正在加载视频...

视频加载失败

返回首页

AI can now turn a single image into an explorable physical world. For engineering, this means we can interact with, stress-test, and build intuition about failure in systems that do not yet exist. We can rapidly generate, interrogate, and learn from these worlds to understand how complex physical behavior...

ProfBuehlerMIT's profile picture

Markus J. Buehler

20,643 subscribers

11,713 次观看 • 1 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:
0:44

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,078,049 次观看 • 1 个月前

In the era of 10T-parameter foundation models 😈, can we still build next-generation world representations using 🦥 a single RTX 3090 GPU? We introduce WorldString (a name inspired by string theory), a tiny neural network representation for reconstructing dynamic world instances, ranging from articulated motion and skeletal skinning to soft-body deformation. 🔥 We view object representation as the core primitive of world modeling: the basic executable unit from which perception, interaction, simulation, and generation can be built. With a compact neural basis, WorldString aims to connect dynamic object modeling with neural simulation and foundation models, enabling a scalable path toward richer representations of the physical world.
0:29

In the era of 10T-parameter foundation models 😈, can we still build next-generation world representations using 🦥 a single RTX 3090 GPU? We introduce WorldString (a name inspired by string theory), a tiny neural network representation for reconstructing dynamic world instances, ranging from articulated motion and skeletal skinning to soft-body deformation. 🔥 We view object representation as the core primitive of world modeling: the basic executable unit from which perception, interaction, simulation, and generation can be built. With a compact neural basis, WorldString aims to connect dynamic object modeling with neural simulation and foundation models, enabling a scalable path toward richer representations of the physical world.

Xueyan Zou

38,299 次观看 • 1 个月前

Roger Ebert on Louis Malle's "Damage" (1992): "Watching 'Damage' (1992) is like watching an emotional traffic accident as it unfolds. The film is based on the best seller by Josephine Hart, which had a certain undeniable power, but the right place for this material is the screen, I think, because it can show exactly how the two look at one another. This is a movie about sight; from the first moment the two meet, it is filled with what is seen and what is not seen, as Stephen [Jeremy Irons] suffers though a dinner party with his wife, his son, Anna [Juliette Binoche] and her mother – and some observe, and some do not, what has happened. (...) 'Damage' is one of those rare movies that is about s*xuality, not s*x; about the tension between people, not “relationships”; about how physical love is meaningless without a psychic engine behind it. Stephen and Anna are wrong to do what they do in 'Damage' but they cannot help themselves. We know they are careening toward disaster. We cannot look away." ("Damage", Roger Ebert, 1993)
1:47

Roger Ebert on Louis Malle's "Damage" (1992): "Watching 'Damage' (1992) is like watching an emotional traffic accident as it unfolds. The film is based on the best seller by Josephine Hart, which had a certain undeniable power, but the right place for this material is the screen, I think, because it can show exactly how the two look at one another. This is a movie about sight; from the first moment the two meet, it is filled with what is seen and what is not seen, as Stephen [Jeremy Irons] suffers though a dinner party with his wife, his son, Anna [Juliette Binoche] and her mother – and some observe, and some do not, what has happened. (...) 'Damage' is one of those rare movies that is about s*xuality, not s*x; about the tension between people, not “relationships”; about how physical love is meaningless without a psychic engine behind it. Stephen and Anna are wrong to do what they do in 'Damage' but they cannot help themselves. We know they are careening toward disaster. We cannot look away." ("Damage", Roger Ebert, 1993)

