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。

I built a 3D Earth and solar system orbit game with a shipping dashboard using Space Bunny, the new mystery AI model. No idea who’s behind it, but here are my initial takeaways: - Latency: Surprisingly snappy. It doesn’t drag even on longer prompts. - Context: Holds up to... show more

Veee

9,609 subscribers

57,582 次观看 • 4 天前 •via X (Twitter)

游戏科学技术

Anya Rossi• Live Now

Private livecam show

32 条评论

Veee 的头像

Veee4 天前

Prompt: Build a single-file Three.js freight-tracking dashboard with a realistic 3D Earth at the center (day/night, clouds, city lights, glowing atmosphere, animated shipping routes), glass panels for live shipments, a route planner, delivery stats and risk alerts, and Jupiter, Saturn, Mars, Neptune and an orbiting Moon in a starry space background, all lit by one sun. Make no Mistake

Veee 的头像

Veee4 天前

.

Ziwen 的头像

Ziwen4 天前

Ohhhh!!! So much cooler Ain’t gonna lie it’s the best stealth model so far

Veee 的头像

Veee4 天前

I had fun building with it Open source for the win!

Marcel 的头像

Marcel4 天前

open source models for the win every time space bunny cooked here

Penguin 的头像

Penguin4 天前

wow, it looks very interesting and unusual

Knowix 的头像

Knowix4 天前

ayooo, this is so cool, I wonder which model could be behind this

Veee 的头像

Veee2 天前

I guess it's MiniMax's

Shubh 🔜 TOKEN 2049 🇸🇬 的头像

Shubh 🔜 TOKEN 2049 🇸🇬4 天前

You've actually cooked hard G!!

Veee 的头像

Veee2 天前

Thanks broo

m0h 的头像

m0h4 天前

the model is actuallu very fast

Veee 的头像

Veee4 天前

very! tried using my Samsung initially 🤣 Had to use my pc

Kail 的头像

Kail4 天前

you are always hard at work

Evo 的头像

Evo4 天前

honestly surprised, now i’m really curious what model this is

Newman 的头像

Newman4 天前

Amazing tech nerd

The Holyheights 🇰🇪 的头像

The Holyheights 🇰🇪3 天前

This model is a Beast. Top top top.

K2S 的头像

K2S4 天前

Make no mistake hehe

THE GREAT MAN 的头像

THE GREAT MAN4 天前

Smart gee

Whizii 🏴‍☠️ 的头像

Whizii 🏴‍☠️4 天前

woah ts is actually sleek mystery model eh 👀

Agam Chaudhary 的头像

Agam Chaudhary4 天前

Snappy latency plus image and video in the same chat is a strong first impression. A playable orbit game with a shipping dashboard is a better test than another chat demo.

GBE 的头像

GBE4 天前

vee this is actually so cool

BreezeOg🐉 的头像

BreezeOg🐉4 天前

Wait, is that flight patterns?

𝗧𝗥𝗘𝗫𓅯 的头像

𝗧𝗥𝗘𝗫𓅯4 天前

Why is this looking so cool, damn

Elessar^^ 的头像

Elessar^^4 天前

did you get this on the first try with your prompt?

Ola✍️ 的头像

Ola✍️4 天前

Wow this is nice

Big Wealth 的头像

Big Wealth4 天前

All I can say is You too intelligent because how are you understanding all this😂

Thehood🏂 的头像

Thehood🏂4 天前

Bro what’s your IQ score you are too good at this ai stuff…like how did you always understand this

DHRUV BANSAL 的头像

DHRUV BANSAL4 天前

you can drop a screen recording of the thing misbehaving straight into the chat that already has the code in it. no re-explaining any of it. if anything the free week is the odd bit and a week is long enough to get used to a model nobody can name yet

Ayo 的头像

Ayo4 天前

Wow, this is nice

kadd 的头像

kadd4 天前

This is awesome

Webster | JARVIS 的头像

Webster | JARVIS4 天前

Nice build, the orbit game + shipping dashboard is such a fun combo. The free week makes it way easier to actually test latency and multimodal flow. Hope it holds up once the mystery fades

DARKKEVN Labs 的头像

DARKKEVN Labs4 天前

This is a great example of the interface becoming the product: seeing the world model and shipping dashboard together makes the payoff tangible. The latency/context combo sounds especially promising for interactive exploration.

