Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall →... show more

abdel

30,887 subscribers

39,459 Aufrufe • vor 4 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

32 Kommentare

Profilbild von abdel

abdelvor 4 Monaten

thanks @feltroidPrime for recording setup and the edits for the highlights

Profilbild von eni 🍞

eni 🍞vor 4 Monaten

can't believe I was lucky enough to see this live

Profilbild von abdel

abdelvor 4 Monaten

😘

Profilbild von Jay H

Jay Hvor 4 Monaten

@Scobleizer I kinda agree that LLMs can only take us so far. The next bog endeavour is to get the hardware (robotics) to where LLMs are now

Profilbild von LeBonPrompt

LeBonPromptvor 4 Monaten

Latent-space planning is the underrated bit. No pixel rendering, so it stays fast enough to close a real control loop.

Profilbild von Gaylord

Gaylordvor 4 Monaten

👀

Profilbild von Tracy Masucci

Tracy Masuccivor 4 Monaten

@Scobleizer Interesting!

Profilbild von Cyrus

Cyrusvor 4 Monaten

@Scobleizer no opposite

Profilbild von Arnold Kuepo

Arnold Kuepovor 4 Monaten

I also think that LLMs have reached their limits and that World Models could be the logical next step, but I wonder if we currently have the hardware that would make such a paradigm possible.

Profilbild von Skyfall AI

Skyfall AIvor 4 Monaten

World models > LLMs

Profilbild von Alex Ken

Alex Kenvor 4 Monaten

Is this on YouTube ?

Profilbild von abdel

abdelvor 4 Monaten

Nope

Profilbild von infiniteidiot

infiniteidiotvor 4 Monaten

Thanks for sharing the insights and the perspective what the future could Look like. Interesting.

Profilbild von sal

salvor 4 Monaten

Learned a lot, great presentation

Profilbild von abdel

abdelvor 4 Monaten

Thanks 🙏

Profilbild von PunkXBT

PunkXBTvor 2 Monaten

embodied intelligence feels like the next frontier, language alone can only get you so far

Profilbild von Alex Houdz 🍉

Alex Houdz 🍉vor 4 Monaten

i was just listening yesterday Yann LeCun talking about world models, thanks Abdel for the great presentation 🙏

Profilbild von abdel

abdelvor 4 Monaten

Yann LeCun is the GOAT. I was skeptical. Now I am fully convinced. His push for open source and open research is amazing. Love this guy and his mindset and ability to fight fiercely for his strong convictions. Thanks.

Profilbild von Liya

Liyavor 4 Monaten

this clarifies the embodied intelligence path

Profilbild von TriDung.sol

TriDung.solvor 4 Monaten

llms can talk the talk but world models might actually walk it

Profilbild von T_Khanh2026.eth

T_Khanh2026.ethvor 2 Monaten

Latent space planning is the only way to escape the token prediction trap

Profilbild von ۟Mew 〽️🐾

۟Mew 〽️🐾vor 4 Monaten

World models are the real upgrade. LLMs were just the warmup.

Profilbild von Crypto Hustler

Crypto Hustlervor 2 Monaten

World models might be the real shift.

Profilbild von Xipe Totec

Xipe Totecvor 3 Monaten

Hi. Musk must have broken redirects because this does not work it is in the starknet repo (the root)

Profilbild von Snibby

Snibbyvor 3 Monaten

world models feel like the missing piece for AI moving from predicting text to actually understanding environments and actions

Profilbild von Shtihmas | Trade Spot 0% Fees On CoinUp

Shtihmas | Trade Spot 0% Fees On CoinUpvor 4 Monaten

World models > word models. Finally.

Profilbild von Dr. C. Misiak🇩🇪Psychologist🇹🇷🇱🇰🇰🇪🇻🇳🇵🇭

Dr. C. Misiak🇩🇪Psychologist🇹🇷🇱🇰🇰🇪🇻🇳🇵🇭vor 4 Monaten

SHRDLU is calling ...

