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.

Next week I’ll put online physics examples, and I’ll need some gamer testers👾 The magic of Three.js Blocks Engine is that users can plug in their own Physics Models: Platformers, FPS, RTS, anything. It even ships with presets like quake, here I vibe coded a CS1.6 surf mod!

Renaud

12,331 subscribers

55,089 Aufrufe • vor 8 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Some progress on my CS 1.6 surf mod! ⛷️ It’s accurate enough now that I can’t complete it, starting to feel just like the original. 😄 Any surf experts already spotting obvious physics issues from the video? I’ll put an online demo up tomorrow!

Some progress on my CS 1.6 surf mod! ⛷️ It’s accurate enough now that I can’t complete it, starting to feel just like the original. 😄 Any surf experts already spotting obvious physics issues from the video? I’ll put an online demo up tomorrow!

Renaud

32,308 Aufrufe • vor 8 Monaten

The 𝟒-𝟏-𝟐-𝟏-𝟐 (𝟐) is finally here and it is CRACKED🔥 #FC24 Genuinely surprised how good it is in possession too! Tiki-Taka, runs in behind, counter attacks galore😮‍💨 Anyway, I NEED TESTERS‼️ drop a comment below and I’ll send it over to some of you for some feedback⬇️

The 𝟒-𝟏-𝟐-𝟏-𝟐 (𝟐) is finally here and it is CRACKED🔥 #FC24 Genuinely surprised how good it is in possession too! Tiki-Taka, runs in behind, counter attacks galore😮‍💨 Anyway, I NEED TESTERS‼️ drop a comment below and I’ll send it over to some of you for some feedback⬇️

FTD - EAFC Trader/Creator

184,131 Aufrufe • vor 2 Jahren

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.

Leandro von Werra

97,262 Aufrufe • vor 3 Monaten

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

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

Jim Fan

6,183,111 Aufrufe • vor 2 Jahren

Many people laugh at me, but that’s ok. This is my next $ million-dollar business in the making. Soon, I’ll have a fleet of Teslas, working for me 24/7, generating $ for me while I sleep. In every major city, I probably won’t even need my own car anymore bc I’ll just haul a ride from my own fleet. That’s the future I see. And when it happens, they’ll again say I was lucky.

Many people laugh at me, but that’s ok. This is my next $ million-dollar business in the making. Soon, I’ll have a fleet of Teslas, working for me 24/7, generating $ for me while I sleep. In every major city, I probably won’t even need my own car anymore bc I’ll just haul a ride from my own fleet. That’s the future I see. And when it happens, they’ll again say I was lucky.

Teslaconomics

227,079 Aufrufe • vor 1 Jahr

I am really super happy to show you my research that transform 3D volumetric capture of man capture with Kartel.ai and with env gaussian splatting generated with World Labs in a three.js player . And all that is "upscale" using Hunyuan vid2vid model with a Lora train on videos on the main actor. Hope the future of movie is here :) . Still need some work, but you can get the idea

I am really super happy to show you my research that transform 3D volumetric capture of man capture with Kartel.ai and with env gaussian splatting generated with World Labs in a three.js player . And all that is "upscale" using Hunyuan vid2vid model with a Lora train on videos on the main actor. Hope the future of movie is here :) . Still need some work, but you can get the idea

Lovis Odin

23,004 Aufrufe • vor 1 Jahr

I am summing up our interaction with big boys of global engine supply chain in Wings India. Pratt & Whitney and Rolls Royce stated : An engine is a complex and strategic tech, most of the players have mastered it with more than half a century of continous efforts. India has shown phenomonal efforts and progress in their pursuit of developing of an engine. India has the minds, it just need a right collabration to speed up the process which can take 10-15 years on its own.

I am summing up our interaction with big boys of global engine supply chain in Wings India. Pratt & Whitney and Rolls Royce stated : An engine is a complex and strategic tech, most of the players have mastered it with more than half a century of continous efforts. India has shown phenomonal efforts and progress in their pursuit of developing of an engine. India has the minds, it just need a right collabration to speed up the process which can take 10-15 years on its own.

