正在加载视频...

视频加载失败

返回首页

With everyone busily using LLMs + Blender/Three.js to make 3D models, I thought I'd try a different geometric representation. This dragon isn't a mesh, NeRF, 3DGS, or video model: it's 27kb of GLSL code (generated via LLM), defining a closed-form implicit surface. 🧵 [1/n]

keenanisalive's profile picture

Keenan Crane

48,941 subscribers

679,330 次观看 • 7 天前 •via X (Twitter)

教育科学技术
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

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”
0:18

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,927 次观看 • 2 年前

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.
0:12

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,849 次观看 • 1 年前

NVIDIA finally released Neuralangelo's source code! The model can turn videos from any device into detailed 3D structures, fully replicating buildings, sculptures, or other real aworld objects or spaces virtually. Here's how it works: A model utilizes a 2D video with multiple angles of an object or scene. I selects frames from different viewpoints to understand depth, size, and shape. The AI creates an initial 3D representation, similar to a sculptor shaping a subject. The render is optimized to enhance details, like a sculptor refining texture. The outcome is a 3D object or scene suitable for virtual reality, digital twins, or robotics.
0:13

NVIDIA finally released Neuralangelo's source code! The model can turn videos from any device into detailed 3D structures, fully replicating buildings, sculptures, or other real aworld objects or spaces virtually. Here's how it works: A model utilizes a 2D video with multiple angles of an object or scene. I selects frames from different viewpoints to understand depth, size, and shape. The AI creates an initial 3D representation, similar to a sculptor shaping a subject. The render is optimized to enhance details, like a sculptor refining texture. The outcome is a 3D object or scene suitable for virtual reality, digital twins, or robotics.

Lior Alexander

478,069 次观看 • 3 年前

✨ 3d models are now LIVE on Photo AI 😊 You can now turn any AI photo you make into a 3d model by pressing [ 📦 Make 3d model ] And then you can view it inside Photo AI or download it as a .GLB 3d model file It's still very early in AI generated 3d model world but it's nice to have this feature working already As always, the models will keep improving, so this feature will keep getting better (like it did with video, it sucked before, now it's getting passable) Next would be nice to switch to .USDZ so you can load it straight into your iPhone with ARKit and put it in your room Available now for everyone on the Premium and Ultra plan
0:19

✨ 3d models are now LIVE on Photo AI 😊 You can now turn any AI photo you make into a 3d model by pressing [ 📦 Make 3d model ] And then you can view it inside Photo AI or download it as a .GLB 3d model file It's still very early in AI generated 3d model world but it's nice to have this feature working already As always, the models will keep improving, so this feature will keep getting better (like it did with video, it sucked before, now it's getting passable) Next would be nice to switch to .USDZ so you can load it straight into your iPhone with ARKit and put it in your room Available now for everyone on the Premium and Ultra plan

@levelsio

112,930 次观看 • 1 年前

Generative 3d environments just became a thing with the announcement of OpenAI's new video model, Sora. Michael Rublof from took one of those videos, and turned it into a NeRF using Colmap and Nerfstudio. While people are laughing at the topology of generated models, the world is changing around us, and that's exciting and a little scary, but we'll find a way to turn Gen Ai into creative superpowers. I believe in human creativity, in our ability to surprise, to move, to change and to challenge. Here's to the future! #ai #art
0:14

Generative 3d environments just became a thing with the announcement of OpenAI's new video model, Sora. Michael Rublof from took one of those videos, and turned it into a NeRF using Colmap and Nerfstudio. While people are laughing at the topology of generated models, the world is changing around us, and that's exciting and a little scary, but we'll find a way to turn Gen Ai into creative superpowers. I believe in human creativity, in our ability to surprise, to move, to change and to challenge. Here's to the future! #ai #art

Martin Nebelong

288,988 次观看 • 2 年前

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.
0:13

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.