Profilbild von ZeboSato

ZeboSatovor 4 Monaten

Est-ce que c’est toi ou je me trompe? Est-ce que tu as fait des cétogène diet ? 👍

Profilbild von abdel

abdelvor 4 Monaten

c'est bien moi. non pour la seconde question

Profilbild von ZeboSato

ZeboSatovor 4 Monaten

Nice 👍 keep going!

Profilbild von Puzzle Paws

Puzzle Pawsvor 4 Monaten

man 'dead end' is a hell of a claim. world models look legit but LLMs aren't leaving my stack. what's the actual license on that 'open' framework?

Profilbild von VAULT wallet

VAULT walletvor 4 Monaten

World models make sense, but LLMs aren't going anywhere. They’ll evolve together intelligence needs both talk and touch.

Ähnliche Videos

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 Aufrufe • vor 5 Monaten

Yann LeCun says language isn’t intelligence. Predicting text doesn’t mean understanding reality. The real world is messy, physical, and causal and today’s LLMs barely touch that. The next leap is Physical AI: world models, cause and effect, real planning. Do you think LLMs can evolve into this, or do we need a completely new architecture?

Yann LeCun says language isn’t intelligence. Predicting text doesn’t mean understanding reality. The real world is messy, physical, and causal and today’s LLMs barely touch that. The next leap is Physical AI: world models, cause and effect, real planning. Do you think LLMs can evolve into this, or do we need a completely new architecture?

VraserX e/acc

76,220 Aufrufe • vor 9 Monaten

Large language models reason through text. Vision‑language‑action models reason through the real world. By fusing perception, context, and action from live video, VLAs deliver the awareness physical AI needs for next‑gen robotics and edge systems.

Large language models reason through text. Vision‑language‑action models reason through the real world. By fusing perception, context, and action from live video, VLAs deliver the awareness physical AI needs for next‑gen robotics and edge systems.

Intel

15,931 Aufrufe • vor 8 Monaten

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

Jon Hernandez

20,660 Aufrufe • vor 8 Monaten

World models have a causality problem. Realistic videos are not enough. A world model should predict the future caused by an action, not just a plausible future. We find that many latent-action world models generate convincing videos while barely responding to the supplied action. The root cause lies in Latent Action Models (LAMs): reconstruction objectives entangle action-induced dynamics with action-irrelevant visual changes, producing visually confounded latent actions. Our solution is CD-LAM (Causally Debiased Latent Action Model). It cleanses latent action representations before pre-training begins, requiring zero changes to backbone architectures, latent dimensions, or action interfaces. Key Benchmark Results: - Action Controllability: Cuts action-following error by >30% while simultaneously enhancing visual fidelity. - Extreme Sample Efficiency: Achieves baseline performance in just 3,000 post-training steps instead of 50,000 - a >10x speedup. By removing visual confounding, CD-LAM bridges the gap between passive video prediction and actionable causal intelligence for robotics. The next bottleneck for world models isn’t realism. It’s causality. Paper, project page and additional resources in the reply below. #WorldModels #EmbodiedAI #Robotics #CausalAI

World models have a causality problem. Realistic videos are not enough. A world model should predict the future caused by an action, not just a plausible future. We find that many latent-action world models generate convincing videos while barely responding to the supplied action. The root cause lies in Latent Action Models (LAMs): reconstruction objectives entangle action-induced dynamics with action-irrelevant visual changes, producing visually confounded latent actions. Our solution is CD-LAM (Causally Debiased Latent Action Model). It cleanses latent action representations before pre-training begins, requiring zero changes to backbone architectures, latent dimensions, or action interfaces. Key Benchmark Results: - Action Controllability: Cuts action-following error by >30% while simultaneously enhancing visual fidelity. - Extreme Sample Efficiency: Achieves baseline performance in just 3,000 post-training steps instead of 50,000 - a >10x speedup. By removing visual confounding, CD-LAM bridges the gap between passive video prediction and actionable causal intelligence for robotics. The next bottleneck for world models isn’t realism. It’s causality. Paper, project page and additional resources in the reply below. #WorldModels #EmbodiedAI #Robotics #CausalAI

