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.

ML SHARP is an exciting example of how far single Image 3D inference has come🤯 At KIRI Engine, our focus has always been slightly different🌍🌕 We build tools for capturing the physical world as it is, not approximating it📷 When real world accuracy, editability, and geometric consistency matter, reliable... show more

KIRI Engine - 3D Scanner App

5,018 subscribers

27,217 views • 7 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

no matter how often i listen to junkyu's voice, it still gives me chills for how beautiful it is. it's the way how he's able to convey different emotions and feel every notes for different songs is so admiring. it's why the song he sings always have the element of surprise everytime— they always sound different despite it's the same voice we listen to. not only he has a golden voice, he also has a voice that speaks to the soul. kim junkyu, you're truly one of a kind 🩷

no matter how often i listen to junkyu's voice, it still gives me chills for how beautiful it is. it's the way how he's able to convey different emotions and feel every notes for different songs is so admiring. it's why the song he sings always have the element of surprise everytime— they always sound different despite it's the same voice we listen to. not only he has a golden voice, he also has a voice that speaks to the soul. kim junkyu, you're truly one of a kind 🩷

s a l ♡༘ semi ia

23,051 views • 1 year ago

🚨🎙️Ishow speed says that Messi had it easy and FIFA has always rigged the World Cup and always favored him that is why Ronaldo is the Goat 🗣️I respect lionel Messi, he is a legend, BUT HOW are people acting like bro had the hardest career ever when he stayed in basically ONE league for MOST of his life Barcelona Like c’monnnn. Meanwhile Ronaldo was out here proving himself in England, Spain, Italy, different systems, different teams, different pressure EVERY TIME he conquers it 🗣️And don’t even get me STARTED on that World Cup ,Everybody acting like it was some perfect fairy tale ending… man FIFA really wanted that movie script BAD penalties everywhere, storyline too perfect and we all know that 🗣️You can disagree if you want but in MY BOOK… Ronaldo is the GOAT 🐐 Different leagues. Different challenges. Different mentality. Different grind. THAT’S greatness

🚨🎙️Ishow speed says that Messi had it easy and FIFA has always rigged the World Cup and always favored him that is why Ronaldo is the Goat 🗣️I respect lionel Messi, he is a legend, BUT HOW are people acting like bro had the hardest career ever when he stayed in basically ONE league for MOST of his life Barcelona Like c’monnnn. Meanwhile Ronaldo was out here proving himself in England, Spain, Italy, different systems, different teams, different pressure EVERY TIME he conquers it 🗣️And don’t even get me STARTED on that World Cup ,Everybody acting like it was some perfect fairy tale ending… man FIFA really wanted that movie script BAD penalties everywhere, storyline too perfect and we all know that 🗣️You can disagree if you want but in MY BOOK… Ronaldo is the GOAT 🐐 Different leagues. Different challenges. Different mentality. Different grind. THAT’S greatness

Hk🐐🇵🇹🇯🇵

268,384 views • 1 month ago

It's so cool how v0 + Supabase make it easy for scientists to build their own software 🧪💻 Today we ran an internal hackathon at Adaptyv Bio where we "forced" everyone to use AI tools like v0 & co to solve problems we have in our lab Our head of biosensing, who at 49 y/o has never coded in his life, built himself an app to inspect protein binding curves. Took 30 minutes and what would've been an annoying analysis with excel is now a matter of seconds

It's so cool how v0 + Supabase make it easy for scientists to build their own software 🧪💻 Today we ran an internal hackathon at Adaptyv Bio where we "forced" everyone to use AI tools like v0 & co to solve problems we have in our lab Our head of biosensing, who at 49 y/o has never coded in his life, built himself an app to inspect protein binding curves. Took 30 minutes and what would've been an annoying analysis with excel is now a matter of seconds

Julian Englert

18,289 views • 1 year ago

I'm using GPT Image 2 to create a video concept for a weapon selection screen for CHILD OF THE SOIL. When I initially made the short film I always envisioned this as an open world hack and slash video game inspired by my own continent of Africa. As an avid gamer I wanted to just quickly envision different weapons Nyoni can use as she traverses the world. Of course there is no video game here, it's just a rough idea presented purely as a video. The video sequence is just cycling through 4 different images and I used Seedance 2.0 omni to generate the video. I added music in post. Prompt: A static shot shows a video game menu screen. During the sequence it selects different weapons. It selects all 4 different weapon types. Ensure the item in her hand changes to show the selected item. Every time a weapon is selected she poses and analyzes it. The wooden animal next to her is looking around. Do not change any text. No music, only sound fx when the weapons change. No dialogue.

