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 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?show more

Muhammad Ayan

69,366 subscribers

61,959 次观看 • 3 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

20 条评论

Muhammad Ayan 的头像

Muhammad Ayan3 天前

Try Space Bunny now on:

Brjan | AI Builder 的头像

Brjan | AI Builder3 天前

building a feature like that sounds like it could really up engagement for users

Javeriya Ahsan 的头像

Javeriya Ahsan3 天前

Sub 2 second first token keeps the loop feeling live!!

Dhanian 🗯️ 的头像

Dhanian 🗯️3 天前

Helpful

Saman Ahmed 的头像

Saman Ahmed3 天前

okay Space Bunny is kinda cooking

Muhammad Ayan 的头像

Muhammad Ayan3 天前

full kitchen tbh 🔥

H A J R A 的头像

H A J R A3 天前

The ASCII self-check before shipping is honestly the coolest part

Muhammad Ayan 的头像

Muhammad Ayan3 天前

bestie, you always catch the nerdy detail :))

Parul Gautam 的头像

Parul Gautam3 天前

The self-checking ASCII map is wild. AI coding is moving fast.

Nelly; 的头像

Nelly;3 天前

OpenCode is becoming a serious playground for these model tests

Muhammad Ayan 的头像

Muhammad Ayan3 天前

free models plus a good harness, dangerous combo for my sleep schedule 😅

Mimu | AI Tools & News 的头像

Mimu | AI Tools & News3 天前

That self-checking ASCII map stuff is mind-blowing. AI coding is moving insanely fast right now

Neo Kim 的头像

Neo Kim3 天前

pretty cool....

auqib 的头像

auqib3 天前

That self checking workflow makes the speed even more impressive.

Charlie Hills 的头像

Charlie Hills3 天前

Free in OpenCode this week, so go stress test it!! P.S. My token bill thanks this bunny 🫠

Muhammad Ayan 的头像

Muhammad Ayan3 天前

both our token bills needed this, back to paid rates next week

TH33ORACL3 𝕏 的头像

TH33ORACL3 𝕏3 天前

ascii map self-check before shipping is the best part

Samuel Hu 的头像

Samuel Hu3 天前

the 3d globe demo is the fun part. i'd throw a dirty api response and a 30s tool timeout at it next. agents often look instant until one call hangs, then the whole ui stalls. did the build keep working after you edited the generated code?

Maryam Asim 的头像

Maryam Asim3 天前

Claude Code stays my daily driver, but for 5 minute prototypes this bunny is a fun second seat

Muhammad Ayan 的头像

Muhammad Ayan3 天前

Claude Code stays undefeated 🤩

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 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 1M input / 524k output. - Multimodal: Smoothly reads images and video directly in the middle of a chat without breaking flow. It’s fast, and can feel flash level. It’s sitting on OpenCode for free this week if you want to try it.

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 1M input / 524k output. - Multimodal: Smoothly reads images and video directly in the middle of a chat without breaking flow. It’s fast, and can feel flash level. It’s sitting on OpenCode for free this week if you want to try it.

Veee

57,582 次观看 • 4 天前

MINIMAX OPEN SOURCED A CODING AGENT THAT LIVES IN YOUR TERMINAL its called MiniMax Code CLI. i gave it one prompt, 19 minutes later i had a working interactive 3d globe. → 249 countries → 14 animated flight arcs across 16 hubs → click a country and the camera flies to it → fresnel atmosphere, bloom, the full pass it did it in 9 phases at about 96 tok/s, committing after every one. Mcode is MIT and it is not locked to MiniMax models, you can bring your own key and point it at claude, gpt, or a local model. setup in your terminal: 1.⁠ ⁠curl -fsSL | bash 2.⁠ ⁠cd into the project and run mcode 3.⁠ ⁠run mcode init . first, that is the step that writes the AGENTS.md the AGENTS.md is doing more work here than the model. build commands, what not to touch, and a rule that it verifies before it calls anything done i will drop the repo below

MINIMAX OPEN SOURCED A CODING AGENT THAT LIVES IN YOUR TERMINAL its called MiniMax Code CLI. i gave it one prompt, 19 minutes later i had a working interactive 3d globe. → 249 countries → 14 animated flight arcs across 16 hubs → click a country and the camera flies to it → fresnel atmosphere, bloom, the full pass it did it in 9 phases at about 96 tok/s, committing after every one. Mcode is MIT and it is not locked to MiniMax models, you can bring your own key and point it at claude, gpt, or a local model. setup in your terminal: 1.⁠ ⁠curl -fsSL | bash 2.⁠ ⁠cd into the project and run mcode 3.⁠ ⁠run mcode init . first, that is the step that writes the AGENTS.md the AGENTS.md is doing more work here than the model. build commands, what not to touch, and a rule that it verifies before it calls anything done i will drop the repo below