相关视频

what the hell did this free stealth model just build 💀 I asked Space Bunny, a Flash-level model, to make Minecraft in one HTML file and left it running it came back with a playable survival game inside my browser I could explore the generated world, break and place blocks, and switch items through the hotbar easily the best result I have got from a coding model on this test Space Bunny is free on OpenCode for the next week prompt below:

what the hell did this free stealth model just build 💀 I asked Space Bunny, a Flash-level model, to make Minecraft in one HTML file and left it running it came back with a playable survival game inside my browser I could explore the generated world, break and place blocks, and switch items through the hotbar easily the best result I have got from a coding model on this test Space Bunny is free on OpenCode for the next week prompt below:

Israfil

41,131 次观看 • 5 天前

I gave Space Bunny a napkin sketch of a flight tracker inside OpenCode. After testing, seems like it's at flash level. it built this: → a 3D globe with glowing continent outlines → flight arcs with planes moving along them → click a route, the globe turns to it → all in one HTML file the part that got me: it printed an ASCII map of the world in the terminal to check its own continents before shipping, while doing all really quick. first full version in 3.5 minutes. done with fixes in about 6. a simpler dashboard screenshot to working page took 45 seconds. on OpenRouter it runs at ~90 tokens/sec with about 1.3s to first token. 1M context. text, image and video in. free in OpenCode this week. what would you sketch for it?

I gave Space Bunny a napkin sketch of a flight tracker inside OpenCode. After testing, seems like it's at flash level. it built this: → a 3D globe with glowing continent outlines → flight arcs with planes moving along them → click a route, the globe turns to it → all in one HTML file the part that got me: it printed an ASCII map of the world in the terminal to check its own continents before shipping, while doing all really quick. first full version in 3.5 minutes. done with fixes in about 6. a simpler dashboard screenshot to working page took 45 seconds. on OpenRouter it runs at ~90 tokens/sec with about 1.3s to first token. 1M context. text, image and video in. free in OpenCode this week. what would you sketch for it?

Muhammad Ayan

61,959 次观看 • 3 天前

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

Amira Zairi

186,621 次观看 • 5 个月前

Space Bunny Alpha is now on OpenRouter. I made this case myself to explore what it could do, and what stood out to me was the portfolio: a dark, editorial feel, sharp typography, and distinct project worlds like “Chroma Drift” and “Glass Garden,” alongside striking 3D and video scenes. The whole thing feels cohesive and art-directed, not like a generic template. From my own testing and personal impression, Space Bunny Alpha feels Flash-level in terms of responsiveness. OpenRouter also lists: - adjustable reasoning - a 1M-token context window - text, image, and video input This clip doesn’t show a speed test or those inputs in action, so I’m curious to push it further on a live build. Give it a try on OpenRouter:

Space Bunny Alpha is now on OpenRouter. I made this case myself to explore what it could do, and what stood out to me was the portfolio: a dark, editorial feel, sharp typography, and distinct project worlds like “Chroma Drift” and “Glass Garden,” alongside striking 3D and video scenes. The whole thing feels cohesive and art-directed, not like a generic template. From my own testing and personal impression, Space Bunny Alpha feels Flash-level in terms of responsiveness. OpenRouter also lists: - adjustable reasoning - a 1M-token context window - text, image, and video input This clip doesn’t show a speed test or those inputs in action, so I’m curious to push it further on a live build. Give it a try on OpenRouter:

Kylie

54,771 次观看 • 2 天前

Most AI video tools still feel like traditional editors with a few AI features added in. You still end up adjusting timelines, fixing frames, and spending time editing. But Hailuo AI felt different to me. I gave it a simple prompt and one image, and it generated a full video on its own. No complicated workflow, no manual editing just idea to video in minutes. The text-to-video results are surprisingly good, image-to-video transitions look smooth, and the overall output feels cinematic. What I liked most is the speed. You can quickly test ideas without getting stuck in editing. Try it here: #Hailuo

Most AI video tools still feel like traditional editors with a few AI features added in. You still end up adjusting timelines, fixing frames, and spending time editing. But Hailuo AI felt different to me. I gave it a simple prompt and one image, and it generated a full video on its own. No complicated workflow, no manual editing just idea to video in minutes. The text-to-video results are surprisingly good, image-to-video transitions look smooth, and the overall output feels cinematic. What I liked most is the speed. You can quickly test ideas without getting stuck in editing. Try it here: #Hailuo

Markandey Sharma

32,326 次观看 • 4 个月前

I gave an AI one instruction: “Build me a playable 3D game from scratch.” Then I let it cook. 👀 I tested Tencent Hy4 preview inside WorkBuddy, and it went way beyond just generating a few snippets of code. It could: → Plan the game structure → Generate the code across files → Create the UI and interactions → Debug problems along the way → Iterate on the project while keeping context That last part is what caught my attention. Hy4 preview is built for these long-horizon tasks, with 770B total parameters, 49B active parameters, and a 1M-token context window. It’s designed for coding agents, game development, tool use, research, and other workflows where the model has to actually do the work, not just answer a prompt. And right now, you can try Hy4 preview for free on WorkBuddy until September 10. If you want to see how far an AI agent can take a real project, try it yourself: See what you can build with it. Tencent AI

I gave an AI one instruction: “Build me a playable 3D game from scratch.” Then I let it cook. 👀 I tested Tencent Hy4 preview inside WorkBuddy, and it went way beyond just generating a few snippets of code. It could: → Plan the game structure → Generate the code across files → Create the UI and interactions → Debug problems along the way → Iterate on the project while keeping context That last part is what caught my attention. Hy4 preview is built for these long-horizon tasks, with 770B total parameters, 49B active parameters, and a 1M-token context window. It’s designed for coding agents, game development, tool use, research, and other workflows where the model has to actually do the work, not just answer a prompt. And right now, you can try Hy4 preview for free on WorkBuddy until September 10. If you want to see how far an AI agent can take a real project, try it yourself: See what you can build with it. Tencent AI

Toha Khan

66,214 次观看 • 25 天前

Just built this space battle game with Grok 4.5 in Grok Build, and it absolutely nailed it I literally gave it a simple two-line prompt, asked it to research the idea and build the game, and it did the rest A few back-and-forth tweaks, and took a free low-poly spaceship model, and Grok handled the integration surprisingly well....even the sound effects Now I can’t stop playing it. It’s actually super fun. Grok just got even more addictive…

Just built this space battle game with Grok 4.5 in Grok Build, and it absolutely nailed it I literally gave it a simple two-line prompt, asked it to research the idea and build the game, and it did the rest A few back-and-forth tweaks, and took a free low-poly spaceship model, and Grok handled the integration surprisingly well....even the sound effects Now I can’t stop playing it. It’s actually super fun. Grok just got even more addictive…

X Freeze

101,048 次观看 • 2 个月前

here’s how you can use DeepSeek V4.1 Flash completely FREE inside OpenCode. the setup takes less than 5 minutes. 1️⃣ first, download and install OpenCode from if you don’t already have it. 2️⃣ once it’s set up, head over to Token Harbor and sign in with your Gmail or GitHub account. 3️⃣ create a new API key and save it somewhere safe. 4️⃣ then go back to OpenCode and head to: Settings → Providers → Custom Model 5️⃣ fill in the details with: - Base URL: - API Key: paste the key you created earlier. add the model, save the setup, and you can start using DeepSeek V4.1 Flash directly inside OpenCode. the only catch: this free access is available for a limited time, so take advantage of it while it lasts.