I'm using GPT Image 2 to create a video concept for a weapon selection screen for CHILD OF THE SOIL. When I initially made the short film I always envisioned this as an open world hack and slash video game inspired by my own continent of Africa. As an avid gamer I wanted to just quickly envision different weapons Nyoni can use as she traverses the world. Of course there is no video game here, it's just a rough idea presented purely as a video. The video sequence is just cycling through 4 different images and I used Seedance 2.0 omni to generate the video. I added music in post. Prompt: A static shot shows a video game menu screen. During the sequence it selects different weapons. It selects all 4 different weapon types. Ensure the item in her hand changes to show the selected item. Every time a weapon is selected she poses and analyzes it. The wooden animal next to her is looking around. Do not change any text. No music, only sound fx when the weapons change. No dialogue.

Travis Davids

37,400 views • 4 months ago

Seedance 2.0 has a fix for character drift almost nobody uses. Every new text description is a fresh interpretation of appearance. That's where the drift comes from: a slightly different face, a slightly different outfit, proportions that shift from scene to scene. The @ Image tag solves this directly — attach a photo once, and it becomes the fixed source of truth for face, outfit, and proportions across the entire multi-shot sequence. The @ Video tag works the same way for motion and camera — tag a reference instead of describing it, and the model copies that exact style instead of an approximation. You're not making the model remember. You're just stopping yourself from reminding it differently every single time.

Seedance 2.0 has a fix for character drift almost nobody uses. Every new text description is a fresh interpretation of appearance. That's where the drift comes from: a slightly different face, a slightly different outfit, proportions that shift from scene to scene. The @ Image tag solves this directly — attach a photo once, and it becomes the fixed source of truth for face, outfit, and proportions across the entire multi-shot sequence. The @ Video tag works the same way for motion and camera — tag a reference instead of describing it, and the model copies that exact style instead of an approximation. You're not making the model remember. You're just stopping yourself from reminding it differently every single time.

Zentrix⌚️

88,931 views • 1 month ago

Adix is built from the ground up to be AI-powered - not as a feature, but as core infrastructure. $ADIX uses machine learning to match brands with the right creators, optimize campaign outcomes, and build on-chain reputation profiles based on real performance. It replaces manual workflows, reduces spend inefficiencies, and introduces precision at every step of the marketing process. Adix is what happens when AI and blockchain come together to solve real-world problems at scale. 🔥 👉

Adix is built from the ground up to be AI-powered - not as a feature, but as core infrastructure. $ADIX uses machine learning to match brands with the right creators, optimize campaign outcomes, and build on-chain reputation profiles based on real performance. It replaces manual workflows, reduces spend inefficiencies, and introduces precision at every step of the marketing process. Adix is what happens when AI and blockchain come together to solve real-world problems at scale. 🔥 👉

Adix

74,014 views • 10 months ago

💎 It's been an incredible few days since we announced EstateX Invest. The response from the Web3 community has been amazing: hundreds of early sign-ups, a ton of buzz, and genuine excitement for what's to come next! 🚨 Early access is filling up fast. 🔗 Sign Up for EstateX Invest Early Access: By signing up, you'll be among the first to: ✅ Discover new tokenized property investments ✅ Learn how to earn passive income through real-world assets ✅ Get access to our private community updates and insights The world of real estate is changing fast, and with EstateX Invest, you're not just watching it happen. The world of real estate is changing, and you can either watch it happen or be part of it.

💎 It's been an incredible few days since we announced EstateX Invest. The response from the Web3 community has been amazing: hundreds of early sign-ups, a ton of buzz, and genuine excitement for what's to come next! 🚨 Early access is filling up fast. 🔗 Sign Up for EstateX Invest Early Access: By signing up, you'll be among the first to: ✅ Discover new tokenized property investments ✅ Learn how to earn passive income through real-world assets ✅ Get access to our private community updates and insights The world of real estate is changing fast, and with EstateX Invest, you're not just watching it happen. The world of real estate is changing, and you can either watch it happen or be part of it.