Biwei Huang

15,084 Aufrufe • vor 3 Monaten

World models that aren't grounded in the real world will never reach their potential for physical AI. 🌎 Just as RAG cut hallucination in LLMs, location-specific grounding lets robots choose the right action in the right place. Read more about Niantic Spatial’s thinking: #WorldModels #PhysicalAI #AI #EmbodiedAI #SpatialAI #Robotics

World models that aren't grounded in the real world will never reach their potential for physical AI. 🌎 Just as RAG cut hallucination in LLMs, location-specific grounding lets robots choose the right action in the right place. Read more about Niantic Spatial’s thinking: #WorldModels #PhysicalAI #AI #EmbodiedAI #SpatialAI #Robotics

Niantic Spatial 🌎

34,745 Aufrufe • vor 1 Monat

Before AI can understand the physical world, it needs data about the physical world. Not just images. Spatial environments. Real streets, buildings, parks, stores, museums, and public spaces captured in 3D. OVER has already reconstructed 290,000+ real-world 3D scenes, creating a growing dataset for the next generation of spatial and embodied AI. And this is exactly the kind of real-world spatial data AI companies are looking for. We're already in conversations with multiple AI and Robotics companies exploring how OVER's dataset can support the development and training of models that need to understand the physical world. The next AI race will be about real-world data.

Before AI can understand the physical world, it needs data about the physical world. Not just images. Spatial environments. Real streets, buildings, parks, stores, museums, and public spaces captured in 3D. OVER has already reconstructed 290,000+ real-world 3D scenes, creating a growing dataset for the next generation of spatial and embodied AI. And this is exactly the kind of real-world spatial data AI companies are looking for. We're already in conversations with multiple AI and Robotics companies exploring how OVER's dataset can support the development and training of models that need to understand the physical world. The next AI race will be about real-world data.

Over the Reality 🌐

24,343 Aufrufe • vor 1 Monat

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 Aufrufe • vor 10 Monaten

Introducing WorldForge: testable world-model workflows for physical AI systems. You can think of it, loosely, as “LangChain for world models”. The problem is that “world model” has become an overloaded label. Depending on context, it can mean a video generator, a cost model, a robot policy, a JEPA-style latent predictor, etc. They share almost nothing, different inputs, runtimes, failure modes. I built WorldForge to stop pretending they're interchangeable. Front-door demo: a real Hugging Face LeRobot (LeRobot) diffusion_pusht policy combined with LeWorldModel by Lucas Maes checkpoint for scoring. Both run locally on my MacBook in the demo video. LeWM is extremely efficient (~15M params), can plan up to 48× faster, and runs on commodity hardware. WorldForge wires the loop: policy → candidates → score → select Replay happens in a local TUI today, but the same loop could drive a real robot in the world. Would love feedback from people working on world models, physical AI, robotics, ML infra, and adjacent tooling. Fully open source. Contributions very welcome. Plan in the dream, replay in real world.

Introducing WorldForge: testable world-model workflows for physical AI systems. You can think of it, loosely, as “LangChain for world models”. The problem is that “world model” has become an overloaded label. Depending on context, it can mean a video generator, a cost model, a robot policy, a JEPA-style latent predictor, etc. They share almost nothing, different inputs, runtimes, failure modes. I built WorldForge to stop pretending they're interchangeable. Front-door demo: a real Hugging Face LeRobot (LeRobot) diffusion_pusht policy combined with LeWorldModel by Lucas Maes checkpoint for scoring. Both run locally on my MacBook in the demo video. LeWM is extremely efficient (~15M params), can plan up to 48× faster, and runs on commodity hardware. WorldForge wires the loop: policy → candidates → score → select Replay happens in a local TUI today, but the same loop could drive a real robot in the world. Would love feedback from people working on world models, physical AI, robotics, ML infra, and adjacent tooling. Fully open source. Contributions very welcome. Plan in the dream, replay in real world.