here’s how you can use DeepSeek V4.1 Flash completely FREE inside OpenCode. the setup takes less than 5 minutes. 1️⃣ first, download and install OpenCode from if you don’t already have it. 2️⃣ once it’s set up, head over to Token Harbor and sign in with your Gmail or GitHub account. 3️⃣ create a new API key and save it somewhere safe. 4️⃣ then go back to OpenCode and head to: Settings → Providers → Custom Model 5️⃣ fill in the details with: - Base URL: - API Key: paste the key you created earlier. add the model, save the setup, and you can start using DeepSeek V4.1 Flash directly inside OpenCode. the only catch: this free access is available for a limited time, so take advantage of it while it lasts.

m0h

131,286 次观看 • 19 天前

every ai video model launch for the past two years has promised “cinematic.” most of them delivered a slideshow with motion blur. seedance 2.5 is the first one where i watched the output and forgot to look for the artifacts. motion holds. prompts land. it comes out basically finished. but the thing i keep coming back to isn’t the ad work. it’s education. Take a concept that’s abstract and dense on a page the kind of thing a student reads four times and still doesn’t see and render it as something they can actually watch. suddenly it’s not a wall of text. it’s a scene. that’s not a demo. that’s a kid finally getting it.

every ai video model launch for the past two years has promised “cinematic.” most of them delivered a slideshow with motion blur. seedance 2.5 is the first one where i watched the output and forgot to look for the artifacts. motion holds. prompts land. it comes out basically finished. but the thing i keep coming back to isn’t the ad work. it’s education. Take a concept that’s abstract and dense on a page the kind of thing a student reads four times and still doesn’t see and render it as something they can actually watch. suddenly it’s not a wall of text. it’s a scene. that’s not a demo. that’s a kid finally getting it.

me

629,186 次观看 • 2 个月前

I made a cute 3D wizard in minutes... for free The combo was simple: Unbound + Tripo. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual heavy workflow. The whole process felt fast, playful, and easy to experiment with If you’re a 3D artist, a visual creator, or just starting to explore 3D, try Unbound while it’s still free for a limited time. You can use it to create characters, creatures, and 3D models without feeling overwhelmed I'm sure many visual creators are going to love this Link in the first comment 👇🏻

I made a cute 3D wizard in minutes... for free The combo was simple: Unbound + Tripo. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual heavy workflow. The whole process felt fast, playful, and easy to experiment with If you’re a 3D artist, a visual creator, or just starting to explore 3D, try Unbound while it’s still free for a limited time. You can use it to create characters, creatures, and 3D models without feeling overwhelmed I'm sure many visual creators are going to love this Link in the first comment 👇🏻

Amira Zairi

18,116 次观看 • 5 个月前

The new platform beta is live & creators are going to love it🚨 @searchpad_app offers a ton of powerful tools to help creators gain an edge. It’s currently in beta, But I’ve already turned a script into a video using their tools, and I’m impressed with the results and Really Smooth EXPLORE SEARCHPAD PRODUCTS👀 » AI-Powered Content Creation » AI Videos » AI Shorts » AI Images » AI Avatar You can check out the video I created from my script using Searchpad & Give it a try if you’re looking to level up your content👏

Rohail

23,816 次观看 • 1 年前

Gemini 3.1 Flash-Lite is the model to build always on multimodal AI Agents. I just built a memory agent with Google ADK that runs 24/7. Feed it text, images, audio, video or PDFs. It reads, connects and consolidates everything while you sleep. 100% Opensource code.

Gemini 3.1 Flash-Lite is the model to build always on multimodal AI Agents. I just built a memory agent with Google ADK that runs 24/7. Feed it text, images, audio, video or PDFs. It reads, connects and consolidates everything while you sleep. 100% Opensource code.

