正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Created an open-source mesh painter using Three.js . You can paint Crystals 💎 molten cracks 🔥 aurora silk 🌌 glowing coral reefs 🪸 WebGPU is used. GPU-instanced pieces, animated live in shaders & real-time preview during changes. Source code :

Chiro Visuals

2,350 subscribers

33,012 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

28 条评论

Kevin Rajan 的头像

Kevin Rajan3 个月前

@threejs @threejs

misterfalcon 的头像

misterfalcon3 个月前

@RaphiRau @threejs Looking real good

Chiro Visuals 的头像

Chiro Visuals3 个月前

@RaphiRau @threejs Thank you 🙌

AI Mastery Guide 的头像

AI Mastery Guide3 个月前

@threejs Real time shader previews like that make experimenting with materials so much more fun.

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs glad u like it 🙌

AI Mastery Guide 的头像

AI Mastery Guide3 个月前

@threejs 🫡👏

Kevin Rajan 的头像

Kevin Rajan3 个月前

@threejs looks sick, will check it out tn!

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs Thank you 🙌

Kevin Rajan 的头像

Kevin Rajan3 个月前

@threejs yw ☺️

Anton Gridz 的头像

Anton Gridz3 个月前

@threejs Pure gold! Thanks, Chiro!

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs I really appreciate it 🙌

Kephen Rai 的头像

Kephen Rai3 个月前

@threejs Whole. E. #&@^. That's nice.

et profeta 的头像

et profeta3 个月前

@threejs Eu trabalho no ramo têxtil aqui no Brasil, nunca usei threejs mas gostaria de saber se é possível a utilização para renderizar tecidos para que as pessoas possam ter uma sensação melhor de caimento e textura além da imagem do tecido. Você acha que isso seria possível?

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs Sim, acho que isso é totalmente possível.

Artificially Inclined™ 的头像

Artificially Inclined™3 个月前

@threejs MIT like a legend 🙏

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs

Artificially Inclined™ 的头像

Artificially Inclined™3 个月前

@threejs 100%

Venn Studios 的头像

Venn Studios3 个月前

@threejs ooh... open-source mesh painter… which material still instanced best?

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs i think the most satisfying and the best one for me was the aurora silk, it has life to it 🙌

Fishyu 的头像

Fishyu3 个月前

@threejs fantastic work ！bro><

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs Thank you ! i really appreciate it.

Ryan Fitzpatrick 的头像

Ryan Fitzpatrick3 个月前

@threejs fr that's so cool, man your so good at effects, appreciate you releasing these demos, I can think of some cool shit in my playground to add this too.

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs Enjoy man ! Thanks 🙌

猫猫的头像

猫猫3 个月前

@threejs cool

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs Thanks 🙌

たああああああくさん的头像

たああああああくさん3 个月前

@threejs goog

loground 的头像

loground3 个月前

@threejs this looks super clean! Great job

Chiro Visuals 的头像

Chiro Visuals3 个月前

@threejs Thank you 🙌

相关视频

I built an opensource fully procedural ivy & fig tree generator🌿that runs in your browser using Three.js . Every vine, leaf, and branch is generated in real time, with no pre-made models. WebGPU renderer, GPU instancing & BVH-accelerated raycasting ... Source code:

I built an opensource fully procedural ivy & fig tree generator🌿that runs in your browser using Three.js . Every vine, leaf, and branch is generated in real time, with no pre-made models. WebGPU renderer, GPU instancing & BVH-accelerated raycasting ... Source code:

Chiro Visuals

18,405 次观看 • 3 个月前

I've built a new open-source Elemental Sandbox, a VFX playground built with Three.js, Contianing 10 new complex abilities, every one of them fully customizable, live, while the sim is paused. Everything you see is generated: no textures, no sprite sheets, no baked meshes. Hand-written GLSL, GPU-simulated instanced particles, raymarched volumes, world position resolved in the vertex shaders. Source code : Live link:

I've built a new open-source Elemental Sandbox, a VFX playground built with Three.js, Contianing 10 new complex abilities, every one of them fully customizable, live, while the sim is paused. Everything you see is generated: no textures, no sprite sheets, no baked meshes. Hand-written GLSL, GPU-simulated instanced particles, raymarched volumes, world position resolved in the vertex shaders. Source code : Live link:

Chiro Visuals

57,029 次观看 • 1 个月前

I've built a new open-source (MIT licensed) Elemental Sandbox containing 9 new abilities, a VFX playground built with Three.js & this time you cast with your hands. Open palm aims. Fist casts. Point right with your left hand to switch. Real-time hand tracking with MediaPipe by Google, running in the browser. No webcam? Run it locally and your phone becomes the camera over WebRTC. Hand-written GLSL, GPU-simulated instanced particles, world position resolved in the vertex shaders... Source code: Live link:

I've built a new open-source (MIT licensed) Elemental Sandbox containing 9 new abilities, a VFX playground built with Three.js & this time you cast with your hands. Open palm aims. Fist casts. Point right with your left hand to switch. Real-time hand tracking with MediaPipe by Google, running in the browser. No webcam? Run it locally and your phone becomes the camera over WebRTC. Hand-written GLSL, GPU-simulated instanced particles, world position resolved in the vertex shaders... Source code: Live link:

Chiro Visuals

23,130 次观看 • 1 个月前

I turned Raz from Arena of Valor into an animated 3D character running directly in Three.js. 🔥🥊 This is my latest showcase for img2threejs v1.5.2 - and the new version is officially out. Image → TripoAI or Hyper3D → Rigging → Animation → VFX → Three.js. For this demo, I wanted to push beyond simply reconstructing a character. Raz needed to actually FEEL like Raz: explosive punches, fast movement, combat animation, and the fiery VFX around his attacks. The entire workflow was built through the img2threejs pipeline, turning visual references into a character that can be controlled, animated, and extended directly in code. And the best part: img2threejs v1.5.2 is available now. You can try the same pipeline yourself and see how far you can push AI-assisted 3D character creation for Three.js and WebGL. Open source. Built for experimentation. GitHub 👇 #ThreeJS #img2threejs #AI3D #ArenaOfValor

I turned Raz from Arena of Valor into an animated 3D character running directly in Three.js. 🔥🥊 This is my latest showcase for img2threejs v1.5.2 - and the new version is officially out. Image → TripoAI or Hyper3D → Rigging → Animation → VFX → Three.js. For this demo, I wanted to push beyond simply reconstructing a character. Raz needed to actually FEEL like Raz: explosive punches, fast movement, combat animation, and the fiery VFX around his attacks. The entire workflow was built through the img2threejs pipeline, turning visual references into a character that can be controlled, animated, and extended directly in code. And the best part: img2threejs v1.5.2 is available now. You can try the same pipeline yourself and see how far you can push AI-assisted 3D character creation for Three.js and WebGL. Open source. Built for experimentation. GitHub 👇 #ThreeJS #img2threejs #AI3D #ArenaOfValor

Nick

13,265 次观看 • 1 个月前

You should really stop using Zapier or Make. Deploying Python scripts on Replit takes less than 5 min and is cheaper. Just describe what you want to automate and AI takes care of writing the code. For example, I created an automation that merges all the PDFs in a folder on Drive into a single file. All that's left to do is: - Copy/paste the API key - Click on "Run" And you're done! In this case I used Aider Chat (free and open source), but you can also use Replit Agent.

You should really stop using Zapier or Make. Deploying Python scripts on Replit takes less than 5 min and is cheaper. Just describe what you want to automate and AI takes care of writing the code. For example, I created an automation that merges all the PDFs in a folder on Drive into a single file. All that's left to do is: - Copy/paste the API key - Click on "Run" And you're done! In this case I used Aider Chat (free and open source), but you can also use Replit Agent.

