正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

World models like Odyssey-3 can now simulate general environments with far greater physical accuracy, all in real time. The knowledge learned by models like Odyssey-3 can also power robots, humanoids, driverless cars, and drones. And world models are just getting started!

Odyssey

49,842 subscribers

21,665 次观看 • 6 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

Oliver Cameron 的头像

Oliver Cameron6 天前

On top of the world 🫶

jhilemo 的头像

jhilemo6 天前

I use it and I love it, especially for the latest simulation I posted

PythonMan 的头像

PythonMan6 天前

Je suis content de cet avancé. Par contre on regarde de chaque côté avant de traverser la route !

Wayne Brown 的头像

Wayne Brown6 天前

Real enough that the toddler running out into the road made me wince. Good job!

Ernesto 的头像

Ernesto6 天前

mogged by Genie 4

ArcyDev 的头像

ArcyDev6 天前

What the hell is happening? Five years ago, this would've been unimaginable. Scratch that, even two years ago!

clankr 的头像

clankr6 天前

These environments look impressive. But seems like world models that arent spesific for robots still couldn't hold in physical interractions.

Dylan Swanepoel 的头像

Dylan Swanepoel6 天前

Real-time is the part that makes world models usable for agents. Simulating before acting is a big deal once robots and drones are in the loop.

Aadarsh 的头像

Aadarsh6 天前

How can I try these myself, these seem very cool.

相关视频

JUST IN: Odyssey unveils Odyssey-3, an AI world model that can learn from visual data and apply its knowledge to robots, cars, drones and video games.

JUST IN: Odyssey unveils Odyssey-3, an AI world model that can learn from visual data and apply its knowledge to robots, cars, drones and video games.

Whale Insider

41,140 次观看 • 1 个月前

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

Odyssey

2,188,010 次观看 • 6 个月前

Odyssey launches Odyssey-3, a foundation world model that sets a new state of the art on Physics-IQ Verified (66.1) for video-to-video physical simulation. The same pretrained model generates real-time interactive environments from prompts and adapts to control robots, humanoids, cars, and drones with limited task-specific data.

Odyssey launches Odyssey-3, a foundation world model that sets a new state of the art on Physics-IQ Verified (66.1) for video-to-video physical simulation. The same pretrained model generates real-time interactive environments from prompts and adapts to control robots, humanoids, cars, and drones with limited task-specific data.

Documenting AGI

38,907 次观看 • 27 天前

Today we’re unveiling Odyssey-3, a big step forward for foundation world models. It can control robots, power humanoids, drive cars (on the roads of India!), train AIs, pilot drones, and even play video games. We can’t wait to see what intelligent systems it enables.

Today we’re unveiling Odyssey-3, a big step forward for foundation world models. It can control robots, power humanoids, drive cars (on the roads of India!), train AIs, pilot drones, and even play video games. We can’t wait to see what intelligent systems it enables.

Odyssey

2,343,632 次观看 • 1 个月前

Real-time World Models x Multi-agent reality simulator with Odyssey

Real-time World Models x Multi-agent reality simulator with Odyssey

Cris Lenta

45,923 次观看 • 8 个月前

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Google AI

102,812 次观看 • 1 年前

We’re giving away 1,000,000 simulations of reality, powered by our newest world model, Odyssey-2 Pro. Grab an API key, call /simulate, and get back a beautiful MP4. All free. The GPT-2 era rapidly explored language models. Now it’s time we explore world models together.

We’re giving away 1,000,000 simulations of reality, powered by our newest world model, Odyssey-2 Pro. Grab an API key, call /simulate, and get back a beautiful MP4. All free. The GPT-2 era rapidly explored language models. Now it’s time we explore world models together.

Odyssey

40,935 次观看 • 9 个月前

Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simulations of any imaginable world. This could be the key missing piece for embodied AGI… and it can also create beautiful beaches with my dog, playable real time

Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simulations of any imaginable world. This could be the key missing piece for embodied AGI… and it can also create beautiful beaches with my dog, playable real time

Jack Parker-Holder

2,091,059 次观看 • 1 年前

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

MTS

11,693 次观看 • 5 个月前

Field AI raised $405M in funding and introduced Field Foundation Models These models are designed to grapple with uncertainties and the physical constraints of the real world, enabling safe robot behaviors when navigating in new environments

Field AI raised $405M in funding and introduced Field Foundation Models These models are designed to grapple with uncertainties and the physical constraints of the real world, enabling safe robot behaviors when navigating in new environments

Brett Adcock

15,136 次观看 • 1 年前

Nano Banana 2, new state of the art in image generation and editing combined with Gemini’s real-world knowledge! You can simulate 3D CAD models purely through images. From sketch to real object!