DepressedBergman

39,978 次观看 • 1 个月前

Automating the lab bench is the best thing we can do for AI in biology. Most experiments are still run by hand. Every biologist's handiwork is unique and every lab is a little different. So, biology faces widespread reproducibility issues. But, AI will demand more reproducible data than we can produce, and generate more ideas than we can test. Experiments must be communicated and executed in a standardized way to generate reproducible data. So, Tetsuwan is building a lab where users specify experiments in an exact syntax. These experiments are executed by an automated platform to generate transparent, reproducible output. The user never needs physical access to a lab. This is a biology lab you can use like a computer. Our platform, built and tested with pilot labs over the past two years, lets users configure automated workflows rapidly & precisely. Later this year, we will bring our first services online, focusing on functional screens for protein design. Alex and I met at Caltech, where she was one year my senior. We're building this company because we were little kids who wanted to be biologists that grew up into adults who resented the lab bench. We want biology to be about asking questions, not the painful and frustrating manual process of asking them. For those looking to receive updates on our pilot services, looking for a meaningful job, or just to learn more about our work, see the links in the comments!
0:59

Automating the lab bench is the best thing we can do for AI in biology. Most experiments are still run by hand. Every biologist's handiwork is unique and every lab is a little different. So, biology faces widespread reproducibility issues. But, AI will demand more reproducible data than we can produce, and generate more ideas than we can test. Experiments must be communicated and executed in a standardized way to generate reproducible data. So, Tetsuwan is building a lab where users specify experiments in an exact syntax. These experiments are executed by an automated platform to generate transparent, reproducible output. The user never needs physical access to a lab. This is a biology lab you can use like a computer. Our platform, built and tested with pilot labs over the past two years, lets users configure automated workflows rapidly & precisely. Later this year, we will bring our first services online, focusing on functional screens for protein design. Alex and I met at Caltech, where she was one year my senior. We're building this company because we were little kids who wanted to be biologists that grew up into adults who resented the lab bench. We want biology to be about asking questions, not the painful and frustrating manual process of asking them. For those looking to receive updates on our pilot services, looking for a meaningful job, or just to learn more about our work, see the links in the comments!

Cristian Ponce

839,171 次观看 • 1 个月前

NVIDIA CEO Jensen Huang just gave us a glimpse into the future of AI, and it's far bigger than text and images. He asked: "If you can understand worlds, is it possible that you understand proteins and chemicals that have structure?” This is the quiet revolution happening in AI right now. We're moving from an AI that understands human language to an AI that understands the language of nature itself. The "letters" are atoms. The "words" are molecules. The "sentences" are the complex structures of life, networks, and reality. The same foundational models that generate video are now being used to: *Decode proteins to fight disease *Design new materials at the atomic level *Simulate complex systems in quantum computing These were once the domain of supercomputers and Nobel laureates. Now, they're becoming solvable problems for a new generation of startups. AI is transitioning from a tool for communication to a tool for creation and discovery in the physical world. This is where the next wave of generational companies will be built. The "hard-to-solve" problems are now within reach.
2:14

NVIDIA CEO Jensen Huang just gave us a glimpse into the future of AI, and it's far bigger than text and images. He asked: "If you can understand worlds, is it possible that you understand proteins and chemicals that have structure?” This is the quiet revolution happening in AI right now. We're moving from an AI that understands human language to an AI that understands the language of nature itself. The "letters" are atoms. The "words" are molecules. The "sentences" are the complex structures of life, networks, and reality. The same foundational models that generate video are now being used to: *Decode proteins to fight disease *Design new materials at the atomic level *Simulate complex systems in quantum computing These were once the domain of supercomputers and Nobel laureates. Now, they're becoming solvable problems for a new generation of startups. AI is transitioning from a tool for communication to a tool for creation and discovery in the physical world. This is where the next wave of generational companies will be built. The "hard-to-solve" problems are now within reach.

Konstantine Buhler

13,014 次观看 • 9 个月前

I believe safety is important, but we must distinguish between two very different narratives: The "Sci-Fi" Narrative: Stories about AI controlling the world, having "feelings," or possessing secret intelligence designed to fool us. Too often, the research in this narrative is used for PR or as an excuse to stifle open-source research. The Engineering Reality: How do we build systems that are robust and hard to break? As Yann points out, current LLMs rely on post-training for safety, which is inherently fragile and can always be jailbroken. He argues for "Objective-Driven AI, which means systems that satisfy safety constraints by construction, similar to how a jet engine is engineered to handle stress. I agree with Yann that patching models with fine-tuning isn't the long-term solution. However, the practical path to embedding these hard "guardrails" into a reasoning agent is still a massive open question. We know what we need, but we haven't figured out how to build it effectively in practice.
4:50