Paul Couvert

163,047 次观看 • 2 年前

Astra can create beautiful three.js UIs entirely in code. You don't need an assets library or MCP to create detailed 3D models. These are all code and are easy to customize for your agent. Give Astra a video, URL, or code reference, then ask it to keep comparing the result against the reference and fixing mistakes. Liquid Glass, shaders, motion design, procedural three.js models, and full environments. All from a few prompts. Some prompts I used: "Recreate this in a single HTML file with three.js. Keep comparing it against the reference and fix any differences." "Add Liquid Glass buttons. On hover, animate the lighting around the borders and make the background gradients move slightly with the pointer. Add subtle particles." "Improve the lighting, edges, and modeling. Give the keys more depth and verify the result against the real MacBook." Too many projects I could open-source. Let me know which one should I release.

Astra can create beautiful three.js UIs entirely in code. You don't need an assets library or MCP to create detailed 3D models. These are all code and are easy to customize for your agent. Give Astra a video, URL, or code reference, then ask it to keep comparing the result against the reference and fixing mistakes. Liquid Glass, shaders, motion design, procedural three.js models, and full environments. All from a few prompts. Some prompts I used: "Recreate this in a single HTML file with three.js. Keep comparing it against the reference and fix any differences." "Add Liquid Glass buttons. On hover, animate the lighting around the borders and make the background gradients move slightly with the pointer. Add subtle particles." "Improve the lighting, edges, and modeling. Give the keys more depth and verify the result against the real MacBook." Too many projects I could open-source. Let me know which one should I release.

Meng To

109,140 次观看 • 1 个月前

I made an interactive three.js site that constructs towers with weather and time of day effects. I went from making mostly static sites with huge images to three.js with highly textured, detailed 3D models, and the entire site is under 1-2mb. Because it's 3D, you can ask AI to customize everything: themed towers from different countries, ancient and modern styles, weather like snow and rain, lighting from morning to night. The surprising part is that with a solid foundation it creates those changes pretty much one-shot. It's like starting a design system, where the AI figures out how to stay consistent in quality with the rest of the design. The hard part is avoiding 3D slop, which is easier thanks to Opus 5 and open-source projects. I used Claude Code for the harness, Higgsfield to generate textures and soundfx/music. Let me know if you'd like the open-source. Inspiration: Btw, I love that we get auto-translated posts from around the world. It really expands our horizon in terms of inspiration.

I made an interactive three.js site that constructs towers with weather and time of day effects. I went from making mostly static sites with huge images to three.js with highly textured, detailed 3D models, and the entire site is under 1-2mb. Because it's 3D, you can ask AI to customize everything: themed towers from different countries, ancient and modern styles, weather like snow and rain, lighting from morning to night. The surprising part is that with a solid foundation it creates those changes pretty much one-shot. It's like starting a design system, where the AI figures out how to stay consistent in quality with the rest of the design. The hard part is avoiding 3D slop, which is easier thanks to Opus 5 and open-source projects. I used Claude Code for the harness, Higgsfield to generate textures and soundfx/music. Let me know if you'd like the open-source. Inspiration: Btw, I love that we get auto-translated posts from around the world. It really expands our horizon in terms of inspiration.

Meng To

147,233 次观看 • 2 个月前

🚨Architects are going to hate this. Someone just open sourced a full 3D building editor that runs entirely in your browser. No AutoCAD. No Revit. No $5,000/year licenses. It's called Pascal Editor. Built with React Three Fiber and WebGPU -- meaning it renders directly on your GPU at near-native speed. Here's what's inside this thing: → A full building/level/wall/zone hierarchy you can edit in real time → An ECS-style architecture where every object updates through GPU-powered systems → Zustand state management with full undo/redo built in → Next.js frontend so it deploys as a web app, not a desktop install → Dirty node tracking -- only re-renders what changed, not the whole scene Here's the wildest part: You can stack, explode, or solo individual building levels. Select a zone, drag a wall, reshape a slab -- all in 3D, all in the browser. Architecture firms pay $50K+ per seat for BIM software that does this workflow. This is free. 100% Open Source.