Israfil

25,153 次观看 • 7 天前

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

Tom Krcha

1,441,453 次观看 • 26 天前

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

I gave Space Bunny an ASCII wireframe and told it to compile it into a working dashboard. the ascii map was the entire spec. exact 250px sidebar, responsive grid, live charts on a 2-second mock telemetry loop. It reproduced the layout pixel-for-pixel and wired up all the state: sidebar nav, profile dropdown, table filters, just in first try. The part that got me: most models approximate layouts from descriptions. this one treated an ascii diagram like a blueprint. It also surprised me with the fast speed in responses and task handling. The provider is still anonymous, no lab has claimed it yet. free for 7 days only, go build something fun👀

Fakhr

51,702 次观看 • 3 天前

The Inception of Worthless Coin: At 3am in early July I was recording a video of me trading. Here's live footage of W popping up on my wallet tracker. I traded it, it died shortly after, and something spoke to me to start my first ever CTO. This is a small teaser. The full video is 90 minutes. Then I recorded updates every single day for a week to make a documentary with when it takes over the world. I knew what this was from the jump, and here's proof to back it.

The Inception of Worthless Coin: At 3am in early July I was recording a video of me trading. Here's live footage of W popping up on my wallet tracker. I traded it, it died shortly after, and something spoke to me to start my first ever CTO. This is a small teaser. The full video is 90 minutes. Then I recorded updates every single day for a week to make a documentary with when it takes over the world. I knew what this was from the jump, and here's proof to back it.

Nikolai

26,672 次观看 • 1 年前

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad

Om Patel

29,618 次观看 • 3 个月前

I plugged MiniMax (official) M3 into Claude Code in under 5 minutes and gave it a real task. most models need hand-holding every few steps. M3 ran 147 iterations on its own. what it actually did: → took a broken CUDA kernel → ran it for 24 hours, autonomously → pushed hardware efficiency from 7.6% to 71.3% → shipped a 9.4x speedup I didn't touch it once across that whole window. the rest of the spec sheet: → 1M token context window → native multimodal from day one → fully open weights pricing: → $20/month for 1.7B tokens → $50/month for 5.1B tokens → text, image, speech, and music all share one pool usually with this kind of capability the bill catches up fast. M3 keeps both lines low at the same time. that's the part that surprised me. and if this is what M3 does at launch, the full rollout is going to be one to watch. what would you build with 1M context? #MiniMax #MiniMaxM3 #ClaudeCode #LLM

I plugged MiniMax (official) M3 into Claude Code in under 5 minutes and gave it a real task. most models need hand-holding every few steps. M3 ran 147 iterations on its own. what it actually did: → took a broken CUDA kernel → ran it for 24 hours, autonomously → pushed hardware efficiency from 7.6% to 71.3% → shipped a 9.4x speedup I didn't touch it once across that whole window. the rest of the spec sheet: → 1M token context window → native multimodal from day one → fully open weights pricing: → $20/month for 1.7B tokens → $50/month for 5.1B tokens → text, image, speech, and music all share one pool usually with this kind of capability the bill catches up fast. M3 keeps both lines low at the same time. that's the part that surprised me. and if this is what M3 does at launch, the full rollout is going to be one to watch. what would you build with 1M context? #MiniMax #MiniMaxM3 #ClaudeCode #LLM

Nelly;

17,576 次观看 • 3 个月前

Mamdani put out a map of New York's immigrant neighborhoods for the whole world to see — thirty of them. And he left MY people off of it. Little Italy. The Greeks. The Jewish neighborhoods. The Irish. Then he tells us it was an "accident." People — I got a bridge in Brooklyn to sell you. In this one I get into all of it — the map, the permit, the socialism scam they're running on all of you, and what we would've done about a guy like this back in the day.

Mamdani put out a map of New York's immigrant neighborhoods for the whole world to see — thirty of them. And he left MY people off of it. Little Italy. The Greeks. The Jewish neighborhoods. The Irish. Then he tells us it was an "accident." People — I got a bridge in Brooklyn to sell you. In this one I get into all of it — the map, the permit, the socialism scam they're running on all of you, and what we would've done about a guy like this back in the day.

Michael Franzese

158,803 次观看 • 2 个月前

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.

Mckay Wrigley

85,751 次观看 • 2 年前

I've been showing the output of my flight reconstruction tool for a while and I wanted to share something like it which wasn't a mess of hand tuned stuff that required X-Plane. So I created a completely new version in javascript that runs in an HTML page so that anyone can use it. The output is a KML file which is a tour that works in Google Earth pro with all the attitude information included. This is a long way from perfect, I messed around with multiple smoothing algorithms and none of them compares well with the python code, but they're readable and understandable for anyone.