I believe safety is important, but we must distinguish between two very different narratives: The "Sci-Fi" Narrative: Stories about AI controlling the world, having "feelings," or possessing secret intelligence designed to fool us. Too often, the research in this narrative is used for PR or as an excuse to stifle open-source research. The Engineering Reality: How do we build systems that are robust and hard to break? As Yann points out, current LLMs rely on post-training for safety, which is inherently fragile and can always be jailbroken. He argues for "Objective-Driven AI, which means systems that satisfy safety constraints by construction, similar to how a jet engine is engineered to handle stress. I agree with Yann that patching models with fine-tuning isn't the long-term solution. However, the practical path to embedding these hard "guardrails" into a reasoning agent is still a massive open question. We know what we need, but we haven't figured out how to build it effectively in practice.

Ravid Shwartz Ziv

23,782 次观看 • 7 个月前

How is the Web changing due to AI? This visit to TinyFish yesterday goes deeply into just how. TinyFish makes a new kind of web browser. One that is started virtually. It is like a Google Chrome in the cloud. But it is very smart, can read and use any website, and your AI agents can talk to it. Here we talk about what it all means for business and the future of robots, brain computer interfaces, and AI glasses. It lets you build systems that can look at MANY websites at the same time and build new kinds of apps to do all sorts of new things.
1:02:10

How is the Web changing due to AI? This visit to TinyFish yesterday goes deeply into just how. TinyFish makes a new kind of web browser. One that is started virtually. It is like a Google Chrome in the cloud. But it is very smart, can read and use any website, and your AI agents can talk to it. Here we talk about what it all means for business and the future of robots, brain computer interfaces, and AI glasses. It lets you build systems that can look at MANY websites at the same time and build new kinds of apps to do all sorts of new things.

Robert Scoble

16,341 次观看 • 7 个月前

World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe! 🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address: 1️⃣ How can robots cooperate or compete intelligently? 2️⃣ How do humans build social bonds and communities? 3️⃣ How can both co-exist in an open, dynamic world? Announcing Virtual Community Project — a social-physical world simulator, where human characters and robotic agents can interact, grow, and co-evolve within open-world societies, stretching from London to New York, and beyond! Key features include: ✅ Unified multi-agent physics simulations for rich social + physical interactions of humans and robots ✅ Massive auto-generated 3D scenes grounded with the rea-world geospatial data ✅ Agent communities populated by robots and LLM-driven human characters with rich appearances, personalities, and social ties. 🌍 Enter our Virtual Community, an open world to study embodied AI at scale— one social-physical world model at a time! 🔗 Project: 💻 Code: Paper: 1/n
0:53

World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe! 🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address: 1️⃣ How can robots cooperate or compete intelligently? 2️⃣ How do humans build social bonds and communities? 3️⃣ How can both co-exist in an open, dynamic world? Announcing Virtual Community Project — a social-physical world simulator, where human characters and robotic agents can interact, grow, and co-evolve within open-world societies, stretching from London to New York, and beyond! Key features include: ✅ Unified multi-agent physics simulations for rich social + physical interactions of humans and robots ✅ Massive auto-generated 3D scenes grounded with the rea-world geospatial data ✅ Agent communities populated by robots and LLM-driven human characters with rich appearances, personalities, and social ties. 🌍 Enter our Virtual Community, an open world to study embodied AI at scale— one social-physical world model at a time! 🔗 Project: 💻 Code: Paper: 1/n

Chuang Gan

90,261 次观看 • 1 年前

The new Sora 2 app by Chat GPT crosses the line by allowing users to take video from any person, living or dead, replicate their likeness and voice, and generate content from it. MAKING MARTIN LUTHER KING YELL LIKE A MONKEY IS HATE, NOT INNOVATION. This is not just offensive, it is a violation of name, image, and likeness. Iconic figures have a right to publicity, to control how their legacy is represented and used. As we push forward into the future with AI-generated content, this is the unfortunate circumstance that can happen, and will happen, when technology allows anyone to exploit another person’s identity. When AI is used to turn legacies into racist memes, that is not creativity it is exploitation.
0:22