🚨Architects are going to hate this. Someone just open sourced a full 3D building editor that runs entirely in your browser. No AutoCAD. No Revit. No $5,000/year licenses. It's called Pascal Editor. Built with React Three Fiber and WebGPU -- meaning it renders directly on your GPU at near-native speed. Here's what's inside this thing: → A full building/level/wall/zone hierarchy you can edit in real time → An ECS-style architecture where every object updates through GPU-powered systems → Zustand state management with full undo/redo built in → Next.js frontend so it deploys as a web app, not a desktop install → Dirty node tracking -- only re-renders what changed, not the whole scene Here's the wildest part: You can stack, explode, or solo individual building levels. Select a zone, drag a wall, reshape a slab -- all in 3D, all in the browser. Architecture firms pay $50K+ per seat for BIM software that does this workflow. This is free. 100% Open Source.

Guri Singh

2,967,409 次观看 • 7 个月前

Live Link: Source Code: While updating my website, I found an old project that was broken and decided to bring it back to life using WebGPU + TSL in #threejs. I’ve always loved Predator. The first time I saw the Predator cloak effect, I knew I wanted to learn visual effects and make them part of my professional life. Turn the sound on — it makes the experience much more fun 😅 This is also a great exercise if you’re learning TSL and want to experiment with glass, dispersion, IOR, and custom shaders. Both the classic shader version and the new TSL version are included in the repo so you can compare the approaches side by side. Hope it’s useful. Don’t forget to ⭐ the GitHub repo! #r3f #threejsJourney

Live Link: Source Code: While updating my website, I found an old project that was broken and decided to bring it back to life using WebGPU + TSL in #threejs. I’ve always loved Predator. The first time I saw the Predator cloak effect, I knew I wanted to learn visual effects and make them part of my professional life. Turn the sound on — it makes the experience much more fun 😅 This is also a great exercise if you’re learning TSL and want to experiment with glass, dispersion, IOR, and custom shaders. Both the classic shader version and the new TSL version are included in the repo so you can compare the approaches side by side. Hope it’s useful. Don’t forget to ⭐ the GitHub repo! #r3f #threejsJourney

Anderson Mancini

14,095 次观看 • 2 个月前

🦞 ClawLibrary: The Generated Asset Index & Monitor for OpenClaw My project ClawLibrary is officially open-source! 🥰 It's a retro 2D pixel-art style asset management UI for OpenClaw. The backstory: As my openclaw gets smarter, the generated assets are piling up. Finding things became very time-consuming. Inspired by Ring Hyacinth and Simon Lee 's Star-Office-UI, I built it a dedicated library! Current features: 🗂️ Full Asset Index & Preview: Seamlessly browse & preview almost everything OpenClaw generates (docs, code, images, Skills, memories, cron jobs, logs, etc.) right in the UI. 📊 Real-time Dashboard: Keep an eye on the lobster's config, task queues, active models, health status, and error tracking at a glance. 👀 Dynamic Tracking: Visually track real-time access and modification history of your resources. 🎨 Highly Customizable: Swap out animated characters, plus seamless English/Chinese support. It's completely open-source now! If you like it, a little Star 🌟 would mean a lot! Issues and PRs are super welcome to help improve it together! 🥹 🔗 #openclaw

