D reconstruction track." "This is an elegant model that unifies the problem of reconstruction and generation by anchoring on viewpoints and viewpoint estimation. That's just incredibly powerful." Justin Johnson Fei-Fei Li
1:52

World Labs co-founders Justin Johnson and Dr. Fei-Fei Li say Atlas unifies the two things computer vision has always kept apart: Justin: "Historically, reconstruction has been its own subfield in computer vision with its own specialized tasks and models. Generation is what all the text-to-video models are really good at." "Those are great for creative applications if I want to imagine something that's never been there before." "But now with Atlas, for the first time, we're putting these two different parts of visual intelligence together in one model. It can do both 3D reconstruction and generation together in one architecture." "We had to make it multimodal from the start. This thing natively works on text, images, videos, and camera poses as a native input to the model... It uses 3D as a native modality that it works on." Fei-Fei: "Computer vision has been around for more than half a century... Our field traditionally has multiple tracks. You go to a computer vision conference: you have the pixel generation track, you have some recognition track, and you have a 3D reconstruction track." "This is an elegant model that unifies the problem of reconstruction and generation by anchoring on viewpoints and viewpoint estimation. That's just incredibly powerful." Justin Johnson Fei-Fei Li

a16z

38,618 Aufrufe • vor 2 Tagen

PJ Tucker says he had four root canals, took no pain medication after, got on a plane for four and a half hours, and played Game 7 Host: “During this Game 6 [Warriors-Rockets series], a bunch of your teeth were cracked” PJ: “So I had four root canals. I had one injection. It was like four and a half hours worth of dental work. And then to fly of four and a half hours. And I didn’t take medication because I don’t like taking it” “I was going through it. But you know what? I didn’t give a sh*t, this is what I’ve dreamed of my entire life. I’m prepared to die out here. Like, there’s no other place in the world I’d rather be. Whether I have all my teeth or none. It was like, it didn’t matter, man” Host: “[You] have the root canals. You go on the plane, you get off, and then you play Game 7” PJ: “Yup”
0:54

PJ Tucker says he had four root canals, took no pain medication after, got on a plane for four and a half hours, and played Game 7 Host: “During this Game 6 [Warriors-Rockets series], a bunch of your teeth were cracked” PJ: “So I had four root canals. I had one injection. It was like four and a half hours worth of dental work. And then to fly of four and a half hours. And I didn’t take medication because I don’t like taking it” “I was going through it. But you know what? I didn’t give a sh*t, this is what I’ve dreamed of my entire life. I’m prepared to die out here. Like, there’s no other place in the world I’d rather be. Whether I have all my teeth or none. It was like, it didn’t matter, man” Host: “[You] have the root canals. You go on the plane, you get off, and then you play Game 7” PJ: “Yup”

katsu

94,156 Aufrufe • vor 1 Monat

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax (official) leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇
1:06

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax (official) leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇

ComfyUI

234,096 Aufrufe • vor 1 Monat

my new song “BREAKDOWN.” is out on the 21st of June!!! 🖤🖤🖤 I wrote this poem because it’s been the hardest year for my mental health. In my life I’ve always never felt good enough, it’s just the thing that’s eaten me up. For as long as I can remember i have felt constantly afraid of how quickly my head can turn dark. It’s always been so hard to fight the darkness that i inevitably have. A lot of people will say it’s a phase and it will go away. But it doesn’t and the reality of the situation is I have to find strategies to deal with it. To put it plainly the things I don’t like about myself will probably never change, people tell me one day I’ll come-to terms with them one day but I want that day to be FUCKING NOW. This song is a message to myself to try and exist alongside my insecurities and my darkness by grounding myself and remembering what is real in life and the world is so much bigger than me. Try and get out of your head and notice the world around you, notice the things and people around you. Connect with them, the chances are they probably feel the same. Don’t let the bullshit inside your head consume you. It just wastes precious time. Remember what is real. Help people, be kind, help the world, help yourself. If you think you can’t do it, you can. You can get through this, trust me. Use this poem in a mornin to get u out of bed, use it when youre about to back out of something last minute, use it when you’re at your darkest. It’s got a little bit of light in it. Don’t forget to put your feet in the grass … Mind
0:55