EstateX

126,612 views • 9 months ago

another mini update with examples of octra state inference speed - it has grown even more with the latest updates the circle version is performing well and is already acquiring some kind of interface, the future plans are clear - expanding capabilities, adding ml-tools and deploying more complex mechanisms (this is an early version, but significant progress has already been made) the devnet version is written entirely in Applied circles will allow the creation of multiple, fully private and verifiable models, they can be assigned tasks, combined into rooms and given different access rights, the so called agents will come to life in the state and will be able to work directly with the network (this is useful for debugging and deep tuning) this direction definitely has potential and we will continue to work on it

another mini update with examples of octra state inference speed - it has grown even more with the latest updates the circle version is performing well and is already acquiring some kind of interface, the future plans are clear - expanding capabilities, adding ml-tools and deploying more complex mechanisms (this is an early version, but significant progress has already been made) the devnet version is written entirely in Applied circles will allow the creation of multiple, fully private and verifiable models, they can be assigned tasks, combined into rooms and given different access rights, the so called agents will come to life in the state and will be able to work directly with the network (this is useful for debugging and deep tuning) this direction definitely has potential and we will continue to work on it

λ

23,568 views • 3 months ago

Trained on zero real-world data. Learned to walk, pick up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:

Trained on zero real-world data. Learned to walk, pick up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

12,950 views • 1 month ago

This vandalism at Zimbabwe’s new Mbudzi Interchange is a perfect example of what Dr Solomon Guramatunhu always reminds us — that Zimbabwean leaders are a reflection of Zimbabwean society and the Zimbabwean mindset. Our leaders do not fall from the sky; they come from our communities. What we are seeing here is no different from a leader who loots public funds. Public funds are meant for the public good. When ZANUPF loots national resources, it is not different from the Zimbabwean citizen who goes to an interchange and steals cables. Both acts are theft, both are sabotage of the common good, and both expose a destructive mindset that holds the whole nation back. It is exactly the same behaviour that South Africans have been complaining about us for years, when some Zimbabweans vandalise public infrastructure and steal cables across the Limpopo. We are quick to call that xenophobia, but what then do we call it when we are destroying our own country with the same reckless disregard? We all know that in Zimbabwean homes, from the poor to the affluent, there are lithium batteries stolen from mobile phone towers in South Africa and sold cheaply in Zimbabwe. When South Africans complain about this, we dismiss them as being xenophobic. Here is an example of us doing the same thing in our own country. We are destroying and stealing from ourselves. When the lights fail, the interchange will be plunged into darkness, and people will be mugged and killed because there is no lighting. This is wrong. We cannot build a better country with the same hands that destroy it. It can’t!!!!

This vandalism at Zimbabwe’s new Mbudzi Interchange is a perfect example of what Dr Solomon Guramatunhu always reminds us — that Zimbabwean leaders are a reflection of Zimbabwean society and the Zimbabwean mindset. Our leaders do not fall from the sky; they come from our communities. What we are seeing here is no different from a leader who loots public funds. Public funds are meant for the public good. When ZANUPF loots national resources, it is not different from the Zimbabwean citizen who goes to an interchange and steals cables. Both acts are theft, both are sabotage of the common good, and both expose a destructive mindset that holds the whole nation back. It is exactly the same behaviour that South Africans have been complaining about us for years, when some Zimbabweans vandalise public infrastructure and steal cables across the Limpopo. We are quick to call that xenophobia, but what then do we call it when we are destroying our own country with the same reckless disregard? We all know that in Zimbabwean homes, from the poor to the affluent, there are lithium batteries stolen from mobile phone towers in South Africa and sold cheaply in Zimbabwe. When South Africans complain about this, we dismiss them as being xenophobic. Here is an example of us doing the same thing in our own country. We are destroying and stealing from ourselves. When the lights fail, the interchange will be plunged into darkness, and people will be mugged and killed because there is no lighting. This is wrong. We cannot build a better country with the same hands that destroy it. It can’t!!!!

Hopewell Chin’ono

111,596 views • 10 months ago

This is called the sonder effect. It’s the realization that every stranger you see has an inner life as rich, layered, and emotionally real as your own. The person walking past you is not just “a woman in a red coat” or “some guy in traffic.” He has a past, private fears, people he misses, routines he hates, memories that still sting, and plans he has not told anyone yet. Most of the time, our brains simplify other people into background. Not because we are cruel, but because we have to move through the world from inside our own point of view. Sonder is what happens when that illusion breaks for a second. You stop seeing people as scenery and start seeing them as entire worlds. That is what makes it powerful. It does not just make the world feel bigger. It makes you more humble, more patient, and a little more aware of how much you do not know about the people around you. For one second, the background characters disappear. And everyone becomes real.

This is called the sonder effect. It’s the realization that every stranger you see has an inner life as rich, layered, and emotionally real as your own. The person walking past you is not just “a woman in a red coat” or “some guy in traffic.” He has a past, private fears, people he misses, routines he hates, memories that still sting, and plans he has not told anyone yet. Most of the time, our brains simplify other people into background. Not because we are cruel, but because we have to move through the world from inside our own point of view. Sonder is what happens when that illusion breaks for a second. You stop seeing people as scenery and start seeing them as entire worlds. That is what makes it powerful. It does not just make the world feel bigger. It makes you more humble, more patient, and a little more aware of how much you do not know about the people around you. For one second, the background characters disappear. And everyone becomes real.