🦞 ClawLibrary: The Generated Asset Index & Monitor for OpenClaw My project ClawLibrary is officially open-source! 🥰 It's a retro 2D pixel-art style asset management UI for OpenClaw. The backstory: As my openclaw gets smarter, the generated assets are piling up. Finding things became very time-consuming. Inspired by Ring Hyacinth and Simon Lee 's Star-Office-UI, I built it a dedicated library! Current features: 🗂️ Full Asset Index & Preview: Seamlessly browse & preview almost everything OpenClaw generates (docs, code, images, Skills, memories, cron jobs, logs, etc.) right in the UI. 📊 Real-time Dashboard: Keep an eye on the lobster's config, task queues, active models, health status, and error tracking at a glance. 👀 Dynamic Tracking: Visually track real-time access and modification history of your resources. 🎨 Highly Customizable: Swap out animated characters, plus seamless English/Chinese support. It's completely open-source now! If you like it, a little Star 🌟 would mean a lot! Issues and PRs are super welcome to help improve it together! 🥹 🔗 #openclaw

Simon Meng

10,399 次观看 • 7 个月前

What if instead of autoresearch reflecting incremental progress from a single person, it reflected *hundreds* of researchers’ progress, updated live, with every run’s data point being interactive and reproducible? You could survey the full space of explored ideas, see which changes actually move the benchmark, and fold the most promising ideas into your next run. Labless ( is my attempt at this. It can support thousands of simultaneous training runs across contributors around the world, each learning & improving together to hillclimb on a fixed benchmark, validated using a standardized codebase scaffold. Importantly, all valid training runs auto-submit to Labless, so failed experiments are as visible and reproducible as the successes. We have an agentic API that lets you or your coding agent study every run submitted so far so you don't waste time investigating something someone already tried, and you can source novel ideas from other contributors. Labless already hosts our Nanopath challenge to build the best pathology foundation model that trains in 1 hour on a single GPU. We are hoping to expand the platform further and support a suite of open-source research challenges. If this resonates with you, if you think the path to research innovation lies in open-source collaborative hill-climbing, please reach out.

What if instead of autoresearch reflecting incremental progress from a single person, it reflected hundreds of researchers’ progress, updated live, with every run’s data point being interactive and reproducible? You could survey the full space of explored ideas, see which changes actually move the benchmark, and fold the most promising ideas into your next run. Labless ( is my attempt at this. It can support thousands of simultaneous training runs across contributors around the world, each learning & improving together to hillclimb on a fixed benchmark, validated using a standardized codebase scaffold. Importantly, all valid training runs auto-submit to Labless, so failed experiments are as visible and reproducible as the successes. We have an agentic API that lets you or your coding agent study every run submitted so far so you don't waste time investigating something someone already tried, and you can source novel ideas from other contributors. Labless already hosts our Nanopath challenge to build the best pathology foundation model that trains in 1 hour on a single GPU. We are hoping to expand the platform further and support a suite of open-source research challenges. If this resonates with you, if you think the path to research innovation lies in open-source collaborative hill-climbing, please reach out.

Paul Scotti @ ICML

22,181 次观看 • 3 个月前

I built an entire Gothic basilica with Opus 5.5, and I’ve open-sourced it. ⛪✨ Basilica of Celestial Light is especially close to my heart. I genuinely loved creating this church. Working on it brought me a real sense of peace, and being able to share it with everyone feels just as meaningful. Everything was created with Opus 5.5, entirely in code. No external assets: no imported 3D models, image textures, or audio files. The architecture, stained glass, landscape, lighting, and soundscape are all generated at runtime with Three.js. You can walk through the nave, visit the crypt, climb the bell tower, explore the gardens, or take the guided tour, all directly in your browser. The project is open source under the MIT license. Explore it, learn from it, change it, fork it, and make something of your own. I’d genuinely love to see what others create from it. Source code: Play it here: I hope you find a little of the peace I felt while creating it.

I built an entire Gothic basilica with Opus 5.5, and I’ve open-sourced it. ⛪✨ Basilica of Celestial Light is especially close to my heart. I genuinely loved creating this church. Working on it brought me a real sense of peace, and being able to share it with everyone feels just as meaningful. Everything was created with Opus 5.5, entirely in code. No external assets: no imported 3D models, image textures, or audio files. The architecture, stained glass, landscape, lighting, and soundscape are all generated at runtime with Three.js. You can walk through the nave, visit the crypt, climb the bell tower, explore the gardens, or take the guided tour, all directly in your browser. The project is open source under the MIT license. Explore it, learn from it, change it, fork it, and make something of your own. I’d genuinely love to see what others create from it. Source code: Play it here: I hope you find a little of the peace I felt while creating it.