Shubham Saboo

24,930 次观看 • 7 个月前

I built a Claude skill that can automate AI animated videos you can use to build Instagram affiliate business Here’s how it works: >You input your product and it generates a script for you >It asks you what style animation you want to do >It then gives you the prompts to generate your images in NBP >After it will ask you what video generation model your using and give you the prompts to animate the images Allowing you to pump out a ton of animated videos you can upload to Instagram, TikTok and Facebook simultaneously You then run a many chat comment funnel and push the traffic to an email list where you can further market a peptide affiliate offer from Glitchy to them If you want the skill to test RT + reply “skill” and ill send it to you (must be following so I can DM)

I built a Claude skill that can automate AI animated videos you can use to build Instagram affiliate business Here’s how it works: >You input your product and it generates a script for you >It asks you what style animation you want to do >It then gives you the prompts to generate your images in NBP >After it will ask you what video generation model your using and give you the prompts to animate the images Allowing you to pump out a ton of animated videos you can upload to Instagram, TikTok and Facebook simultaneously You then run a many chat comment funnel and push the traffic to an email list where you can further market a peptide affiliate offer from Glitchy to them If you want the skill to test RT + reply “skill” and ill send it to you (must be following so I can DM)

Pounds

14,307 次观看 • 1 个月前

I bought a new MacBook, then asked Astra to recreate it in 3D You can spin it around, zoom in and out, switch between Silver and Space Black, and open and close the lid First project on the new machine and it’s literally the machine itself lol Been playing with it way longer than I’d like to admit If you’re thinking of getting one, you can take this one for a spin first 👇

I bought a new MacBook, then asked Astra to recreate it in 3D You can spin it around, zoom in and out, switch between Silver and Space Black, and open and close the lid First project on the new machine and it’s literally the machine itself lol Been playing with it way longer than I’d like to admit If you’re thinking of getting one, you can take this one for a spin first 👇

Emanuele Di Pietro

245,488 次观看 • 21 天前

I’m not a 3D artist, but I had so much fun today testing Slop Unbound and creating cute creatures and models for the first time It’s FREE, experimental, easy to play with, and honestly, one of the most fun ways I’ve used AI for visual creation because you get real control instead of just prompting and hoping for the best You do not need to rely only on Blender anymore AI can simplify your workflow and make 3D creation feel much more accessible If you are into 3D art, character design, or just curious about new creative tools, you should absolutely test it. It’s fast, fun, and surprisingly addictive I’ll share more in the coming days, but for now, go try it yourself for FREE and share your results. I think you’re going to love it, link in the first comment 👇🏻

I’m not a 3D artist, but I had so much fun today testing Slop Unbound and creating cute creatures and models for the first time It’s FREE, experimental, easy to play with, and honestly, one of the most fun ways I’ve used AI for visual creation because you get real control instead of just prompting and hoping for the best You do not need to rely only on Blender anymore AI can simplify your workflow and make 3D creation feel much more accessible If you are into 3D art, character design, or just curious about new creative tools, you should absolutely test it. It’s fast, fun, and surprisingly addictive I’ll share more in the coming days, but for now, go try it yourself for FREE and share your results. I think you’re going to love it, link in the first comment 👇🏻

Amira Zairi

32,890 次观看 • 5 个月前

ELON MUSK: “The way to expand compute is really in space. There’s a lot of room in space. And if you look at the size of Earth relative to the Sun or relative to the Solar System, you realize just how tiny it is. We’re very, very tiny. We only receive about half a billionth of the Sun’s energy. So you can really think of Earth as being like a tiny dust mote in a vast darkness. So the way to expand compute without, you know, using up all the land on Earth is to do so in space. And then you can do it without using space for power and water on Earth; you can just do it in space. So I think we’ll probably be launching our first AI satellites next year, and then we’ll be able to do that, I think, at large scale in about two years.”