The new Sora 2 app by Chat GPT crosses the line by allowing users to take video from any person, living or dead, replicate their likeness and voice, and generate content from it. MAKING MARTIN LUTHER KING YELL LIKE A MONKEY IS HATE, NOT INNOVATION. This is not just offensive, it is a violation of name, image, and likeness. Iconic figures have a right to publicity, to control how their legacy is represented and used. As we push forward into the future with AI-generated content, this is the unfortunate circumstance that can happen, and will happen, when technology allows anyone to exploit another person’s identity. When AI is used to turn legacies into racist memes, that is not creativity it is exploitation.

Isaac Hayes III

35,000 次观看 • 9 个月前

I made tons of money building websites for people and small companies. Most of that is now gone. You can now generate, customize, and deploy a website using natural language. I recorded myself building a site from scratch using 10Web.io. 4 minutes later, I had a full website generated just for me. Crazy! That's mostly how I paid rent when I graduated college: I'd either build you a new site or make changes to an existing one. It's nuts anyone can do that today by just asking. But this doesn't stop with generating a website. 10Web also released an AI Copilot that you can use to edit a website with a chat-based AI assistant. Here is what you can do with the AI Copilot: 1. You can edit individual elements and widgets on your site by selecting them and describing the changes you want. 2. You can generate new images, create sections, and generate or edit text. 3. You can also add any new elements to the site. The best way to understand how much progress we've made is by looking at the AI Copilot in action: And the funny part is that we are just figuring out how to use AI models. 2025 will be crazy.
4:17

I made tons of money building websites for people and small companies. Most of that is now gone. You can now generate, customize, and deploy a website using natural language. I recorded myself building a site from scratch using 10Web.io. 4 minutes later, I had a full website generated just for me. Crazy! That's mostly how I paid rent when I graduated college: I'd either build you a new site or make changes to an existing one. It's nuts anyone can do that today by just asking. But this doesn't stop with generating a website. 10Web also released an AI Copilot that you can use to edit a website with a chat-based AI assistant. Here is what you can do with the AI Copilot: 1. You can edit individual elements and widgets on your site by selecting them and describing the changes you want. 2. You can generate new images, create sections, and generate or edit text. 3. You can also add any new elements to the site. The best way to understand how much progress we've made is by looking at the AI Copilot in action: And the funny part is that we are just figuring out how to use AI models. 2025 will be crazy.

Santiago

57,917 次观看 • 1 年前

Welcome to AI, Explained by Humans, where we break down new developments in AI and how they'll affect your daily life. Research from leading AI labs suggests that AI systems are capable of lying, scheming, and surprising their creators. Whether or not AI can be conscious, it is clearly doing something markedly more sophisticated than previous generations of digital technology. Today, reporter Tharin Pillay breaks down the discussions happening between researchers, innovators, and even philosophers to figure out if AI has a mind, what it can do with that mind, and what that means for how we interact with it.
1:35

Welcome to AI, Explained by Humans, where we break down new developments in AI and how they'll affect your daily life. Research from leading AI labs suggests that AI systems are capable of lying, scheming, and surprising their creators. Whether or not AI can be conscious, it is clearly doing something markedly more sophisticated than previous generations of digital technology. Today, reporter Tharin Pillay breaks down the discussions happening between researchers, innovators, and even philosophers to figure out if AI has a mind, what it can do with that mind, and what that means for how we interact with it.