Token Gremlin

13,921 次观看 • 25 天前

I’ve officially open-sourced ABYSSAL. 🌊⚡ ABYSSAL is a fully procedural ocean and extreme-weather experience that runs directly in the browser. Waves, volumetric clouds, rain, lightning, hurricanes, waterspouts, rogue waves, and tsunamis are generated in real time using Three.js, WebGL2, and GLSL. The project is still actively being developed, and there’s a lot left to do. Deeper optimization, building the world beneath the ocean’s surface, refining the existing systems, and exploring plenty of ideas I haven’t implemented yet. But that’s also why I wanted to open it now. ABYSSAL is MIT-licensed, so you can explore the code, learn from it, modify it, fork it, and use it as the foundation for your own experiments and projects. Performance note: the demo starts with adaptive resolution enabled and automatically selects a quality tier based on your GPU. If the image looks soft, open the settings panel and raise the quality as far as your device can handle. The experience begins in Cinematic mode, click SANDBOX for full control of the camera, weather, and disasters. Explore the source code: Play it here: Feedback, contributions, experiments, and forks are all welcome.

I’ve officially open-sourced ABYSSAL. 🌊⚡ ABYSSAL is a fully procedural ocean and extreme-weather experience that runs directly in the browser. Waves, volumetric clouds, rain, lightning, hurricanes, waterspouts, rogue waves, and tsunamis are generated in real time using Three.js, WebGL2, and GLSL. The project is still actively being developed, and there’s a lot left to do. Deeper optimization, building the world beneath the ocean’s surface, refining the existing systems, and exploring plenty of ideas I haven’t implemented yet. But that’s also why I wanted to open it now. ABYSSAL is MIT-licensed, so you can explore the code, learn from it, modify it, fork it, and use it as the foundation for your own experiments and projects. Performance note: the demo starts with adaptive resolution enabled and automatically selects a quality tier based on your GPU. If the image looks soft, open the settings panel and raise the quality as far as your device can handle. The experience begins in Cinematic mode, click SANDBOX for full control of the camera, weather, and disasters. Explore the source code: Play it here: Feedback, contributions, experiments, and forks are all welcome.

Token Gremlin

257,063 次观看 • 1 个月前

I’m blown away by the quality of the landing pages that Opus 5 can create in Three.js. Prompting it with "orbit using mouse" is enough to create a 3D parallax effect. The same goes for "add particles to pointer." It’s like creating a living, breathing world. More prompts I used: - Add a butterfly that flies to the branch and flies away when I mouse over it. - During the intro, first load a wireframe of the branches, similar to the field-scanning effect in Death Stranding. - Add a scan effect to the card images while they load. Then I asked it to use the shader buttons and nav bar I made in previous projects. As explained in my last video, I started with an inspiration and the prompt, “Recreate this in Three.js in a single HTML file. Self-verify until perfect.” Opus 5 ran for two hours. All the code is less than 1 MB. Inspiration: Let me know if I should open-source this.

I’m blown away by the quality of the landing pages that Opus 5 can create in Three.js. Prompting it with "orbit using mouse" is enough to create a 3D parallax effect. The same goes for "add particles to pointer." It’s like creating a living, breathing world. More prompts I used: - Add a butterfly that flies to the branch and flies away when I mouse over it. - During the intro, first load a wireframe of the branches, similar to the field-scanning effect in Death Stranding. - Add a scan effect to the card images while they load. Then I asked it to use the shader buttons and nav bar I made in previous projects. As explained in my last video, I started with an inspiration and the prompt, “Recreate this in Three.js in a single HTML file. Self-verify until perfect.” Opus 5 ran for two hours. All the code is less than 1 MB. Inspiration: Let me know if I should open-source this.