Michael Black

22,353 次观看 • 10 个月前

I spent my Astra tokens trying to teach small Qwen3.5 (9B) to create lowpoly 3D rooms using Blender 🏡 you (or Astra) can take this challenge today here's what I learned: > you need to align geometry with deterministic rewards and VLM-as-a-judge (GLM-5.3-Flash which was a great judge) > I tried GEPA at first with various rewards, model learned to make valid rooms (but that's it) > after solving geometry you need the model to add more details, which is very hard > the stricter the reward function, less advantage you get because task is too hard. grpo didn't help > I tried passing image guidance to both policy (Qwen) and judge (GLM) it didn't improve > I tried tastemaxxing trick in this blog, truth is, flowers can be abstract, a house can't be shoutout to OpenEnv, environment is super simple what can you try? > experiment with different rewards or policy (teach a larger Qwen) > generate a dataset of 150-200 Blender render Bpy examples using Astra, fine-tune Qwen on it first and then try GEPA or GRPO > ???
0:13

I spent my Astra tokens trying to teach small Qwen3.5 (9B) to create lowpoly 3D rooms using Blender 🏡 you (or Astra) can take this challenge today here's what I learned: > you need to align geometry with deterministic rewards and VLM-as-a-judge (GLM-5.3-Flash which was a great judge) > I tried GEPA at first with various rewards, model learned to make valid rooms (but that's it) > after solving geometry you need the model to add more details, which is very hard > the stricter the reward function, less advantage you get because task is too hard. grpo didn't help > I tried passing image guidance to both policy (Qwen) and judge (GLM) it didn't improve > I tried tastemaxxing trick in this blog, truth is, flowers can be abstract, a house can't be shoutout to OpenEnv, environment is super simple what can you try? > experiment with different rewards or policy (teach a larger Qwen) > generate a dataset of 150-200 Blender render Bpy examples using Astra, fine-tune Qwen on it first and then try GEPA or GRPO > ???

merve

22,903 次观看 • 1 个月前

I can already see the tree I'd ski into. If this perspective became interactive, I'd need cheap attempts more than a heroic opening shot. Vivix W1's $0.003/sec would make another eight generated seconds $0.024, with fast generation and comparable quality. That's a useful starting point for a real-time interactive video model you can actually spend time learning to use. The real-time capability is on its API; the run I'd like to try is still a possibility.
0:10

I can already see the tree I'd ski into. If this perspective became interactive, I'd need cheap attempts more than a heroic opening shot. Vivix W1's $0.003/sec would make another eight generated seconds $0.024, with fast generation and comparable quality. That's a useful starting point for a real-time interactive video model you can actually spend time learning to use. The real-time capability is on its API; the run I'd like to try is still a possibility.

Maria

24,201 次观看 • 5 天前

A very happy Monday to the Haringey Conservatives! A very popular party locally, *cough*. Thought I’d make your life easier and do a video of me driving a car. Because I drive all the time, you see! Feel free to watch this all day with the curtains closed guys, and … 1/2
0:18

A very happy Monday to the Haringey Conservatives! A very popular party locally, *cough*. Thought I’d make your life easier and do a video of me driving a car. Because I drive all the time, you see! Feel free to watch this all day with the curtains closed guys, and … 1/2

Carla Francome

16,470 次观看 • 3 年前

You might not believe me but the 3D in this video was procedurally generated using Claude Code in blender. The main things I manually worked on were some texture changes as well as lighting and compositing/colorgrade in post later super cool that ai can help with stuff like this now, especially for a process that would usually take multiple days or even weeks if done traditionally Lmk if you'd want a guide on my process / how I did this
0:12

You might not believe me but the 3D in this video was procedurally generated using Claude Code in blender. The main things I manually worked on were some texture changes as well as lighting and compositing/colorgrade in post later super cool that ai can help with stuff like this now, especially for a process that would usually take multiple days or even weeks if done traditionally Lmk if you'd want a guide on my process / how I did this

newo

140,042 次观看 • 1 个月前

2023 was the year of AI avatars 2024 was the year of AI photos 2025 was the year of AI videos And I think it's becoming clear now that 2026 will be the year of AI world models Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt In turn these 2d images can then be generated by AI too So soon you can generate fully explorable virtual 3d worlds based on your own imagination Next will be figuring out how to make those worlds interactive This is World Labs (unaffiliated, but I like it) As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now) Very exciting time again!
0:18

