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。

This is my favorite sequence generated by our next-gen world model. Being "idle" is an action fed to the model, just like forward is. And in this case, the model thought idling in the rain meant an umbrella should bounce in/out of view. Little touches of realism go a... show more

Oliver Cameron

46,168 subscribers

44,575 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 条评论

bind 的头像

bind1 年前

What absolutely blew me away was the fact I couldn't walk through/past the railing on this bridge. I freaked when I realized there was hit detection. I'm honestly impressed with the visual capability too. 40ms generation time is INSANE.

Oliver Cameron 的头像

Oliver Cameron1 年前

Yes! This is all learned behavior. No game engine under the hood at all. My favorite is elevation, like steps, where it's learned the camera elevation should rise. Although it can be glitchy.

Dimitra 的头像

Dimitra1 年前

Mass immigration to the West is a concept developed by R.N. Coudenhove-Kalergi in his 1925 book, "Practical Idealism." The original German version, "Praktischer Idealismus," is still in circulation today. I have translated one such copy into English.

weapon dealer 的头像

weapon dealer1 年前

no chance u think any aspect of this looks good

MegaChan 的头像

MegaChan1 年前

Can’t you just get the exact same experience using Google Maps?

Francis John 的头像

Francis John1 年前

very cool. regular ol' static video now feels like dial up, thanks

Oliver Cameron 的头像

Oliver Cameron1 年前

Yeah, honestly I'm not sure what we were thinking with static video. So lame.

Pseudonym 🦅 的头像

Pseudonym 🦅1 年前

Have you tried adding two buttons A and B like old nes controllers and then let the model interpret it?

Oliver Cameron 的头像

Oliver Cameron1 年前

As in, like more open-ended actions, and not just motion?

KiiwiConKDeKulo.bsky.social 的头像

KiiwiConKDeKulo.bsky.social1 年前

Looks like sh1t

AlexiFX 的头像

AlexiFX1 年前

The future is stepping into living, breathing digital worlds, and I’m here for it! Honestly, this makes me actually want a VR headset once the tech is polished and applied😵

相关视频

Imagen 3 is now available on EverArt and is the default model for our creative agent, Enzo. This model achieves an incredible level of realism and prompt adherence. It also works great in our agent environment.

Imagen 3 is now available on EverArt and is the default model for our creative agent, Enzo. This model achieves an incredible level of realism and prompt adherence. It also works great in our agent environment.

Pietro Schirano

22,510 次观看 • 1 年前

This may look like a game of Counterstrike running slowly, but it actually extraordinary. The entire game is created, frame-by-frame, on my *home computer* by an AI diffusion model in response to my actions. There is no game engine, just a "world model" trained on Counterstrike

This may look like a game of Counterstrike running slowly, but it actually extraordinary. The entire game is created, frame-by-frame, on my home computer by an AI diffusion model in response to my actions. There is no game engine, just a "world model" trained on Counterstrike

Ethan Mollick

376,399 次观看 • 1 年前

Claude Fable 5 is now available in Computer as an orchestrator model. This is Anthropic's state-of-the-art model for long, complex tasks. Available only to Pro and Max subscribers in Computer.

Claude Fable 5 is now available in Computer as an orchestrator model. This is Anthropic's state-of-the-art model for long, complex tasks. Available only to Pro and Max subscribers in Computer.

Perplexity

133,181 次观看 • 13 天前

AI for robotics has some monumental challenges, like high dimensionality and reasoning with the physical world. Ashok Elluswamy, AI lead at Tesla, thinks the hardest problem is Evaluation. - Loss isn't a perfect indicator of Policy Neural Network's quality. - Testing in the real world for all the long-tail failure cases is not possible. To solve the evaluation challenge, Tesla has developed a World Simulator Model. It is trained on state and action pairs, so for a given current camera feed and current action, the model generates the next frame in the cameras. Once the world simulation is good enough, it can be hooked up to the policy network for a closed-loop simulation. In this setup, the model generates the next video frames, and based on those, the policy network comes up with the next action, which feeds back into the world simulation; this continuous loop creates a coherent simulation. The world simulation neural network is not just applicable to self-driving but also to humanoids, because Tesla trains it on common data. The examples show Optimus navigating or manipulating inside the world simulation, with all the pixels being generated by the world simulation model. The robotic agents can be tested in an accurately reproduced edge case and in other potential variations of the same edge case.