my new song “BREAKDOWN.” is out on the 21st of June!!! 🖤🖤🖤 I wrote this poem because it’s been the hardest year for my mental health. In my life I’ve always never felt good enough, it’s just the thing that’s eaten me up. For as long as I can remember i have felt constantly afraid of how quickly my head can turn dark. It’s always been so hard to fight the darkness that i inevitably have. A lot of people will say it’s a phase and it will go away. But it doesn’t and the reality of the situation is I have to find strategies to deal with it. To put it plainly the things I don’t like about myself will probably never change, people tell me one day I’ll come-to terms with them one day but I want that day to be FUCKING NOW. This song is a message to myself to try and exist alongside my insecurities and my darkness by grounding myself and remembering what is real in life and the world is so much bigger than me. Try and get out of your head and notice the world around you, notice the things and people around you. Connect with them, the chances are they probably feel the same. Don’t let the bullshit inside your head consume you. It just wastes precious time. Remember what is real. Help people, be kind, help the world, help yourself. If you think you can’t do it, you can. You can get through this, trust me. Use this poem in a mornin to get u out of bed, use it when youre about to back out of something last minute, use it when you’re at your darkest. It’s got a little bit of light in it. Don’t forget to put your feet in the grass … Mind

YUNGBLUD

66,420 Aufrufe • vor 2 Jahren

Old footage sitting in your camera roll could now be reconstructable as a 3D scene. World Labs co-founders Ben Mildenhall and Fei-Fei Li on how Atlas got there: Ben: "In a casual sense... I took three photos of this object, or six photos of this room. I look at the photos, I can understand in my mind how those piece together. I can fill in the gaps and get it." "But there's never really been any reconciliation between those data-driven priors and the brute force dense reconstruction, which is much more akin to scientific or medical imaging... When we say dense, we really mean dense." "This room, I want like 100, 200, 300 photos to capture it. And what we're trying to do is bring that down to like three. We're saying like 50, 100x reduction." "At that scale it completely flips that calculus on its head of what type of captures you reconstruct. You can go back to existing imagery you have. You can go to stuff you find on the internet and even build scenes out of that. You can go to casual videos and unearth a lot of footage that in the past we would never have treated as reconstructable, and bring it to life as 3D." "This is something we've been playing around with a lot with Atlas. Taking old clips. I've taken a bunch of my own old captures that never worked before and put them through the system and seen a reconstruction for the first time." Fei-Fei: "The Stanford demo is underappreciated. Anywhere between 3 to 25 images, you can reconstruct that entire Stanford quad... Everything you see is generated, but according to the laws of reconstruction. And this is really magical." Ben Mildenhall Fei-Fei Li
2:01

Old footage sitting in your camera roll could now be reconstructable as a 3D scene. World Labs co-founders Ben Mildenhall and Fei-Fei Li on how Atlas got there: Ben: "In a casual sense... I took three photos of this object, or six photos of this room. I look at the photos, I can understand in my mind how those piece together. I can fill in the gaps and get it." "But there's never really been any reconciliation between those data-driven priors and the brute force dense reconstruction, which is much more akin to scientific or medical imaging... When we say dense, we really mean dense." "This room, I want like 100, 200, 300 photos to capture it. And what we're trying to do is bring that down to like three. We're saying like 50, 100x reduction." "At that scale it completely flips that calculus on its head of what type of captures you reconstruct. You can go back to existing imagery you have. You can go to stuff you find on the internet and even build scenes out of that. You can go to casual videos and unearth a lot of footage that in the past we would never have treated as reconstructable, and bring it to life as 3D." "This is something we've been playing around with a lot with Atlas. Taking old clips. I've taken a bunch of my own old captures that never worked before and put them through the system and seen a reconstruction for the first time." Fei-Fei: "The Stanford demo is underappreciated. Anywhere between 3 to 25 images, you can reconstruct that entire Stanford quad... Everything you see is generated, but according to the laws of reconstruction. And this is really magical." Ben Mildenhall Fei-Fei Li

a16z

47,384 Aufrufe • vor 4 Tagen

Anish Acharya: We're going to see a "YouTube moment for software": "If you think about YouTube 20 years ago—we had lots of video and lots of television, and it was high production quality, and it wasn't clear that we needed more and 20 years later, YouTube's a $550 billion enterprise that would be one of the biggest companies in the world if it was independent." "I think the same thing is going to happen for software. People want to make software, and for the first time they can—and they can distribute it and they can consume it." "Sometimes it's going to be important software. Sometimes it's going to be totally trivial. It's going to be software for a bachelor party weekend, software for a joke, software for a prompt. We have this sort of seriousness about software that we had about video and television 20 years ago." "Now it's like—I just took a video on my phone. It's going to be like—I just made an app on my phone. Same energy." Anish Acharya on BILLIONS with Guillaume Moubeche
1:30