TIME

20,302 次观看 • 5 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 ➡️
0:33

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

102,615 次观看 • 11 个月前

A Talk About AI That Will Blow Your Mind. It Did In 1998 When I Attended The Talk. I just found this video from 1998 when I attended this talk by Rupert Sheldrake, Terence McKenna and Ralph Abraham at the University of California, Santa Cruz to explore how machine intelligence might evolve in relation to our own. I never thought I would see this again and it had a great influence on me in the AI I was building in that era and on to today. But ai just found a copy. I certainly did not run around with a VHS recorder so I am blown away that this exists. Now you can see what I saw. At that time, the internet was still young, and artificial intelligence belonged mostly to science fiction. Yet many of the questions we raised then have become part of daily life. In this conversation, it was explored whether intelligence is best understood as logic and computation, or as something embodied, participatory, and alive. Can the mind be reduced to code, or does life itself depend on forms of knowing that no algorithm can contain? AI now outpace us in speed, reach, and memory. Yet the deeper mystery is not how far they can go, but what they reveal about mind and ourselves. Will AI reproduce the limitations of our mechanistic worldview, or might it help us rediscover dimensions of mind that transcend machinery altogether? It's striking how near we now are to the possibilities we once only speculated about. Quantum computing, self-learning systems, large language models very much as Terence describes—and the looming prospect of superintelligence—have moved from the margins to the mainstream. But the heart of the conversation remains just as relevant today, if not more so: what is consciousness, and how might we participate in its unfolding evolution?
42:37

A Talk About AI That Will Blow Your Mind. It Did In 1998 When I Attended The Talk. I just found this video from 1998 when I attended this talk by Rupert Sheldrake, Terence McKenna and Ralph Abraham at the University of California, Santa Cruz to explore how machine intelligence might evolve in relation to our own. I never thought I would see this again and it had a great influence on me in the AI I was building in that era and on to today. But ai just found a copy. I certainly did not run around with a VHS recorder so I am blown away that this exists. Now you can see what I saw. At that time, the internet was still young, and artificial intelligence belonged mostly to science fiction. Yet many of the questions we raised then have become part of daily life. In this conversation, it was explored whether intelligence is best understood as logic and computation, or as something embodied, participatory, and alive. Can the mind be reduced to code, or does life itself depend on forms of knowing that no algorithm can contain? AI now outpace us in speed, reach, and memory. Yet the deeper mystery is not how far they can go, but what they reveal about mind and ourselves. Will AI reproduce the limitations of our mechanistic worldview, or might it help us rediscover dimensions of mind that transcend machinery altogether? It's striking how near we now are to the possibilities we once only speculated about. Quantum computing, self-learning systems, large language models very much as Terence describes—and the looming prospect of superintelligence—have moved from the margins to the mainstream. But the heart of the conversation remains just as relevant today, if not more so: what is consciousness, and how might we participate in its unfolding evolution?

Brian Roemmele

147,955 次观看 • 8 个月前

With enough data, robots and AI can learn “world models” that let them predict the results of their actions. These models are a way to learn how embodied AI agents can perform a wide variety of useful tasks — but they require a huge amount of data. The team at General Intuition General Intuition has a solution: use data from video games! Games teach movement, problem solving, and complex spatial reasoning, and they come in a staggering diversity of forms, covering a wide variety of problems. What’s more, the captured data is high-quality, without the noise or annotation error that can come from We sat down with Pim de Witte and Adam Jelley from the General Intuition team to learn more about their history, their plans, and their philosophy.
53:51

With enough data, robots and AI can learn “world models” that let them predict the results of their actions. These models are a way to learn how embodied AI agents can perform a wide variety of useful tasks — but they require a huge amount of data. The team at General Intuition General Intuition has a solution: use data from video games! Games teach movement, problem solving, and complex spatial reasoning, and they come in a staggering diversity of forms, covering a wide variety of problems. What’s more, the captured data is high-quality, without the noise or annotation error that can come from We sat down with Pim de Witte and Adam Jelley from the General Intuition team to learn more about their history, their plans, and their philosophy.