I've been showing the output of my flight reconstruction tool for a while and I wanted to share something like it which wasn't a mess of hand tuned stuff that required X-Plane. So I created a completely new version in javascript that runs in an HTML page so that anyone can use it. The output is a KML file which is a tour that works in Google Earth pro with all the attitude information included. This is a long way from perfect, I messed around with multiple smoothing algorithms and none of them compares well with the python code, but they're readable and understandable for anyone.

Scott Manley

19,808 次观看 • 7 个月前

A solo quant with no desk and no team just finished in the top 0.04% at WorldQuant. He didn't have better ideas than the $650,000 kids in Greenwich. He had a machine that rewrites its own losing strategies while he sleeps. Your last strategy lost money and you deleted it. His read its own autopsy, found where it bled, rewrote its own code and passed the retest. Nobody touched a keyboard. That was supposed to be a 2028 problem. A hedge fund is six steps on repeat, and five of them cost you nothing as of this year. A junior quant runs the same loop once a month at about $87,500 an idea, and most of what he builds is dead by week six. You type the idea in plain English. An agent writes the rules, backtests 5 years in about 12 seconds, applies Deflated Sharpe so luck across 4,000 combinations can't pass itself off as an edge, and puts it live on Alpaca or Hyperliquid in about 90 seconds. Comes back red? It shows you where it bleeds, rebuilds it and tests again. Try this in two clicks, no code, free in trial period: The sixth step is the one nobody has shipped. Every lesson from a losing trade dies in a log file, so your agent hands you back the idea that already failed in a bear market with a fresh name on it. Whoever closes that gap owns a machine that gets better every week without them. That gets built in months, not years. Bookmark this & read full breakdown about this 6-steps cycle in the article below. When the first closed loop turns up with real money behind it, you'll want the map of what they assembled.

A solo quant with no desk and no team just finished in the top 0.04% at WorldQuant. He didn't have better ideas than the $650,000 kids in Greenwich. He had a machine that rewrites its own losing strategies while he sleeps. Your last strategy lost money and you deleted it. His read its own autopsy, found where it bled, rewrote its own code and passed the retest. Nobody touched a keyboard. That was supposed to be a 2028 problem. A hedge fund is six steps on repeat, and five of them cost you nothing as of this year. A junior quant runs the same loop once a month at about $87,500 an idea, and most of what he builds is dead by week six. You type the idea in plain English. An agent writes the rules, backtests 5 years in about 12 seconds, applies Deflated Sharpe so luck across 4,000 combinations can't pass itself off as an edge, and puts it live on Alpaca or Hyperliquid in about 90 seconds. Comes back red? It shows you where it bleeds, rebuilds it and tests again. Try this in two clicks, no code, free in trial period: The sixth step is the one nobody has shipped. Every lesson from a losing trade dies in a log file, so your agent hands you back the idea that already failed in a bear market with a fresh name on it. Whoever closes that gap owns a machine that gets better every week without them. That gets built in months, not years. Bookmark this & read full breakdown about this 6-steps cycle in the article below. When the first closed loop turns up with real money behind it, you'll want the map of what they assembled.

cvxv666

62,384 次观看 • 1 个月前

Gwyneth Paltrow says she once hooked up in an airplane bathroom with a random guy on an overnight flight to Paris "I think one time back in the day, I did it in the in a airplane bathroom on an overnight flight to Paris." "It wasn't anyone famous." "You know I missed the whole dating app thing and all of that like I totally missed that."

Sensitive content

Gwyneth Paltrow says she once hooked up in an airplane bathroom with a random guy on an overnight flight to Paris "I think one time back in the day, I did it in the in a airplane bathroom on an overnight flight to Paris." "It wasn't anyone famous." "You know I missed the whole dating app thing and all of that like I totally missed that."

Rixlerr

783,913 次观看 • 1 个月前

I’ve been playing with several new AI companies I found yesterday at the AI/UX event in San Francisco that swyx @aiDotEngineer WF ran. It has a demo area with a bunch of companies. One impressed me after I got home: It makes notes for you. You ramble at it for a few minutes about something you want to build. Tomorrow I have an important meeting to discuss my media business. So I ramble on about that for a few minutes and what I need to cover. Then it pulled out important themes. Totally on point in first try. Here is the founder showing it to me.