2023 was the year of AI avatars 2024 was the year of AI photos 2025 was the year of AI videos And I think it's becoming clear now that 2026 will be the year of AI world models Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt In turn these 2d images can then be generated by AI too So soon you can generate fully explorable virtual 3d worlds based on your own imagination Next will be figuring out how to make those worlds interactive This is World Labs (unaffiliated, but I like it) As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now) Very exciting time again!

@levelsio

585,091 次观看 • 1 年前

I am blown away 🤯. Check this out! CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models TL;DR: "To enable broader exploration of dynamic scenes, our model can generate new video clips of the same scene based on previously generated content and user-provided camera trajectories. This approach maintains dynamic capabilities, accurate camera control, and scene consistency throughout the extended exploration." "Our model enables precise camera control across diverse scenarios while preserving dynamic scene elements, e.g." "Our method can generate videos with strong 3D consistency, which enables high-quality 3D reconstruction using the camera-controlled videos." Contributions: 1) A systematic data curation pipeline for constructing a dynamic video dataset with camera trajectory annotations; 2) A lightweight camera control injection module and corresponding training strategy that preserves dynamic video generation capabilities while adding camera control effect; 3) A clip-wise autoregressive generation recipe that enables extended range exploration of generated scenes.
0:10

I am blown away 🤯. Check this out! CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models TL;DR: "To enable broader exploration of dynamic scenes, our model can generate new video clips of the same scene based on previously generated content and user-provided camera trajectories. This approach maintains dynamic capabilities, accurate camera control, and scene consistency throughout the extended exploration." "Our model enables precise camera control across diverse scenarios while preserving dynamic scene elements, e.g." "Our method can generate videos with strong 3D consistency, which enables high-quality 3D reconstruction using the camera-controlled videos." Contributions: 1) A systematic data curation pipeline for constructing a dynamic video dataset with camera trajectory annotations; 2) A lightweight camera control injection module and corresponding training strategy that preserves dynamic video generation capabilities while adding camera control effect; 3) A clip-wise autoregressive generation recipe that enables extended range exploration of generated scenes.

MrNeRF

12,633 次观看 • 1 年前

🚨 Wait… I think I just discovered something HUGE about AI-generated 3D models. I found Hyper3D’s new Agentic Mode that can BUILD, EDIT & ANIMATE 3D models!! And there’s one thing that really surprised me. Unlike regular 3D generation, Agentic Mode can automatically filter and organize more informative input. You can give it different views, individual parts, or even a single reference image of separate components… And it can figure out how they fit together and generate a complete 3D model — with surprisingly accurate structure and details. That’s something I haven’t seen regular 3D generation handle this well. Check out this 3D windmill animation 👇 Hyper3D Agentic Mode lets you control 3D models with PARAMETERS !! Instead of rebuilding the sofa from scratch, you can change things like: → Parametric Control → Animation Pressets → Enhance Materials So you can generate the model once... and keep editing its geometry without starting from scratch
0:17

🚨 Wait… I think I just discovered something HUGE about AI-generated 3D models. I found Hyper3D’s new Agentic Mode that can BUILD, EDIT & ANIMATE 3D models!! And there’s one thing that really surprised me. Unlike regular 3D generation, Agentic Mode can automatically filter and organize more informative input. You can give it different views, individual parts, or even a single reference image of separate components… And it can figure out how they fit together and generate a complete 3D model — with surprisingly accurate structure and details. That’s something I haven’t seen regular 3D generation handle this well. Check out this 3D windmill animation 👇 Hyper3D Agentic Mode lets you control 3D models with PARAMETERS !! Instead of rebuilding the sofa from scratch, you can change things like: → Parametric Control → Animation Pressets → Enhance Materials So you can generate the model once... and keep editing its geometry without starting from scratch