RoboPapers

85,927 次观看 • 8 个月前

A few months ago we set out to understand exactly how our models can be used to accelerate progress in robotics and other AI systems that don’t just represent the world, but are actually able to interact with it. We’ve been collaborating with leading companies in the space and we’ve developed an initial approach that we're now opening up to accelerate development across the industry. Our fifth announcement is GWM Robotics. GWM Robotics is a learned simulator that generates synthetic data for scalable robot training and policy evaluation, removing the bottlenecks of physical hardware.
1:14

A few months ago we set out to understand exactly how our models can be used to accelerate progress in robotics and other AI systems that don’t just represent the world, but are actually able to interact with it. We’ve been collaborating with leading companies in the space and we’ve developed an initial approach that we're now opening up to accelerate development across the industry. Our fifth announcement is GWM Robotics. GWM Robotics is a learned simulator that generates synthetic data for scalable robot training and policy evaluation, removing the bottlenecks of physical hardware.

Runway

35,040 次观看 • 7 个月前

🌎Create, Tokenize, and Trade Your Own Worlds This is one way we envision the World Engine. It’s an engine designed to let you create without limits, supported by an AI master agent that assists across every aspect of development. The agent can spawn assets, generate complete scenes and levels, and help with placement, styling, mechanics and coding, all within a single engine. With these capabilities, you can seamlessly build your own world. From there, the launchpad enables you to tokenize that world, pair its token with $NEURAL, create a liquidity pool, and release a tradable token directly tied to your world. 🖥 Watch the video for the full breakdown!
0:53

🌎Create, Tokenize, and Trade Your Own Worlds This is one way we envision the World Engine. It’s an engine designed to let you create without limits, supported by an AI master agent that assists across every aspect of development. The agent can spawn assets, generate complete scenes and levels, and help with placement, styling, mechanics and coding, all within a single engine. With these capabilities, you can seamlessly build your own world. From there, the launchpad enables you to tokenize that world, pair its token with $NEURAL, create a liquidity pool, and release a tradable token directly tied to your world. 🖥 Watch the video for the full breakdown!

NeuralAI

14,562 次观看 • 1 年前

A physical law is not a fact about any single state of the world; it is a relationship between states. An LLM, it turns out, encodes the law in the same way - not as a point, but as a transformation. In new work using Google's Gemma model we show that a model's physical knowledge lives not in static neural states, but in the controlled relationships between them. The idea was inspired by mechanics - a spring’s stiffness is invisible in a photograph: it appears only when we pull the spring and measure its response. We similarly “pulled” on the model using counterfactual prompt pairs and measured how its hidden states moved. This revealed three levels of internal physics: 1⃣ Readability: Broad materials concepts (like corrosion, toughness, or oxidation) are linearly readable directly from intermediate hidden states, even when those exact terms are completely omitted from the prompt. 2⃣ Representation: Rather than absolute state locations, matched state displacements accurately track and order direct, neutral, and inverse constitutive laws across 60 materials science laws (ρ = 0.910), correctly orienting 39 of 40 directional laws. 3⃣ Causal Use: We can bidirectionally steer the model's decisions. Adding a single, frozen microstructural direction to the hidden state causally shifts its output preference in a controlled, relation-appropriate way. This is a major step toward representation-aware scientific AI: building models that are evaluated and rewarded for preserving physical laws internally, resisting shallow text shortcuts, and exposing testable reasoning structures. This gives us a sharp definition of what it means for an LLM to understand physics, and how we can train future models to develop even deeper abstractions about the world.
1:16

A physical law is not a fact about any single state of the world; it is a relationship between states. An LLM, it turns out, encodes the law in the same way - not as a point, but as a transformation. In new work using Google's Gemma model we show that a model's physical knowledge lives not in static neural states, but in the controlled relationships between them. The idea was inspired by mechanics - a spring’s stiffness is invisible in a photograph: it appears only when we pull the spring and measure its response. We similarly “pulled” on the model using counterfactual prompt pairs and measured how its hidden states moved. This revealed three levels of internal physics: 1⃣ Readability: Broad materials concepts (like corrosion, toughness, or oxidation) are linearly readable directly from intermediate hidden states, even when those exact terms are completely omitted from the prompt. 2⃣ Representation: Rather than absolute state locations, matched state displacements accurately track and order direct, neutral, and inverse constitutive laws across 60 materials science laws (ρ = 0.910), correctly orienting 39 of 40 directional laws. 3⃣ Causal Use: We can bidirectionally steer the model's decisions. Adding a single, frozen microstructural direction to the hidden state causally shifts its output preference in a controlled, relation-appropriate way. This is a major step toward representation-aware scientific AI: building models that are evaluated and rewarded for preserving physical laws internally, resisting shallow text shortcuts, and exposing testable reasoning structures. This gives us a sharp definition of what it means for an LLM to understand physics, and how we can train future models to develop even deeper abstractions about the world.