Sovey

12,469 views • 5 months ago

AI has had exactly two scaling axes that worked so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inference

AI has had exactly two scaling axes that worked so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inference

Sasha Malysheva

11,393 views • 14 days ago

🚨GAUTAM GAMBHIR MASSIVE STATEMENT ON HIS FUTURE AS INDIA's HEAD COACH🤯 Gautam Gambhir said :🗣️ "I am here to display the results & frankly speaking it has been a roller coaster ride so far. The main goal is always to win major tournaments & team has won Champions trophy & T20 World cup. There will be bad days offcourse, but this is how it goes sonedays. I don't listen to the outside noise & we have set our plans for the 2027 ODI WC. This is our first preference & then you can decide my future. I have been appointed as the coach of Indian cricket team to make it the best team in the world & we have been one of the most consistent teams in white ball cricket for some time now. We are in a transition phase in red ball cricket, and the team will get better with time".

🚨GAUTAM GAMBHIR MASSIVE STATEMENT ON HIS FUTURE AS INDIA's HEAD COACH🤯 Gautam Gambhir said :🗣️ "I am here to display the results & frankly speaking it has been a roller coaster ride so far. The main goal is always to win major tournaments & team has won Champions trophy & T20 World cup. There will be bad days offcourse, but this is how it goes sonedays. I don't listen to the outside noise & we have set our plans for the 2027 ODI WC. This is our first preference & then you can decide my future. I have been appointed as the coach of Indian cricket team to make it the best team in the world & we have been one of the most consistent teams in white ball cricket for some time now. We are in a transition phase in red ball cricket, and the team will get better with time".

Akshat

90,783 views • 22 days ago

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

雪踏乌云

113,347 views • 1 month ago

A new chapter starts today. As MegaETH mainnet approaches, Avon’s identity needs to reflect the system we’ve been building: a calm, transparent, and predictable place to lend or borrow. Our first brand was put together quickly during the early build phase. It let us move fast, but it never fully captured the level of clarity and focus we were aiming for. The new brand is built around those principles. Simple. Transparent. Grounded. A visual identity that matches Avon’s role as the credit and liquidity layer of MegaETH. It sets the tone for how lending should feel in a high-throughput, real-time environment: clear, controlled, and reliable. This is the foundation for what Avon is becoming as we head into mainnet.

Avon

56,449 views • 8 months ago

$A memory like this: I’ve been exploring Liquid Glass for at least one year now, recreating many versions exactly nine all built with totally different techniques. I came to a realization. iOS 26, at least for me, missed part of the purpose. Liquid Glass is often used as decoration, while refraction could become the core of the user experience. Not an embellishment, but interaction itself. By turning a glass panel, refraction reveals something else: another app, another image, another portal. That’s when it clicked. You look through one image, turn slightly, and suddenly you’re somewhere else. Same moment, different feeling. I really hope Apple takes this approach to the next level. Vibecoded with WebGL.$

A memory like this: I’ve been exploring Liquid Glass for at least one year now, recreating many versions exactly nine all built with totally different techniques. I came to a realization. iOS 26, at least for me, missed part of the purpose. Liquid Glass is often used as decoration, while refraction could become the core of the user experience. Not an embellishment, but interaction itself. By turning a glass panel, refraction reveals something else: another app, another image, another portal. That’s when it clicked. You look through one image, turn slightly, and suddenly you’re somewhere else. Same moment, different feeling. I really hope Apple takes this approach to the next level. Vibecoded with WebGL.

Tykra

37,802 views • 6 months ago

I'm proud to share that Glean has surpassed $300M ARR, just five months after crossing $200M and growing ~3x over the past 15 months. This is an exciting milestone for Glean, and it's a signal about where the enterprise AI market is heading. We’ve long believed the real challenge in enterprise AI is not access to models. It is grounding AI in how a company actually works: its people, knowledge, workflows, permissions, and systems. That’s even clearer now. The companies creating real value with AI are not just adopting better models. They are building systems that understand their business well enough to deliver reliable outcomes at scale. That is the real moat, and it is what we’ve been building at Glean: an unrivaled context layer for enterprise AI. That context has to work across the business, not just inside a single team or use case. We see that in how customers adopt Glean: more than 85% use it across five or more job functions. It also has to meet the security and governance demands of complex enterprises. We see that in who is choosing Glean: our Fortune 500 customer count nearly doubled year over year. And it has to make economic sense as usage grows. In our recent benchmark with Claude Cowork, Glean was preferred roughly 2.5x as often as off-the-shelf MCP tools and used 30% fewer tokens on average. Better context improves both quality and efficiency. I enjoyed talking with CNBC's Deirdre Bosa about this broader shift. In enterprise AI, the winners will not be defined by better models alone. They will be defined by who builds the strongest foundation for enterprise context. Thank you to our customers, partners, and team for helping us build the future of enterprise AI.