Anish Acharya: We're going to see a "YouTube moment for software": "If you think about YouTube 20 years ago—we had lots of video and lots of television, and it was high production quality, and it wasn't clear that we needed more and 20 years later, YouTube's a $550 billion enterprise that would be one of the biggest companies in the world if it was independent." "I think the same thing is going to happen for software. People want to make software, and for the first time they can—and they can distribute it and they can consume it." "Sometimes it's going to be important software. Sometimes it's going to be totally trivial. It's going to be software for a bachelor party weekend, software for a joke, software for a prompt. We have this sort of seriousness about software that we had about video and television 20 years ago." "Now it's like—I just took a video on my phone. It's going to be like—I just made an app on my phone. Same energy." Anish Acharya on BILLIONS with Guillaume Moubeche

a16z

102,908 Aufrufe • vor 5 Monaten

Remote Viewer Warns of a Terrifying Coordinated Attack on a Major US City?! Remote Viewer, Daz Smith, looked at April world events and what he got back is potentially concerning... "...So it was large structures, weirdly higher than any of containership. I shouldn't have looked at that a bit more detail, but I didn't. Maybe I just thought it was appropriate, moved it to one side, but definitely large structures." "And it felt like the structures were on fire. So I, you know, asked the question why here? And I felt like there was a ground based attack, that was going to happen in, in, in this city location. And it felt like it was like a bomb attack. And I had, like, this very strong visual of a, white truck or van that might be involved, which I tried to draw here. So the, you know, they had these kind of, modern looking van in front of a, multi-level structure, almost like this, like the entranceway or something of the structure." "So it felt like it was a kinetic event, of lots of explosive energy. It was very loud. There was wide dispersal. Definitely had a terror attack feel. It feels like it was a driven vehicle parts and then detonated, as an act of retaliation. The vehicle fills, larger than a car. Felt very van like, possibly white, possibly have branding on it as well." "...It was strategically positioned, in front of an important structure. The whole thing felt very US based. Just not that weird kind of U.S filled me, getting targets. And I also have a dang tang feel to this as well, so it felt like it was in a large U.S urban city, which gave me the idea of New York. Because maybe because I've been to New York and, you know, just had that, but definitely had an East Coast feel to this..." "...it was definitely driven, implanted..." "...it felt like it was in planning. So they were planning or rehearsing for a future event, which is, you know, what we're looking for, a month ahead. And I had a weird I had a well here, weirdly, of Holy Cross... it starts with fear and panic, and it's like they're just implanting a message.... Trying to timeline this site here. You know, again, this is all very experimental..."
2:09

Remote Viewer Warns of a Terrifying Coordinated Attack on a Major US City?! Remote Viewer, Daz Smith, looked at April world events and what he got back is potentially concerning... "...So it was large structures, weirdly higher than any of containership. I shouldn't have looked at that a bit more detail, but I didn't. Maybe I just thought it was appropriate, moved it to one side, but definitely large structures." "And it felt like the structures were on fire. So I, you know, asked the question why here? And I felt like there was a ground based attack, that was going to happen in, in, in this city location. And it felt like it was like a bomb attack. And I had, like, this very strong visual of a, white truck or van that might be involved, which I tried to draw here. So the, you know, they had these kind of, modern looking van in front of a, multi-level structure, almost like this, like the entranceway or something of the structure." "So it felt like it was a kinetic event, of lots of explosive energy. It was very loud. There was wide dispersal. Definitely had a terror attack feel. It feels like it was a driven vehicle parts and then detonated, as an act of retaliation. The vehicle fills, larger than a car. Felt very van like, possibly white, possibly have branding on it as well." "...It was strategically positioned, in front of an important structure. The whole thing felt very US based. Just not that weird kind of U.S filled me, getting targets. And I also have a dang tang feel to this as well, so it felt like it was in a large U.S urban city, which gave me the idea of New York. Because maybe because I've been to New York and, you know, just had that, but definitely had an East Coast feel to this..." "...it was definitely driven, implanted..." "...it felt like it was in planning. So they were planning or rehearsing for a future event, which is, you know, what we're looking for, a month ahead. And I had a weird I had a well here, weirdly, of Holy Cross... it starts with fear and panic, and it's like they're just implanting a message.... Trying to timeline this site here. You know, again, this is all very experimental..."