Markus J. Buehler

24,212 次观看 • 4 天前

We have officially submitted our project to the Pump.fun Hackathon. Through this initiative, our goal is to test Grok in real world conditions and push it to its full operational limits. We want to explore the complete range of it's capabilities, observe how it performs under continuous and complex decision making scenarios, and clearly understand where it's strengths end and it's boundaries begin. This is not a theoretical experiment. We are applying Grok across hardware, software, and physical systems, using live data and real world constraints. Our long term vision is to scale this into something much bigger a fully automated, real world farm powered by robotics, intelligent systems, and AI driven optimization. By building in public and testing without shortcuts, we aim to learn fast, iterate openly, and discover how far this technology can truly go.
3:26

We have officially submitted our project to the Pump.fun Hackathon. Through this initiative, our goal is to test Grok in real world conditions and push it to its full operational limits. We want to explore the complete range of it's capabilities, observe how it performs under continuous and complex decision making scenarios, and clearly understand where it's strengths end and it's boundaries begin. This is not a theoretical experiment. We are applying Grok across hardware, software, and physical systems, using live data and real world constraints. Our long term vision is to scale this into something much bigger a fully automated, real world farm powered by robotics, intelligent systems, and AI driven optimization. By building in public and testing without shortcuts, we aim to learn fast, iterate openly, and discover how far this technology can truly go.

Grok Potato

32,252 次观看 • 6 个月前

Ilya Sutskever explains why AI will do 100% the work that human can do within few years. "Slowly but surely, or maybe not so slowly, AI will keep getting better. The day will come when AI will do all of our, all the things that we can do, not just some of them, but all of them. Anything which I can learn, anything which any one of you can learn, the AI could do as well. How do we know this, by the way? How can I be so sure? How can I be so sure of that? The reason is that all of us have a brain, and the brain is a biological computer. That's why we have a brain; the brain is a biological computer. So why can't the digital computer, a digital brain, do the same things? This is the one-sentence summary for why AI will be able to do all those things: because we have a brain, and the brain is a biological computer." --- Full Video on 'University of Toronto' YT Channel (link in comment)
0:53

Ilya Sutskever explains why AI will do 100% the work that human can do within few years. "Slowly but surely, or maybe not so slowly, AI will keep getting better. The day will come when AI will do all of our, all the things that we can do, not just some of them, but all of them. Anything which I can learn, anything which any one of you can learn, the AI could do as well. How do we know this, by the way? How can I be so sure? How can I be so sure of that? The reason is that all of us have a brain, and the brain is a biological computer. That's why we have a brain; the brain is a biological computer. So why can't the digital computer, a digital brain, do the same things? This is the one-sentence summary for why AI will be able to do all those things: because we have a brain, and the brain is a biological computer." --- Full Video on 'University of Toronto' YT Channel (link in comment)

Rohan Paul

334,691 次观看 • 10 个月前

Been not a CEO for 24 hours. Decided to build my wife a 3d walkthrough of the new house we are building with Fable so she can preview changes and fixtures. I need to learn how to read books or something. But this is cool. Video also edited in Fable.
1:04

Been not a CEO for 24 hours. Decided to build my wife a 3d walkthrough of the new house we are building with Fable so she can preview changes and fixtures. I need to learn how to read books or something. But this is cool. Video also edited in Fable.

Cody Plofker

92,014 次观看 • 19 天前