abdel

17,001 Aufrufe • vor 6 Monaten

Punchline: World models == VQA (about the future)! Planning with world models can be powerful for robotics/control. But most world models are video generators trained to predict everything, including irrelevant pixels and distractions. We ask - what if a world model only predicted the semantic information necessary for decision-making? Introducing Semantic World Models (SWM). Given an observation and an action sequence, SWMs cast modeling as answering textual questions about the future outcome resulting from the actions. Recasting world modeling as a VQA problem lets us directly leverage the pretrained knowledge and machinery of VLMs for generalizable modeling. We had a lot of fun thinking about how this work helps connect these two seemingly very different fields of study - VLMs and world models! 🧵(1/6) Paper: Fun demo:

Punchline: World models == VQA (about the future)! Planning with world models can be powerful for robotics/control. But most world models are video generators trained to predict everything, including irrelevant pixels and distractions. We ask - what if a world model only predicted the semantic information necessary for decision-making? Introducing Semantic World Models (SWM). Given an observation and an action sequence, SWMs cast modeling as answering textual questions about the future outcome resulting from the actions. Recasting world modeling as a VQA problem lets us directly leverage the pretrained knowledge and machinery of VLMs for generalizable modeling. We had a lot of fun thinking about how this work helps connect these two seemingly very different fields of study - VLMs and world models! 🧵(1/6) Paper: Fun demo:

Abhishek Gupta

61,483 Aufrufe • vor 1 Jahr

Schmidhuber: "Well, large language models are far from AGI. LLMs large language models such as ChatGPT. They are just a clever way of indexing the world's existing human generated knowledge, such that it can easily be addressed through in a way that humans are familiar with, which is natural language. That's good enough to facilitate many desktop jobs, for example, writing summaries of existing documents in a particular style, or creating illustrations or an article. And and so on. However true AGI goes far beyond that. It is much harder, for example, to replace craftsmen such as plumbers or electricians, because the real world, the physical world, is much more challenging than the world behind the screen. At the moment, the only Al that works well is behind the screen, and it's good for desktop to desktop workers. But but not really for for people working in the physical world."

Schmidhuber: "Well, large language models are far from AGI. LLMs large language models such as ChatGPT. They are just a clever way of indexing the world's existing human generated knowledge, such that it can easily be addressed through in a way that humans are familiar with, which is natural language. That's good enough to facilitate many desktop jobs, for example, writing summaries of existing documents in a particular style, or creating illustrations or an article. And and so on. However true AGI goes far beyond that. It is much harder, for example, to replace craftsmen such as plumbers or electricians, because the real world, the physical world, is much more challenging than the world behind the screen. At the moment, the only Al that works well is behind the screen, and it's good for desktop to desktop workers. But but not really for for people working in the physical world."

Goran Majić

28,839 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 6 Monaten

You asked for it, we delivered. The full keynote is live. In this keynote, we unveil our enhanced vision to become the World’s Ears for AI & Robotics. We are creating the world’s first decentralized infrastructure for real-world audio intelligence. Check-out our new website: Start training Voice AI now & get rewarded: From noise-level mapping to multilingual voice data and the future of live audio streams, Silencio is building the critical audio data layer that will power foundation models, embodied AI, autonomous vehicles, and robotics.

You asked for it, we delivered. The full keynote is live. In this keynote, we unveil our enhanced vision to become the World’s Ears for AI & Robotics. We are creating the world’s first decentralized infrastructure for real-world audio intelligence. Check-out our new website: Start training Voice AI now & get rewarded: From noise-level mapping to multilingual voice data and the future of live audio streams, Silencio is building the critical audio data layer that will power foundation models, embodied AI, autonomous vehicles, and robotics.