SARAH

91,217 次观看 • 17 天前

As always everyone is blind staring at the progress of LLMs for coding and chat But meanwhile the new SOTA video model Seedance 2.5 has been slowly rolling out and it's really quite exceptional It's made by ByteDance (TikTok) who of course have lots of training data With just a few reference pics, it can get quite close to how you look IRL and you can do quite professional video shots with just a prompt I'd say it's the first video model that's now at the level of image models with the level of character likeness, cracking that in image models also took about 3 years (2022-2025) Generating 15 seconds takes about 4 minutes I put it live now on Photo AI, you can use it under [ Make video ] from the sidebar with just a prompt and your model selected! So you don't need to take an AI photo first and then turn that into a video! Saves lots of time :D It's more expensive than but I kept the credits the same (30 for 1 video) It also works inside the new video editor and you can make changes in your video with [ Magic edit ] in both the main app and the video editor Also a message for my server guy Daniel Lockyer (it can do voice too and you can even submit a voice sample of yourself, but I didn't here)
0:15

As always everyone is blind staring at the progress of LLMs for coding and chat But meanwhile the new SOTA video model Seedance 2.5 has been slowly rolling out and it's really quite exceptional It's made by ByteDance (TikTok) who of course have lots of training data With just a few reference pics, it can get quite close to how you look IRL and you can do quite professional video shots with just a prompt I'd say it's the first video model that's now at the level of image models with the level of character likeness, cracking that in image models also took about 3 years (2022-2025) Generating 15 seconds takes about 4 minutes I put it live now on Photo AI, you can use it under [ Make video ] from the sidebar with just a prompt and your model selected! So you don't need to take an AI photo first and then turn that into a video! Saves lots of time :D It's more expensive than but I kept the credits the same (30 for 1 video) It also works inside the new video editor and you can make changes in your video with [ Magic edit ] in both the main app and the video editor Also a message for my server guy Daniel Lockyer (it can do voice too and you can even submit a voice sample of yourself, but I didn't here)

@levelsio

711,938 次观看 • 2 个月前

✨ Every time the video models get better, the try on model on Photo AI also becomes a lot more useful, as a large % of my customers now are e-commerce store And showing clothes in a video is nice for sales! With AI this means stores don't need to do expensive shoots flying a model and entire camera and light crew around the world They can just upload a few photos of their models, then upload the clothes, and describe the setting (like a beach in Thailand) and in less than 10 seconds it's generated, for a video in less than a minute! Below is the input: a dress laid flat, and output: a full video shoot
0:10

✨ Every time the video models get better, the try on model on Photo AI also becomes a lot more useful, as a large % of my customers now are e-commerce store And showing clothes in a video is nice for sales! With AI this means stores don't need to do expensive shoots flying a model and entire camera and light crew around the world They can just upload a few photos of their models, then upload the clothes, and describe the setting (like a beach in Thailand) and in less than 10 seconds it's generated, for a video in less than a minute! Below is the input: a dress laid flat, and output: a full video shoot