I’ve been playing with several new AI companies I found yesterday at the AI/UX event in San Francisco that swyx @aiDotEngineer WF ran. It has a demo area with a bunch of companies. One impressed me after I got home: It makes notes for you. You ramble at it for a few minutes about something you want to build. Tomorrow I have an important meeting to discuss my media business. So I ramble on about that for a few minutes and what I need to cover. Then it pulled out important themes. Totally on point in first try. Here is the founder showing it to me.

Robert Scoble

131,705 次观看 • 2 年前

A lot of you don’t know this about me because I don’t post my art much or talk about it but I was an honors art student, accepted with scholarships to nearly every prestigious art school in the country, and my original major was illustration. The “sketch” portion of this video is embarrassing. It does not in any way resemble someone sketching from scratch, but rather it bears very distinct tells of someone drawing over an existing image and trying to pass it off as an original sketch. Everything about the sketch is what I would call “performative” - she’s doing what she *thinks* people do when they sketch, but she doesn’t actually know what that entails. There’s also a reason she recorded this with a secondary device rather than using the built-in screen recording tools on the device/app she’s using. doing that would have revealed the hidden layers that she carefully edited out. Anyway, here’s a real drawing I made. It isn’t good, but I drew it from scratch with my own hands, and that makes me 1000x better than a fraud like her.

A lot of you don’t know this about me because I don’t post my art much or talk about it but I was an honors art student, accepted with scholarships to nearly every prestigious art school in the country, and my original major was illustration. The “sketch” portion of this video is embarrassing. It does not in any way resemble someone sketching from scratch, but rather it bears very distinct tells of someone drawing over an existing image and trying to pass it off as an original sketch. Everything about the sketch is what I would call “performative” - she’s doing what she thinks people do when they sketch, but she doesn’t actually know what that entails. There’s also a reason she recorded this with a secondary device rather than using the built-in screen recording tools on the device/app she’s using. doing that would have revealed the hidden layers that she carefully edited out. Anyway, here’s a real drawing I made. It isn’t good, but I drew it from scratch with my own hands, and that makes me 1000x better than a fraud like her.

She-Rage, Princess of Pain

18,009 次观看 • 9 个月前

A while back, I read a message about veterans. In it, I found what I believe to be one of the best explanations of what the title “veteran” really means to the United States. This Memorial Day, I wanted to share it with you all.

A while back, I read a message about veterans. In it, I found what I believe to be one of the best explanations of what the title “veteran” really means to the United States. This Memorial Day, I wanted to share it with you all.

CB Cotton

26,738 次观看 • 4 个月前

Day 9. Building the game I've dreamed of for 15 years with AI. I'm still in shock from GPT-6. Today I handed it my game's UI. I'd started working on it last week with Fable 5.1 and design skills. I built it in HTML first, preparing the images and icons along the way. Figuring out what I wanted and how it should work took time. I needed that time. I also made animated character portraits. I tried Seedance 2.5 for those, and MiniMax H3 gave me much better results for this job. By the end, I had an interactive prototype with the UI logic worked out and all the assets ready. I could click through it and test how everything behaved before taking it into the game. Once I'd tested it and worked through the remaining questions, I opened GPT-6 in the same project. Gave it the interface and all the materials, and asked it to implement everything in Unity. About two hours later, I had a working UI and nothing to complain about. GPT-6 even went through different resolutions on its own. I'd expected this part to be difficult. It ended up being one of the easiest parts so far. I'd recommend building your UI in HTML first. Iterations are faster, you can click through it just like a real interface, and it's easier to catch the things you missed. Once you've worked those out, connect it to the game. You still have to wait for the engine to compile, whether you write the code yourself or use AI.

Day 9. Building the game I've dreamed of for 15 years with AI. I'm still in shock from GPT-6. Today I handed it my game's UI. I'd started working on it last week with Fable 5.1 and design skills. I built it in HTML first, preparing the images and icons along the way. Figuring out what I wanted and how it should work took time. I needed that time. I also made animated character portraits. I tried Seedance 2.5 for those, and MiniMax H3 gave me much better results for this job. By the end, I had an interactive prototype with the UI logic worked out and all the assets ready. I could click through it and test how everything behaved before taking it into the game. Once I'd tested it and worked through the remaining questions, I opened GPT-6 in the same project. Gave it the interface and all the materials, and asked it to implement everything in Unity. About two hours later, I had a working UI and nothing to complain about. GPT-6 even went through different resolutions on its own. I'd expected this part to be difficult. It ended up being one of the easiest parts so far. I'd recommend building your UI in HTML first. Iterations are faster, you can click through it just like a real interface, and it's easier to catch the things you missed. Once you've worked those out, connect it to the game. You still have to wait for the engine to compile, whether you write the code yourself or use AI.

Stefan 3D AI

275,153 次观看 • 19 天前