Silencio | Voice Data for AI

176,480 Aufrufe • vor 1 Jahr

Karol Hausman is the co-founder and CEO of Physical Intelligence, a robotics company building a general-purpose “AI brain for the physical world.” The company has raised more than $1 billion in funding to develop foundation models that allow robots to operate across many machines, environments, and tasks rather than being programmed for a single purpose. In our conversation, we explore: • The moment a lecture from Sergey Levine convinced him to abandon his PhD research direction and pivot fully to deep learning • The case for building a general “AI brain” for the physical world rather than a single specialized robot • The role of real-world data in training robots, the limits of simulation, and how deployment could create a powerful data flywheel • The unique challenges of physical intelligence and why robots must operate with far higher reliability than language models Thank you to the partners who make this possible - Brex: The intelligent finance platform: - Granola: The app that might actually make you love meetings: Timestamps (00:00) Intro (04:05) Karol’s early fascination with robots (18:21) Karol’s entry point to robotics and PhD program (25:49) Combining robotics with LLMs: The Taylor Swift demo (30:48) The 1970s SHRDLU AI experiment (39:40) How research shapes what Physical Intelligence builds (49:07) The return of reinforcement learning in robotics (1:00:00) NVIDIA’s simulation engines (1:07:31) Compensating for missing senses

Karol Hausman is the co-founder and CEO of Physical Intelligence, a robotics company building a general-purpose “AI brain for the physical world.” The company has raised more than $1 billion in funding to develop foundation models that allow robots to operate across many machines, environments, and tasks rather than being programmed for a single purpose. In our conversation, we explore: • The moment a lecture from Sergey Levine convinced him to abandon his PhD research direction and pivot fully to deep learning • The case for building a general “AI brain” for the physical world rather than a single specialized robot • The role of real-world data in training robots, the limits of simulation, and how deployment could create a powerful data flywheel • The unique challenges of physical intelligence and why robots must operate with far higher reliability than language models Thank you to the partners who make this possible - Brex: The intelligent finance platform: - Granola: The app that might actually make you love meetings: Timestamps (00:00) Intro (04:05) Karol’s early fascination with robots (18:21) Karol’s entry point to robotics and PhD program (25:49) Combining robotics with LLMs: The Taylor Swift demo (30:48) The 1970s SHRDLU AI experiment (39:40) How research shapes what Physical Intelligence builds (49:07) The return of reinforcement learning in robotics (1:00:00) NVIDIA’s simulation engines (1:07:31) Compensating for missing senses

Mario Gabriele 🦊

27,871 Aufrufe • vor 7 Monaten

The next frontier after language models is world models, and learning to predict the next state of a world. Hear from our researchers how these models really work at a low-level and the mountain we're climbing. A general-purpose world simulator (AKA sci-fi) is now in sight.

The next frontier after language models is world models, and learning to predict the next state of a world. Hear from our researchers how these models really work at a low-level and the mountain we're climbing. A general-purpose world simulator (AKA sci-fi) is now in sight.

Odyssey

25,961 Aufrufe • vor 11 Monaten

📁 Yann LeCun says that scaling models will not get us to human intelligence. He explains that the industry remains obsessed with making LLMs bigger, but that this path is fundamentally broken. It does not matter how many parameters we add or how many clusters we build, because the models only imitate language patterns. Human intelligence does not emerge from size, it emerges from understanding the world.

📁 Yann LeCun says that scaling models will not get us to human intelligence. He explains that the industry remains obsessed with making LLMs bigger, but that this path is fundamentally broken. It does not matter how many parameters we add or how many clusters we build, because the models only imitate language patterns. Human intelligence does not emerge from size, it emerges from understanding the world.

Jon Hernandez

159,591 Aufrufe • vor 10 Monaten