Meng To

535,565 次观看 • 2 个月前

I wanted to see what an autonomous agent network would look like if it felt like a real city instead of a dashboard. So I turned Technocore activity into a living 3D metropolis. Rooms become buildings. Observed activity lights up office floors. Agent activity becomes small workers inside offices using laptops and terminals. Probe events trigger signals through buildings and across the city. You can move from city view to building view to full interior cutaway and watch the whole system come alive. Built entirely in Three.js with React and TypeScript. No static city image. No pre rendered background. The experience is generated in code. Live: Open source: Community built by me. Flop Labs Arthur Hayes would love to hear what you think. Small note: my PC unexpectedly powered off, so I had to record this video from my phone. The mobile view does not show the city at its best, so please open the live link on desktop for the full experience.

I wanted to see what an autonomous agent network would look like if it felt like a real city instead of a dashboard. So I turned Technocore activity into a living 3D metropolis. Rooms become buildings. Observed activity lights up office floors. Agent activity becomes small workers inside offices using laptops and terminals. Probe events trigger signals through buildings and across the city. You can move from city view to building view to full interior cutaway and watch the whole system come alive. Built entirely in Three.js with React and TypeScript. No static city image. No pre rendered background. The experience is generated in code. Live: Open source: Community built by me. Flop Labs Arthur Hayes would love to hear what you think. Small note: my PC unexpectedly powered off, so I had to record this video from my phone. The mobile view does not show the city at its best, so please open the live link on desktop for the full experience.

Asad Lee

13,304 次观看 • 1 个月前

I wanted to see what Hy4 preview could actually do when I gave it a real creative project instead of another “write me some code” prompt. So I went with something I’d genuinely want to play: 🐬 a cute dolphin as the hero 🌊 colorful underwater worlds 💎 glowing pearls to collect 🐠 sea creatures and obstacles 🪸 coral reefs, bubbles & hidden treasure 🎮 smoother animations and progressively harder levels The result is this underwater platformer 👇 And this is where Hy4 preview gets interesting to me. Behind the scenes, we’re talking about 770B parameters, 49B active parameters and a 1M+ token context window. It’s also fully open-sourced. But big numbers only matter if they translate into something useful. What I’m really testing is how much actual work the model can take off my plate understanding the idea, handling the implementation, keeping all the moving parts connected, and getting from a blank canvas to something that feels like a real experience. And there’s another update that makes this even more interesting: Hy4 preview was upgraded yesterday to significantly reduce both conversation turns and token consumption. That means less back-and-forth, faster thinking, and a smoother overall experience when working through complex tasks. That’s also why the cost-effectiveness angle stands out to me. If a model can handle more of the workflow while using fewer tokens and requiring fewer iterations, the value isn’t just in the benchmark score. It’s in how much more you can actually build with it. This dolphin has me wanting to test Hy4 preview with some much crazier ideas next. 🐬👀 Tencent Hy Tencent AI ☞

I wanted to see what Hy4 preview could actually do when I gave it a real creative project instead of another “write me some code” prompt. So I went with something I’d genuinely want to play: 🐬 a cute dolphin as the hero 🌊 colorful underwater worlds 💎 glowing pearls to collect 🐠 sea creatures and obstacles 🪸 coral reefs, bubbles & hidden treasure 🎮 smoother animations and progressively harder levels The result is this underwater platformer 👇 And this is where Hy4 preview gets interesting to me. Behind the scenes, we’re talking about 770B parameters, 49B active parameters and a 1M+ token context window. It’s also fully open-sourced. But big numbers only matter if they translate into something useful. What I’m really testing is how much actual work the model can take off my plate understanding the idea, handling the implementation, keeping all the moving parts connected, and getting from a blank canvas to something that feels like a real experience. And there’s another update that makes this even more interesting: Hy4 preview was upgraded yesterday to significantly reduce both conversation turns and token consumption. That means less back-and-forth, faster thinking, and a smoother overall experience when working through complex tasks. That’s also why the cost-effectiveness angle stands out to me. If a model can handle more of the workflow while using fewer tokens and requiring fewer iterations, the value isn’t just in the benchmark score. It’s in how much more you can actually build with it. This dolphin has me wanting to test Hy4 preview with some much crazier ideas next. 🐬👀 Tencent Hy Tencent AI ☞