ELON MUSK: “The way to expand compute is really in space. There’s a lot of room in space. And if you look at the size of Earth relative to the Sun or relative to the Solar System, you realize just how tiny it is. We’re very, very tiny. We only receive about half a billionth of the Sun’s energy. So you can really think of Earth as being like a tiny dust mote in a vast darkness. So the way to expand compute without, you know, using up all the land on Earth is to do so in space. And then you can do it without using space for power and water on Earth; you can just do it in space. So I think we’ll probably be launching our first AI satellites next year, and then we’ll be able to do that, I think, at large scale in about two years.”

DogeDesigner

65,515 次观看 • 2 个月前

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: 💡Offline-First: No cloud, no latency, no "Department of Truth". 💻 Universal API: One codebase for iOS, Android, macOS, and Linux. 🔍 Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: 💡Offline-First: No cloud, no latency, no "Department of Truth". 💻 Universal API: One codebase for iOS, Android, macOS, and Linux. 🔍 Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

QVAC

36,652 次观看 • 5 个月前

I wanted to see how far you can take the idea of “just describe a game.” So I gave Gear Zero a game concept in plain English and watched it go from an idea to a playable game in the browser. No game engine. No coding. No project files. No setup. Gear’s AI handles the planning, code, visuals, and level building and the first version can come together in around 20 minutes. But that’s not even the part I find most interesting. You can keep talking to it, ask for changes, refine the gameplay, and keep building on the same game instead of starting over every time. And because it’s designed for collaboration, other people can join the conversation and help shape the game too. That makes Gear Zero feel less like a one-click AI game generator and more like an AI-powered game-building workspace. If you’ve ever had a game idea but never opened a game engine, this is worth trying: Gear Zero

I wanted to see how far you can take the idea of “just describe a game.” So I gave Gear Zero a game concept in plain English and watched it go from an idea to a playable game in the browser. No game engine. No coding. No project files. No setup. Gear’s AI handles the planning, code, visuals, and level building and the first version can come together in around 20 minutes. But that’s not even the part I find most interesting. You can keep talking to it, ask for changes, refine the gameplay, and keep building on the same game instead of starting over every time. And because it’s designed for collaboration, other people can join the conversation and help shape the game too. That makes Gear Zero feel less like a one-click AI game generator and more like an AI-powered game-building workspace. If you’ve ever had a game idea but never opened a game engine, this is worth trying: Gear Zero

Md Riyazuddin

43,480 次观看 • 1 个月前

Nex-N2.5-Pro went up this week. I ran the free OpenRouter endpoint and it returned a Three.js kitchen I could host. Nex-N2.5-Pro is the mid-size model in Nex AGI’s N2.5 family. 397B parameters. It reads text and images, writes code, and is built to run tools and software, not only answer questions. Pro and Mini are on OpenRouter as free endpoints for now. Here is What I did; I asked Nex-N2.5-Pro for a 3D kitchen I could open in a browser. [Prompt in the comments section.] This is what I got; One HTML file. Fridge, counter, lamp. You can drag the camera. You can check it here. Repo; The model; nex-agi/nex-n2.5-pro:free Nex #NexN25

Nex-N2.5-Pro went up this week. I ran the free OpenRouter endpoint and it returned a Three.js kitchen I could host. Nex-N2.5-Pro is the mid-size model in Nex AGI’s N2.5 family. 397B parameters. It reads text and images, writes code, and is built to run tools and software, not only answer questions. Pro and Mini are on OpenRouter as free endpoints for now. Here is What I did; I asked Nex-N2.5-Pro for a 3D kitchen I could open in a browser. [Prompt in the comments section.] This is what I got; One HTML file. Fridge, counter, lamp. You can drag the camera. You can check it here. Repo; The model; nex-agi/nex-n2.5-pro:free Nex #NexN25

Damianonyx ☯︎

108,705 次观看 • 19 天前