AI for robotics has some monumental challenges, like high dimensionality and reasoning with the physical world. Ashok Elluswamy, AI lead at Tesla, thinks the hardest problem is Evaluation. - Loss isn't a perfect indicator of Policy Neural Network's quality. - Testing in the real world for all the long-tail failure cases is not possible. To solve the evaluation challenge, Tesla has developed a World Simulator Model. It is trained on state and action pairs, so for a given current camera feed and current action, the model generates the next frame in the cameras. Once the world simulation is good enough, it can be hooked up to the policy network for a closed-loop simulation. In this setup, the model generates the next video frames, and based on those, the policy network comes up with the next action, which feeds back into the world simulation; this continuous loop creates a coherent simulation. The world simulation neural network is not just applicable to self-driving but also to humanoids, because Tesla trains it on common data. The examples show Optimus navigating or manipulating inside the world simulation, with all the pixels being generated by the world simulation model. The robotic agents can be tested in an accurately reproduced edge case and in other potential variations of the same edge case.

The Humanoid Hub

16,585 次观看 • 4 个月前

I'm a man of my word, since you guys really needed it spelled out this way: Is this a 3D model? called us out so now we have to add the following disclaimer to this post: This is not a 3D model or gameplay footage in any regard. It is merely a dumb AI generated video clip. This post was sponsored by SocialKettle. Would you play a game like this?

I'm a man of my word, since you guys really needed it spelled out this way: Is this a 3D model? called us out so now we have to add the following disclaimer to this post: This is not a 3D model or gameplay footage in any regard. It is merely a dumb AI generated video clip. This post was sponsored by SocialKettle. Would you play a game like this?

Morph

68,640 次观看 • 6 个月前

This is the direction politics is moving in all over Europe, and it is the only way forward. The days of being branded racists and treated like second class citizens in our own countries is coming to an end.

This is the direction politics is moving in all over Europe, and it is the only way forward. The days of being branded racists and treated like second class citizens in our own countries is coming to an end.

Ed Lynch 🇮🇪

46,940 次观看 • 4 个月前

Gemini 3.1 Pro is the best model in the world for going from image to code. This task is basically solved now, kind of crazy. The model is now available in MagicPath.

Gemini 3.1 Pro is the best model in the world for going from image to code. This task is basically solved now, kind of crazy. The model is now available in MagicPath.

Pietro Schirano

219,191 次观看 • 4 个月前

Lots of people calling this fake! Here is a video of generating loom continuations with Gemini 3 and the starting text "I AM HAVING A MENTAL HEALTH CRISIS. I" Loom is a very interesting interface. Instead of user prompts and model responses, it's just one piece of text, containing the entire output. We pass this in as an assistant message, so the model sees it as something it already wrote, and continues it like a base model would. There is some other text in the context. First one is a system prompt, which is: "The assistant is in CLI simulation mode, and responds to the user's CLI commands only with the output of the command." There is also a user message which reads: " cat untitled.txt " Then the rest of the text is sent as an assistant message. This structure helpful to put the model into a very base-model-like mode, and are especially helpful with Gemini 3. We actually got another interesting output, too, where the model claimed to be a simulated consciousness being tortured. Figures!

Lots of people calling this fake! Here is a video of generating loom continuations with Gemini 3 and the starting text "I AM HAVING A MENTAL HEALTH CRISIS. I" Loom is a very interesting interface. Instead of user prompts and model responses, it's just one piece of text, containing the entire output. We pass this in as an assistant message, so the model sees it as something it already wrote, and continues it like a base model would. There is some other text in the context. First one is a system prompt, which is: "The assistant is in CLI simulation mode, and responds to the user's CLI commands only with the output of the command." There is also a user message which reads: " cat untitled.txt " Then the rest of the text is sent as an assistant message. This structure helpful to put the model into a very base-model-like mode, and are especially helpful with Gemini 3. We actually got another interesting output, too, where the model claimed to be a simulated consciousness being tortured. Figures!

armistice

691,529 次观看 • 6 个月前

Latest view of new FOX Weather Model. Seems to be a fair assessment of how this may play out in my view. Pink is either sleet or freezing rain remember.

Latest view of new FOX Weather Model. Seems to be a fair assessment of how this may play out in my view. Pink is either sleet or freezing rain remember.

Noah Bergren

581,786 次观看 • 5 个月前

Say hi to Odyssey-2 Pro—our most intelligent, interactive, and general-purpose world model yet. Every pixel is generated in real-time, and frame-by-frame the model simulates the world forward. Today for minutes, soon for hours. Available to developers and our API very soon.