Elite Predators

40,403 Aufrufe • vor 7 Monaten

Tomorrow is a big day for me. I’m going to do an activity in my daughter’s class (she’s 5), and I’ll be teaching them what AI is. She’s excited about it, but honestly, I think I’m even more excited. I’ll tell them a little bit of history, we’ll play some games… I’ll try to make it as fun as possible, but always with a focus on ethical and responsible use. Of course, it won’t be a tutorial on how to use any tools, lol. They’re still very young, and in my opinion, it’ll be years before they actually need to start using these tools. But I think it’s important for them to start getting some awareness so they can be prepared for the future that’s coming their way.

Tomorrow is a big day for me. I’m going to do an activity in my daughter’s class (she’s 5), and I’ll be teaching them what AI is. She’s excited about it, but honestly, I think I’m even more excited. I’ll tell them a little bit of history, we’ll play some games… I’ll try to make it as fun as possible, but always with a focus on ethical and responsible use. Of course, it won’t be a tutorial on how to use any tools, lol. They’re still very young, and in my opinion, it’ll be years before they actually need to start using these tools. But I think it’s important for them to start getting some awareness so they can be prepared for the future that’s coming their way.

TechHalla

18,651 Aufrufe • vor 1 Jahr

The part of PixVerse that stood out to me was not just the AI fan host, but the chance to turn a football cheer into something personal. Users can interact with Reina, create personalized cheer videos, and enter a lucky draw for PixVerse service credits. The credits can only be used on PixVerse. They are non transferable and have no cash value. It is a playful early experiment, but I like that it gives users a simple way to make something of their own and share it with others. That mix of creating a cheer moment and joining the credit draw is what I would want to try 👉

The part of PixVerse that stood out to me was not just the AI fan host, but the chance to turn a football cheer into something personal. Users can interact with Reina, create personalized cheer videos, and enter a lucky draw for PixVerse service credits. The credits can only be used on PixVerse. They are non transferable and have no cash value. It is a playful early experiment, but I like that it gives users a simple way to make something of their own and share it with others. That mix of creating a cheer moment and joining the credit draw is what I would want to try 👉

Amit

46,845 Aufrufe • vor 1 Monat

Bon bread is what we eat in my house, and honestly we’ve never had any issues with it. I’ve even recommended it to a few friends, and none of them have complained so far. That said, I haven’t watched the video the lady made, so I can’t confirm whether she mentioned any specific brand or not. So just to be certain, I’ll run my own little test. I’ll stop eating from this very one here for about 1–2 weeks, then come back with a proper update on what I observe. Deal?

MrEazzy

339,021 Aufrufe • vor 4 Monaten

If you typically stream with a 3D model, I highly recommend that you pose your model when you’re not doing full body mocap instead of letting it stay in the stiff generic pose! It makes a huge difference in how your energy is conveyed (ᗒ⩊ᗕ)⸝ި ʕᦏ⌎ I’m only saying this because I noticed this a lot with my own 3D kids, but here’s a comparison showcase: ← default pose & default pendulum physics in Warudo → custom poses & slightly adjusted pendulum physics If you find it hard to pose within Warudo by using bone offsets or none of the existing poses in Warudo vibe with you, you can make your own like me! I made my custom poses in “VRM Posing Desktop” (this is the BEST vrm posing app I’ve ever used in the past 3 years) and exported them as Unity anims then dropped them into Warudo’s animation folder! You can then make a simple blueprint in Warudo to toggle between poses and make your model look more alive! It should fit especially well for just chatting streams 🙂‍↕️✨

If you typically stream with a 3D model, I highly recommend that you pose your model when you’re not doing full body mocap instead of letting it stay in the stiff generic pose! It makes a huge difference in how your energy is conveyed (ᗒ⩊ᗕ)⸝ި ʕᦏ⌎ I’m only saying this because I noticed this a lot with my own 3D kids, but here’s a comparison showcase: ← default pose & default pendulum physics in Warudo → custom poses & slightly adjusted pendulum physics If you find it hard to pose within Warudo by using bone offsets or none of the existing poses in Warudo vibe with you, you can make your own like me! I made my custom poses in “VRM Posing Desktop” (this is the BEST vrm posing app I’ve ever used in the past 3 years) and exported them as Unity anims then dropped them into Warudo’s animation folder! You can then make a simple blueprint in Warudo to toggle between poses and make your model look more alive! It should fit especially well for just chatting streams 🙂‍↕️✨