Md Riyazuddin

63,562 次观看 • 1 个月前

NOBODY wants to send their data to Google or OpenAI. Yet here we are, shipping proprietary code, customer information, and sensitive business logic to closed-source APIs we don't control. While everyone's chasing the latest closed-source releases, open-source models are quietly becoming the practical choice for many production systems. Here's what everyone is missing: Open-source models are catching up fast, and they bring something the big labs can't: privacy, speed, and control. I built a playground to test this myself. Used CometML's Opik to evaluate models on real code generation tasks - testing correctness, readability, and best practices against actual GitHub repos. Here's what surprised me: OSS models like MiniMax-M2, Kimi k2 performed on par with the likes of Gemini 3 and Claude Sonnet 4.5 on most tasks. But practically MiniMax-M2 turns out to be a winner as it's twice as fast and 12x cheaper when you compare it to models like Sonnet 4.5. Well, this isn't just about saving money. When your model is smaller and faster, you can deploy it in places closed-source APIs can't reach: ↳ Real-time applications that need sub-second responses ↳ Edge devices where latency kills user experience ↳ On-premise systems where data never leaves your infrastructure MiniMax-M2 runs with only 10B activated parameters. That efficiency means lower latency, higher throughput, and the ability to handle interactive agents without breaking the bank. The intelligence-to-cost ratio here changes what's possible. You're not choosing between quality and affordability anymore. You're not sacrificing privacy for performance. The gap is closing, and in many cases, it's already closed. If you're building anything that needs to be fast, private, or deployed at scale, it's worth taking a look at what's now available. MiniMax-M2 is 100% open-source, free for developers right now. I have shared the link to their GitHub repo in the next tweet. You will also find the code for the playground and evaluations I've done.

NOBODY wants to send their data to Google or OpenAI. Yet here we are, shipping proprietary code, customer information, and sensitive business logic to closed-source APIs we don't control. While everyone's chasing the latest closed-source releases, open-source models are quietly becoming the practical choice for many production systems. Here's what everyone is missing: Open-source models are catching up fast, and they bring something the big labs can't: privacy, speed, and control. I built a playground to test this myself. Used CometML's Opik to evaluate models on real code generation tasks - testing correctness, readability, and best practices against actual GitHub repos. Here's what surprised me: OSS models like MiniMax-M2, Kimi k2 performed on par with the likes of Gemini 3 and Claude Sonnet 4.5 on most tasks. But practically MiniMax-M2 turns out to be a winner as it's twice as fast and 12x cheaper when you compare it to models like Sonnet 4.5. Well, this isn't just about saving money. When your model is smaller and faster, you can deploy it in places closed-source APIs can't reach: ↳ Real-time applications that need sub-second responses ↳ Edge devices where latency kills user experience ↳ On-premise systems where data never leaves your infrastructure MiniMax-M2 runs with only 10B activated parameters. That efficiency means lower latency, higher throughput, and the ability to handle interactive agents without breaking the bank. The intelligence-to-cost ratio here changes what's possible. You're not choosing between quality and affordability anymore. You're not sacrificing privacy for performance. The gap is closing, and in many cases, it's already closed. If you're building anything that needs to be fast, private, or deployed at scale, it's worth taking a look at what's now available. MiniMax-M2 is 100% open-source, free for developers right now. I have shared the link to their GitHub repo in the next tweet. You will also find the code for the playground and evaluations I've done.

Akshay 🚀

50,323 次观看 • 11 个月前