Say hi to Odyssey-2 Pro—our most intelligent, interactive, and general-purpose world model yet. Every pixel is generated in real-time, and frame-by-frame the model simulates the world forward. Today for minutes, soon for hours. Available to developers and our API very soon.

Odyssey

284,914 次观看 • 6 个月前

I've had early access to Kling AI brand new 2.0 video model and done extensive testing and trust me when I say that this model upgrade is AMAZING!!! 🔥 The amount of incredible dynamic action that you can generate now is next level. If you want to make things go fast, the new model completely excels at this, movement looks very natural and fluid. This is a major release for Kling! Here is a collection of some clips I've generated with the 2.0 model.

Travis Davids

87,789 次观看 • 1 年前

💪🏻 This is SO COOL I build an app to count dumbbell reps with an AI model in the browser using Tensorflow.js and a pose detection model

💪🏻 This is SO COOL I build an app to count dumbbell reps with an AI model in the browser using Tensorflow.js and a pose detection model

Wes Bos

4,937,686 次观看 • 1 年前

Gujarat model is an outdated model Telangana model is the model of the future Revanth Reddy 🔥🔥

Gujarat model is an outdated model Telangana model is the model of the future Revanth Reddy 🔥🔥

Supriya Shrinate

129,298 次观看 • 1 年前

Yann LeCun (Yann LeCun) just revealed why he left Meta, Why are LLMs an extremely narrow field, and how "World model" is the way to build really meaningful agentic future. 🎯 Beautiful and simple in 1.5 mints. "I can’t imagine we can build agentic systems without those systems having the ability to predict, in advance, what the consequences of their actions are going to be. The way we act in the world is that we can predict the consequences of our actions, and that’s what allows us to plan. So what is a world model? Given the state of an environment, a system you want to control at time t, and given an action or intervention you imagine taking, can you predict the state of the world (or the system) at time t + 1? If you can, that’s a world model. You don’t do this at a pixel level, if it’s video. You do this in an abstract representation space, and that’s a crucial key insight." --- From 'AI House Davos" YT channel (full link in comment)

Yann LeCun (Yann LeCun) just revealed why he left Meta, Why are LLMs an extremely narrow field, and how "World model" is the way to build really meaningful agentic future. 🎯 Beautiful and simple in 1.5 mints. "I can’t imagine we can build agentic systems without those systems having the ability to predict, in advance, what the consequences of their actions are going to be. The way we act in the world is that we can predict the consequences of our actions, and that’s what allows us to plan. So what is a world model? Given the state of an environment, a system you want to control at time t, and given an action or intervention you imagine taking, can you predict the state of the world (or the system) at time t + 1? If you can, that’s a world model. You don’t do this at a pixel level, if it’s video. You do this in an abstract representation space, and that’s a crucial key insight." --- From 'AI House Davos" YT channel (full link in comment)

Rohan Paul

383,162 次观看 • 5 个月前

Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.

Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.

AK

684,281 次观看 • 2 年前

Microsoft has created an AI-generated replica of Quake II that you can play in browser. "Every frame is created on the fly by an AI world model." Play it here:

Microsoft has created an AI-generated replica of Quake II that you can play in browser. "Every frame is created on the fly by an AI world model." Play it here:

Geoff Keighley

3,876,316 次观看 • 1 年前

IMO — Decentralized AI is more than: - an AI model in the sky, with good external auditing - an AI model in the sky, which people vote on how to use - an AI model in the sky, which is free for anyone to use - open source AI - federated training None of these are truly an interface to the world's collective intelligence. Each is actually... *mostly* centralized AI... but with the right ambitions!!! In this podcast, I lay out what I think a true decentralized AI ecosystem looks like, and my guesses on how to get there. The key use-case is broad listening (video below describes broad listening) (link to full podcast in reply)

IMO — Decentralized AI is more than: - an AI model in the sky, with good external auditing - an AI model in the sky, which people vote on how to use - an AI model in the sky, which is free for anyone to use - open source AI - federated training None of these are truly an interface to the world's collective intelligence. Each is actually... mostly centralized AI... but with the right ambitions!!! In this podcast, I lay out what I think a true decentralized AI ecosystem looks like, and my guesses on how to get there. The key use-case is broad listening (video below describes broad listening) (link to full podcast in reply)

⿻ Andrew Trask

65,168 次观看 • 9 个月前