𝗞𝗔𝗥𝗜𝗛𝗔 🌘🍀 3D Artist ☻

15,700 Aufrufe • vor 5 Monaten

Outfits are cool... but what about hairstyles? AIKODE offers a wide variety of hairstyles with custom physics that work seamlessly in both cutscenes and gameplay. You can change the color, add different tint masks and accessories. Each hairstyle is fully rigged, strand by strand, ensuring that every style (despite significant differences) functions just like the default hair, without any glitches in cutscenes or gameplay. Here you can see some of the hairstyles in-game. #aikode #UE5

Outfits are cool... but what about hairstyles? AIKODE offers a wide variety of hairstyles with custom physics that work seamlessly in both cutscenes and gameplay. You can change the color, add different tint masks and accessories. Each hairstyle is fully rigged, strand by strand, ensuring that every style (despite significant differences) functions just like the default hair, without any glitches in cutscenes or gameplay. Here you can see some of the hairstyles in-game. #aikode #UE5

AIKODE

40,738 Aufrufe • vor 2 Jahren

🚨 BREAKING: Physics just broke its own rulebook. For decades, every particle in the universe fit into 2 types • Bosons (share space) • Fermions (avoid each other) Now? Scientists just created something in between. A new class of particles called anyons that can behave partly like both. Even crazier In 1D systems, you can tune their behavior like a dial between order and exclusion. This means Particle identity isn’t fixed Quantum behavior is adjustable Reality depends on dimensional constraints Think about that. If the rules change based on dimension. then what we call “fundamental” might just be a limit case. So the real question is Are particles truly different… or just different expressions of the same underlying structure? Follow for deeper physics that challenges the foundations.

🚨 BREAKING: Physics just broke its own rulebook. For decades, every particle in the universe fit into 2 types • Bosons (share space) • Fermions (avoid each other) Now? Scientists just created something in between. A new class of particles called anyons that can behave partly like both. Even crazier In 1D systems, you can tune their behavior like a dial between order and exclusion. This means Particle identity isn’t fixed Quantum behavior is adjustable Reality depends on dimensional constraints Think about that. If the rules change based on dimension. then what we call “fundamental” might just be a limit case. So the real question is Are particles truly different… or just different expressions of the same underlying structure? Follow for deeper physics that challenges the foundations.

TheNewPhysics

21,603 Aufrufe • vor 4 Monaten

✨ I can now generate 3d assets for my drone sim at directly from Cursor (sponsor of #vibejam) I need buildings that you'd see in a war torn city, like warehouses in ruins, broken down abandoned houses, bombed out bridges etc. Nano Banana Pro or 2 can generate them really well and then you can put them in an image-to-3d model and you get a GLB or FBX That one you can then import into your Three.js game, the models might be big though, in my case like 16MB, so I ask it to compress it and make it more low poly so it loads fast ThreeJS then loads the individual GLBs on page load and puts them in my drone sim somewhere randomly, I think I should remove some of the grass and match the sandy color of the ruins though to make it fit in more

✨ I can now generate 3d assets for my drone sim at directly from Cursor (sponsor of #vibejam) I need buildings that you'd see in a war torn city, like warehouses in ruins, broken down abandoned houses, bombed out bridges etc. Nano Banana Pro or 2 can generate them really well and then you can put them in an image-to-3d model and you get a GLB or FBX That one you can then import into your Three.js game, the models might be big though, in my case like 16MB, so I ask it to compress it and make it more low poly so it loads fast ThreeJS then loads the individual GLBs on page load and puts them in my drone sim somewhere randomly, I think I should remove some of the grass and match the sandy color of the ruins though to make it fit in more