I'm proud to share that Glean has surpassed $300M ARR, just five months after crossing $200M and growing ~3x over the past 15 months. This is an exciting milestone for Glean, and it's a signal about where the enterprise AI market is heading. We’ve long believed the real challenge in enterprise AI is not access to models. It is grounding AI in how a company actually works: its people, knowledge, workflows, permissions, and systems. That’s even clearer now. The companies creating real value with AI are not just adopting better models. They are building systems that understand their business well enough to deliver reliable outcomes at scale. That is the real moat, and it is what we’ve been building at Glean: an unrivaled context layer for enterprise AI. That context has to work across the business, not just inside a single team or use case. We see that in how customers adopt Glean: more than 85% use it across five or more job functions. It also has to meet the security and governance demands of complex enterprises. We see that in who is choosing Glean: our Fortune 500 customer count nearly doubled year over year. And it has to make economic sense as usage grows. In our recent benchmark with Claude Cowork, Glean was preferred roughly 2.5x as often as off-the-shelf MCP tools and used 30% fewer tokens on average. Better context improves both quality and efficiency. I enjoyed talking with CNBC's Deirdre Bosa about this broader shift. In enterprise AI, the winners will not be defined by better models alone. They will be defined by who builds the strongest foundation for enterprise context. Thank you to our customers, partners, and team for helping us build the future of enterprise AI.

Arvind Jain

280,790 views • 2 months ago

If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all by some denoising and gradient maths. I won't be surprised if Sora is trained on lots of synthetic data using Unreal Engine 5. It has to be! Let's breakdown the following video. Prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee." - The simulator instantiates two exquisite 3D assets: pirate ships with different decorations. Sora has to solve text-to-3D implicitly in its latent space. - The 3D objects are consistently animated as they sail and avoid each other's paths. - Fluid dynamics of the coffee, even the foams that form around the ships. Fluid simulation is an entire sub-field of computer graphics, which traditionally requires very complex algorithms and equations. - Photorealism, almost like rendering with raytracing. - The simulator takes into account the small size of the cup compared to oceans, and applies tilt-shift photography to give a "minuscule" vibe. - The semantics of the scene does not exist in the real world, but the engine still implements the correct physical rules that we expect. Next up: add more modalities and conditioning, then we have a full data-driven UE that will replace all the hand-engineered graphics pipelines.

If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all by some denoising and gradient maths. I won't be surprised if Sora is trained on lots of synthetic data using Unreal Engine 5. It has to be! Let's breakdown the following video. Prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee." - The simulator instantiates two exquisite 3D assets: pirate ships with different decorations. Sora has to solve text-to-3D implicitly in its latent space. - The 3D objects are consistently animated as they sail and avoid each other's paths. - Fluid dynamics of the coffee, even the foams that form around the ships. Fluid simulation is an entire sub-field of computer graphics, which traditionally requires very complex algorithms and equations. - Photorealism, almost like rendering with raytracing. - The simulator takes into account the small size of the cup compared to oceans, and applies tilt-shift photography to give a "minuscule" vibe. - The semantics of the scene does not exist in the real world, but the engine still implements the correct physical rules that we expect. Next up: add more modalities and conditioning, then we have a full data-driven UE that will replace all the hand-engineered graphics pipelines.

Jim Fan

6,183,063 views • 2 years ago

An absolute world record — a pilot took down a Shahed with interceptor STING at a distance of 500 km Using Hornet Vision Ctrl technology, Roman “Hulk” from the BULAVA unit downed two Shaheds located 500 km away ❗️ This is the first time in the world someone has flown that far remotely — and actually scored intercepts. Not one, but two Shaheds ❤️‍🔥 So when we say: more to come — we mean it. More to come 🐝

An absolute world record — a pilot took down a Shahed with interceptor STING at a distance of 500 km Using Hornet Vision Ctrl technology, Roman “Hulk” from the BULAVA unit downed two Shaheds located 500 km away ❗️ This is the first time in the world someone has flown that far remotely — and actually scored intercepts. Not one, but two Shaheds ❤️‍🔥 So when we say: more to come — we mean it. More to come 🐝

Wild Hornets

401,650 views • 4 months ago