@levelsio

334,317 次观看 • 1 年前

is it legal? NVIDIA and Microsoft just open-sourced the pieces of a full 3D studio for Opus 5.5 15 github repos, sorted by what you want to make: GENERATE 3D ASSETS 01. TRELLIS.2 by Microsoft: -> one image in, a fully textured 3D asset out, about 3 seconds on an H100 02. Hunyuan3D-2.1 by Tencent: -> production-ready 3D assets with PBR textures 03. stable-fast-3d by Stability AI: -> one photo to a clean UV-unwrapped mesh, built for speed 04. meshy-mcp-server by Meshy: -> text or image to 3D, then remesh, retexture, rig and animate from your agent BUILD SCENES AND WORLDS 05. mcp-for-blender: -> prompt-driven modeling, scene building and edits in a live Blender 06. HY-World-2.0 by Tencent: -> text or a single image to a navigable 3D world 07. supersplat by PlayCanvas: -> inspect, edit, optimize and publish 3D Gaussian splats in the browser 08. kit-usd-agents by NVIDIA: -> edit Omniverse USD scenes in plain English, plus MCP servers for Kit and Isaac Sim MAKE A GAME 09. unity-mcp: -> run the Unity Editor in plain English: scenes, C# scripts, assets, tests, builds 10. godot-ai: -> 46 tools for a live Godot editor: scenes, scripts, signals, UI, particles 11. unreal-engine-mcp: -> drive a live Unreal Editor: actors, world building, Blueprints 3D ON THE WEB 12. editor-mcp-server by PlayCanvas: -> your agent builds PlayCanvas scenes and checks they actually run 13. three.js: -> the JavaScript 3D library itself, 115k stars on GitHub 14. react-three-fiber: -> build three.js scenes as reusable React components 15. threejs-skills: -> 10 three.js skills for Claude Code, from shaders to post-processing a full 3D pipeline, and every piece of it lives on github
0:20

is it legal? NVIDIA and Microsoft just open-sourced the pieces of a full 3D studio for Opus 5.5 15 github repos, sorted by what you want to make: GENERATE 3D ASSETS 01. TRELLIS.2 by Microsoft: -> one image in, a fully textured 3D asset out, about 3 seconds on an H100 02. Hunyuan3D-2.1 by Tencent: -> production-ready 3D assets with PBR textures 03. stable-fast-3d by Stability AI: -> one photo to a clean UV-unwrapped mesh, built for speed 04. meshy-mcp-server by Meshy: -> text or image to 3D, then remesh, retexture, rig and animate from your agent BUILD SCENES AND WORLDS 05. mcp-for-blender: -> prompt-driven modeling, scene building and edits in a live Blender 06. HY-World-2.0 by Tencent: -> text or a single image to a navigable 3D world 07. supersplat by PlayCanvas: -> inspect, edit, optimize and publish 3D Gaussian splats in the browser 08. kit-usd-agents by NVIDIA: -> edit Omniverse USD scenes in plain English, plus MCP servers for Kit and Isaac Sim MAKE A GAME 09. unity-mcp: -> run the Unity Editor in plain English: scenes, C# scripts, assets, tests, builds 10. godot-ai: -> 46 tools for a live Godot editor: scenes, scripts, signals, UI, particles 11. unreal-engine-mcp: -> drive a live Unreal Editor: actors, world building, Blueprints 3D ON THE WEB 12. editor-mcp-server by PlayCanvas: -> your agent builds PlayCanvas scenes and checks they actually run 13. three.js: -> the JavaScript 3D library itself, 115k stars on GitHub 14. react-three-fiber: -> build three.js scenes as reusable React components 15. threejs-skills: -> 10 three.js skills for Claude Code, from shaders to post-processing a full 3D pipeline, and every piece of it lives on github

Mnimiy

201,419 次观看 • 4 天前

introducing a new, very fun, LLM benchmark- the Game-of-Life Bench! the rules are simple: given an 8x8 grid following Conway's game of life rules, the goal is to create an initial pattern with at most 32 cells that can last the longest number of turns before dying/repeating. some results to highlight (with caveats detailed below): - gpt 5.1 lasts the longest with a 106 step run - claude models are really bad at this! they refuse to reason about this task and score < 25 points - deepseek r1 is the best open model with 102 steps. why? because i wanted to create a benchmark that has (i think) no practicality, but is still fun to look at, cheap, and still measures something interesting. i also am a big fan of the game of life. its absurdly simple rules leading to intractability is extremely cool to me. also, i saw a lot of work with LLMs trying to "predict" the next state in Conway's game of life, I think game-of-life bench is more fun because it's pretty open ended and only asks the LLM for the initial state. I also think this could be an RL env? but idk why you would ever train on this task haha i don't think this is a "serious" benchmark because it doesnt measure anything practical, but i still think it's a hard benchmark exactly because you can't predict what happens with your initial state many turns into the future; this is why i was initially expecting all LLMs to be bad at it, but turns out, some are clearly better than the others (the ordering may surprise you!) reminder: this is still a work-in-progress; (1) i am gpu-poor so could only do 10 runs for each model, even though total running cost is relatively low. maybe with some more credits i can run more seeds for each model. (2) i handpicked models which i think are at the frontier right now, plus some others that were on my mind. so, if you'd like to see a model on here, let me know. (3) i currently only do an 8x8 grid because i thought that by itself would be pretty hard for current LLMs, but of course we can increase grid sizes! (4) the coolest thing is, i dont think we can calculate the max possible number of states (yay undecidability!) you can go without repeating, so this is essentially a no-ceiling task, which is pretty cool! again, i did this mostly out of a desire to make LLMs do something fun. if this keeps me entertained for a few more days, i'd likely release a blog post on it. if it keeps me entertained for a week (and someone sponsors me), i'll put more work into it :P lastly, this is fully open sourced, so feel free to run this on your own!
0:19