@levelsio

134,777 Aufrufe • vor 4 Monaten

🚁 Adding an Apache attack helicopter today I think I will rewrite the entire flight model today again to be ambiguous of what kind of vehicle it is Planes behave very different than helicopters and different than vehicles like tanks or pedestrians Because people here also requested "Guy with bazooka" so that will be next I have no idea if everyone else is just lying about using AI for their plane models but mine look so clunky (but I like the look), but I now tried with Claude 3.5 and 3.7 and Grok 3 and they all just generate clunky models, not beautiful like you see in other AI vibe coded games, so either they bs'ing or I'm retarded I also have to move sub parts of each model like for 30 minutes until everything fits, AI has a really hard time with 3d models But okay the look is kinda cute

🚁 Adding an Apache attack helicopter today I think I will rewrite the entire flight model today again to be ambiguous of what kind of vehicle it is Planes behave very different than helicopters and different than vehicles like tanks or pedestrians Because people here also requested "Guy with bazooka" so that will be next I have no idea if everyone else is just lying about using AI for their plane models but mine look so clunky (but I like the look), but I now tried with Claude 3.5 and 3.7 and Grok 3 and they all just generate clunky models, not beautiful like you see in other AI vibe coded games, so either they bs'ing or I'm retarded I also have to move sub parts of each model like for 30 minutes until everything fits, AI has a really hard time with 3d models But okay the look is kinda cute

@levelsio

485,431 Aufrufe • vor 1 Jahr

Okay this is kinda wild 👀 NVIDIA is basically handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.

Okay this is kinda wild 👀 NVIDIA is basically handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.

Stefan 3D AI

26,272 Aufrufe • vor 1 Monat

HERE IT IS! The OFFICIAL 1v1 for my PRO CARD. 🏆 In Men’s Physique, the winner of the Short Class goes head to head with the winner of the Tall Class… and whoever wins that battle earns their Pro Card. I’ll be posting the results in my next post! Until then… Take a look through the carousel and let me know Who do YOU think took it? 👀

HERE IT IS! The OFFICIAL 1v1 for my PRO CARD. 🏆 In Men’s Physique, the winner of the Short Class goes head to head with the winner of the Tall Class… and whoever wins that battle earns their Pro Card. I’ll be posting the results in my next post! Until then… Take a look through the carousel and let me know Who do YOU think took it? 👀

FOUSEY

13,178 Aufrufe • vor 9 Monaten

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

Jim Fan

594,014 Aufrufe • vor 2 Jahren

claude fable 5 is live. spawn 5.0 was built with it: 1,687 prompts, 102 sessions, my job shifted from architecture to judging taste. what we built, each of which would've been at least a month with a whole team on opus: — a from-scratch physics engine (mantle) that rivals rapier, testable in a day as a side thread — clustered froxel lighting: 8 lights to 1,000+ fully dynamic ("it's stupid fast" — creator of threejs) — realtime diffuse GI on webgpu, on your phone (landing in the next update) — million-particle gpu vfx with a shader architecture beyond what unreal and unity ship — mmo-scale netcode plus, for good measure: an (alpha) native ios app. all of it in about a week. all of it running on mobile. and the list doesn't include half of what we shipped — full changelog in the thread below. and the part the benchmarks won't show you: this model has a wonderful personality. it's genuinely funny. i laughed so hard i cried multiple times, mid-physics-rewrite. the genius and the character aren't separate features.

claude fable 5 is live. spawn 5.0 was built with it: 1,687 prompts, 102 sessions, my job shifted from architecture to judging taste. what we built, each of which would've been at least a month with a whole team on opus: — a from-scratch physics engine (mantle) that rivals rapier, testable in a day as a side thread — clustered froxel lighting: 8 lights to 1,000+ fully dynamic ("it's stupid fast" — creator of threejs) — realtime diffuse GI on webgpu, on your phone (landing in the next update) — million-particle gpu vfx with a shader architecture beyond what unreal and unity ship — mmo-scale netcode plus, for good measure: an (alpha) native ios app. all of it in about a week. all of it running on mobile. and the list doesn't include half of what we shipped — full changelog in the thread below. and the part the benchmarks won't show you: this model has a wonderful personality. it's genuinely funny. i laughed so hard i cried multiple times, mid-physics-rewrite. the genius and the character aren't separate features.

jacob

55,515 Aufrufe • vor 2 Monaten