Future Forecasting Group

14,822 Aufrufe • vor 5 Monaten

Kevin Bacon says he once disguised himself to see what life was like without fame and it was awful. “I had a disguise built by a special effects makeup artist. What? True. I’m wearing it now.” “People don’t talk about the fact that being recognizable is 99.9% good, because people are nice to you all day long for absolutely no reason. People stop you on the street and say, ‘Kevin, I love you.’ Who doesn’t want to be loved?” “You can get out of tickets, they’ll give you free sneakers and shit like that. It’s mostly good.” “But once in a while, you think, ‘What would it be like to just walk through the world anonymously?’ So I decided to experiment with that, and it worked.” “I went to an outdoor shopping mall in California called the Grove, which is probably the worst place to walk around if you’re a celebrity. I walked straight through, and nobody recognized me it was awful.”
1:35

Kevin Bacon says he once disguised himself to see what life was like without fame and it was awful. “I had a disguise built by a special effects makeup artist. What? True. I’m wearing it now.” “People don’t talk about the fact that being recognizable is 99.9% good, because people are nice to you all day long for absolutely no reason. People stop you on the street and say, ‘Kevin, I love you.’ Who doesn’t want to be loved?” “You can get out of tickets, they’ll give you free sneakers and shit like that. It’s mostly good.” “But once in a while, you think, ‘What would it be like to just walk through the world anonymously?’ So I decided to experiment with that, and it worked.” “I went to an outdoor shopping mall in California called the Grove, which is probably the worst place to walk around if you’re a celebrity. I walked straight through, and nobody recognized me it was awful.”

𝓢𝓵𝓪𝓶 👁️⃤

551,851 Aufrufe • vor 2 Tagen

I am stocked to announce that I won the OpenAI Developers Codex x Mollie Hacka Worldwide Hackathon in Paris. 60+ builders, every one of us working solo, one day to ship. I built mine around a single question: who gets to own intelligence? The default answer is scary. You hand your data to a handful of labs, they train the model, they own it, and you rent back a thin slice of what your own data made possible. That is the bargain on the table today. I do not accept it. So I built Lensemble: a Tapestry like distributed training platform for JEPA based World Models. What does it enable: World Models that a community improves together, keeps sovereign, and co-owns. Two bets sit underneath it. First, the paradigm. Language models predict the next token. Powerful for text, a dead end for the physical world. A robot does not need to autocomplete sentences, it needs to predict what happens next in the world. That is what JEPA does: it learns by predicting representations instead of pixels or tokens. I am convinced world models are the most underrated paradigm in AI right now, and the closest thing we have to a ChatGPT moment for robotics. Second, the politics. Your raw trajectories never leave your machine. Each participant trains locally against a shared protocol and ships only an update, never the data. A federated round folds those updates into one shared world model, a LeWorldModel based model, and the gain is measured, not claimed: a 12k-parameter adapter on a frozen backbone, held-out prediction error down about 12 percent, the model measurably less surprised by the world. Then the upside is split by contribution weight, so the people who improved the model own a share of what it earns. This is the thesis behind Project Tapestry, the AI Alliance and Yann LeCun's push for federated, sovereign frontier AI, carried into world models and robotics. Call it Tapestry for the physical world. All of it built solo, in a single day, with Codex as my pair the whole way. Thank you to OpenAI Codex and Mollie for backing builders who ship real things, and to Boris and the organizing crew for the room and the standard you set. Intelligence the world improves, and the world owns. That is the future I want for my kids, and the one I will keep building.
1:13

I am stocked to announce that I won the OpenAI Developers Codex x Mollie Hacka Worldwide Hackathon in Paris. 60+ builders, every one of us working solo, one day to ship. I built mine around a single question: who gets to own intelligence? The default answer is scary. You hand your data to a handful of labs, they train the model, they own it, and you rent back a thin slice of what your own data made possible. That is the bargain on the table today. I do not accept it. So I built Lensemble: a Tapestry like distributed training platform for JEPA based World Models. What does it enable: World Models that a community improves together, keeps sovereign, and co-owns. Two bets sit underneath it. First, the paradigm. Language models predict the next token. Powerful for text, a dead end for the physical world. A robot does not need to autocomplete sentences, it needs to predict what happens next in the world. That is what JEPA does: it learns by predicting representations instead of pixels or tokens. I am convinced world models are the most underrated paradigm in AI right now, and the closest thing we have to a ChatGPT moment for robotics. Second, the politics. Your raw trajectories never leave your machine. Each participant trains locally against a shared protocol and ships only an update, never the data. A federated round folds those updates into one shared world model, a LeWorldModel based model, and the gain is measured, not claimed: a 12k-parameter adapter on a frozen backbone, held-out prediction error down about 12 percent, the model measurably less surprised by the world. Then the upside is split by contribution weight, so the people who improved the model own a share of what it earns. This is the thesis behind Project Tapestry, the AI Alliance and Yann LeCun's push for federated, sovereign frontier AI, carried into world models and robotics. Call it Tapestry for the physical world. All of it built solo, in a single day, with Codex as my pair the whole way. Thank you to OpenAI Codex and Mollie for backing builders who ship real things, and to Boris and the organizing crew for the room and the standard you set. Intelligence the world improves, and the world owns. That is the future I want for my kids, and the one I will keep building.

abdel

20,169 Aufrufe • vor 2 Monaten