introducing a new, very fun, LLM benchmark- the Game-of-Life Bench! the rules are simple: given an 8x8 grid following Conway's game of life rules, the goal is to create an initial pattern with at most 32 cells that can last the longest number of turns before dying/repeating. some results to highlight (with caveats detailed below): - gpt 5.1 lasts the longest with a 106 step run - claude models are really bad at this! they refuse to reason about this task and score < 25 points - deepseek r1 is the best open model with 102 steps. why? because i wanted to create a benchmark that has (i think) no practicality, but is still fun to look at, cheap, and still measures something interesting. i also am a big fan of the game of life. its absurdly simple rules leading to intractability is extremely cool to me. also, i saw a lot of work with LLMs trying to "predict" the next state in Conway's game of life, I think game-of-life bench is more fun because it's pretty open ended and only asks the LLM for the initial state. I also think this could be an RL env? but idk why you would ever train on this task haha i don't think this is a "serious" benchmark because it doesnt measure anything practical, but i still think it's a hard benchmark exactly because you can't predict what happens with your initial state many turns into the future; this is why i was initially expecting all LLMs to be bad at it, but turns out, some are clearly better than the others (the ordering may surprise you!) reminder: this is still a work-in-progress; (1) i am gpu-poor so could only do 10 runs for each model, even though total running cost is relatively low. maybe with some more credits i can run more seeds for each model. (2) i handpicked models which i think are at the frontier right now, plus some others that were on my mind. so, if you'd like to see a model on here, let me know. (3) i currently only do an 8x8 grid because i thought that by itself would be pretty hard for current LLMs, but of course we can increase grid sizes! (4) the coolest thing is, i dont think we can calculate the max possible number of states (yay undecidability!) you can go without repeating, so this is essentially a no-ceiling task, which is pretty cool! again, i did this mostly out of a desire to make LLMs do something fun. if this keeps me entertained for a few more days, i'd likely release a blog post on it. if it keeps me entertained for a week (and someone sponsors me), i'll put more work into it :P lastly, this is fully open sourced, so feel free to run this on your own!

Akshit

13,775 次观看 • 7 个月前

this is f*cking insane, Claude Code turned a technical drawing into a 3D model you can edit Dario Amodei (CEO of Anthropic) put 14 agents to work on a CAD application with 620,000 lines of code. the assignment was to make it build parts from drawings and check every dimension it could read drop in a bracket drawing. get a model with editable holes, bends and mounting points change the hole spacing from 40 mm to 55 mm and the part rebuilds around the new measurement a model that looks right can still be impossible to manufacture one drawing left the wall thickness unspecified. the system flagged the missing measurement instead of quietly inventing it 34 of 40 sample parts passed dimension and solid-geometry checks. six needed clarification before they could be accepted give Claude Code an open-source CAD repository and a fully dimensioned sample drawing, then ask: "Build a drawing-to-model workflow inside this application 1. Extract dimensions, units and geometric constraints from the drawing. Link each measurement to its location and flag anything missing or ambiguous 2. Use the application's existing modeling API to construct an editable feature tree. Keep dimensions as named parameters rather than baking them into a mesh 3. Have a separate agent compare the model against the drawing. Check dimensions, hole positions and whether the result is a valid solid 4. Build a view showing the drawing beside the model. Let me change a parameter, rebuild the part and export it with a verification report" start with a simple part whose dimensions you can check by hand keep unresolved measurements visible. passing these checks does not establish material strength or fitness for a real assembly watch the drawing become an editable model below
0:18