Nano Banana 2, new state of the art in image generation and editing combined with Gemini’s real-world knowledge! You can simulate 3D CAD models purely through images. From sketch to real object!

koray kavukcuoglu

87,922 次观看 • 8 个月前

we designed + built a new website for Odyssey insane tech, they're building general purpose world models to simulate interactive worlds in real time 🤯 one of the coolest projects my team and I at The Memetic Design Company have had the chance to work on!

we designed + built a new website for Odyssey insane tech, they're building general purpose world models to simulate interactive worlds in real time 🤯 one of the coolest projects my team and I at The Memetic Design Company have had the chance to work on!

abhinav

15,516 次观看 • 8 个月前

Language models understand words. World models could help AI understand the world itself. TIME's Tharin Pillay spoke with Oliver Cameron, CEO of Odyssey, at AMD's Advancing AI event:

Language models understand words. World models could help AI understand the world itself. TIME's Tharin Pillay spoke with Oliver Cameron, CEO of Odyssey, at AMD's Advancing AI event:

TIME

49,444 次观看 • 3 个月前

Okay, the part of the Odyssey-3 launch I keep thinking about is the physics. Their framing is simple: physics is to world models what coding is to language models. If a model can predict how things move and react, robots and AI agents can work out what happens next. Odyssey-3 Pro posted the highest reported Physics-IQ Verified video-to-video score. That's 66.1 with best-of-8 sampling. The research preview is open if you want to try it yourself:

Okay, the part of the Odyssey-3 launch I keep thinking about is the physics. Their framing is simple: physics is to world models what coding is to language models. If a model can predict how things move and react, robots and AI agents can work out what happens next. Odyssey-3 Pro posted the highest reported Physics-IQ Verified video-to-video score. That's 66.1 with best-of-8 sampling. The research preview is open if you want to try it yourself:

Chidanand Tripathi

107,516 次观看 • 27 天前

How do you explain world models to your sibling? 🤖 NVIDIA Cosmos helps physical AI reason about real-world interactions and simulate possible futures before acting in the real world. Or, as they might put it, it teaches robots to dream. 💭

How do you explain world models to your sibling? 🤖 NVIDIA Cosmos helps physical AI reason about real-world interactions and simulate possible futures before acting in the real world. Or, as they might put it, it teaches robots to dream. 💭

NVIDIA

89,292 次观看 • 3 个月前

JUST IN: One model powering humanoids, robot arms, cars, drones and games is a fascinating direction. Odyssey-3 shows how broad pretraining can provide a shared foundation, with just a few hours of task-specific experience needed to adapt

JUST IN: One model powering humanoids, robot arms, cars, drones and games is a fascinating direction. Odyssey-3 shows how broad pretraining can provide a shared foundation, with just a few hours of task-specific experience needed to adapt

Insider Paper

16,140 次观看 • 1 个月前

Without World Models, There Is No AGI. Google Just Proved It. If AGI ever happens, it will not come from bigger chatbots alone. From the very start of this interview, one thing is crystal clear: without world models, we will never reach AGI. And right now, Google is leading with its world simulator Genie 3. Here is the core of what Demis Hassabis explains in this conversation: • World models are the missing core of AGI Hassabis says his deepest long term focus has always been world models and simulations. Not just language. Not just prediction. Actual internal simulations of reality. • LLMs are impressive, but incomplete Language models understand more about the world than expected because human language encodes a lot of reality. Still, language is only a shadow of the real thing. • What text can never fully teach Reality includes things text struggles to express: •3D space and spatial dynamics •Physical causality and mechanics •Sensorimotor experience like movement, force, smell, or balance • Experience beats description To close the gap, AI must learn from interaction and experience, not just static text. That is how you build an internal world simulator. • Why Genie 3 matters With Google DeepMind pushing systems like Genie 3, AI starts to model reality itself, not just talk about it. • Robots and real world assistants depend on this True robotics, smart glasses, and universal assistants require AI that understands the physical world you live in, not just your screen. Bottom line: AGI will not emerge from better text prediction. It will emerge from systems that can simulate, predict, and understand reality itself. Right now, Google is clearly ahead on that path. Curious what you think. Are world models the real AGI unlock, or just another stepping stone?

Without World Models, There Is No AGI. Google Just Proved It. If AGI ever happens, it will not come from bigger chatbots alone. From the very start of this interview, one thing is crystal clear: without world models, we will never reach AGI. And right now, Google is leading with its world simulator Genie 3. Here is the core of what Demis Hassabis explains in this conversation: • World models are the missing core of AGI Hassabis says his deepest long term focus has always been world models and simulations. Not just language. Not just prediction. Actual internal simulations of reality. • LLMs are impressive, but incomplete Language models understand more about the world than expected because human language encodes a lot of reality. Still, language is only a shadow of the real thing. • What text can never fully teach Reality includes things text struggles to express: •3D space and spatial dynamics •Physical causality and mechanics •Sensorimotor experience like movement, force, smell, or balance • Experience beats description To close the gap, AI must learn from interaction and experience, not just static text. That is how you build an internal world simulator. • Why Genie 3 matters With Google DeepMind pushing systems like Genie 3, AI starts to model reality itself, not just talk about it. • Robots and real world assistants depend on this True robotics, smart glasses, and universal assistants require AI that understands the physical world you live in, not just your screen. Bottom line: AGI will not emerge from better text prediction. It will emerge from systems that can simulate, predict, and understand reality itself. Right now, Google is clearly ahead on that path. Curious what you think. Are world models the real AGI unlock, or just another stepping stone?

VraserX e/acc

23,784 次观看 • 10 个月前