this is f*cking insane, Claude Code turned a technical drawing into a 3D model you can edit Dario Amodei (CEO of Anthropic) put 14 agents to work on a CAD application with 620,000 lines of code. the assignment was to make it build parts from drawings and check every dimension it could read drop in a bracket drawing. get a model with editable holes, bends and mounting points change the hole spacing from 40 mm to 55 mm and the part rebuilds around the new measurement a model that looks right can still be impossible to manufacture one drawing left the wall thickness unspecified. the system flagged the missing measurement instead of quietly inventing it 34 of 40 sample parts passed dimension and solid-geometry checks. six needed clarification before they could be accepted give Claude Code an open-source CAD repository and a fully dimensioned sample drawing, then ask: "Build a drawing-to-model workflow inside this application 1. Extract dimensions, units and geometric constraints from the drawing. Link each measurement to its location and flag anything missing or ambiguous 2. Use the application's existing modeling API to construct an editable feature tree. Keep dimensions as named parameters rather than baking them into a mesh 3. Have a separate agent compare the model against the drawing. Check dimensions, hole positions and whether the result is a valid solid 4. Build a view showing the drawing beside the model. Let me change a parameter, rebuild the part and export it with a verification report" start with a simple part whose dimensions you can check by hand keep unresolved measurements visible. passing these checks does not establish material strength or fitness for a real assembly watch the drawing become an editable model below

Mika

30,135 次观看 • 1 天前

" A mattress. Well Maybe for some individuals. " This is something based on a comic I made with Ai in the past. I had the comic animated with Atlabs AI The video pretty much says what everything is about. I honestly like silly comics like this. I really should make more and have them as videos as well. That's another things for a long list of things I need done... Also I plan on running more tests with Omniflash in the future especially when Seedance models may not do things a certain way or have things looking a certain way. Also if anybody is planning on using Atlabs for anything I plan on making a video next month on how I use certain video models and which I typically use. This is specifically on how I use certain models for certain things. Not MG. I plan on having it in a tutorial section. I have hopes this will provide people that use any video models with some needed help when choosing what they should get started with because a Sora video model is no longer an option, which was very integral involving how I would use video models in general. Anyway I have an atlabs link below. If you make an account or have one already I hope what I plan on making next month and showing you, helps a lot. This was made with AtlabsAi. This was all done with Ai. #furrycomedyvideo #furryvideo #aianimation #aifurry
0:10

" A mattress. Well Maybe for some individuals. " This is something based on a comic I made with Ai in the past. I had the comic animated with Atlabs AI The video pretty much says what everything is about. I honestly like silly comics like this. I really should make more and have them as videos as well. That's another things for a long list of things I need done... Also I plan on running more tests with Omniflash in the future especially when Seedance models may not do things a certain way or have things looking a certain way. Also if anybody is planning on using Atlabs for anything I plan on making a video next month on how I use certain video models and which I typically use. This is specifically on how I use certain models for certain things. Not MG. I plan on having it in a tutorial section. I have hopes this will provide people that use any video models with some needed help when choosing what they should get started with because a Sora video model is no longer an option, which was very integral involving how I would use video models in general. Anyway I have an atlabs link below. If you make an account or have one already I hope what I plan on making next month and showing you, helps a lot. This was made with AtlabsAi. This was all done with Ai. #furrycomedyvideo #furryvideo #aianimation #aifurry

CaleAi

11,715 次观看 • 2 个月前