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。

This portable microscope was designed by Opus 5 I gave it a few simple requirements, and it generated the whole design in code Lots of details and interactions It looks sci-fi, but it can be easily 3D printed Some of the code can even run on a Raspberry Pi... show more

Dilum Sanjaya

60,274 subscribers

35,446 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

34 条评论

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

I don't usually share live links because it takes extra effort to get models to optimize performance and test everything, which is the boring part. But for something like this, performance isn't really the goal, and it's fun to play around with. So here's the "it works on my machine" version 😉

Eric Mono 的头像

Eric Mono1 个月前

This can be done purely with code? Any other plugins/connectors needed?

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

yes, you don't need plugins or connectors

Aria Tech 的头像

Aria Tech1 个月前

opus 5 just designed a 3d printable microscope from scratch

Gabriel 的头像

Gabriel1 个月前

This is fucking awesome!.

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

thanks Gabriel

Joebed Arts 的头像

Joebed Arts1 个月前

@threejs I love this!! Thanks for sharing

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

thanks Joebed

Rugova 的头像

Rugova1 个月前

that's pure skill

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

@aliuagon_ thanks

INK 的头像

INK1 个月前

so cool !

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

thanks INK

NPCSlayer 的头像

NPCSlayer1 个月前

wow this is crazy! great work

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

thanks

Ricole Bayes 的头像

Ricole Bayes1 个月前

time to find old optics to repurpose

JungheonLee | 이정헌 的头像

JungheonLee | 이정헌1 个月前

@threejs This is awesome! I’m curious how you made it. Did you use Blender MCP?

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

No, this was made purely with three.js. In terms of looks, I'm sure if I started with Blender MCP and then imported it into three.js, I'd get a better result. The issue is that during that process, the model loses context around things like why it added a button in a certain place and what that button is supposed to do. So when it comes to making everything interactive in three.js, it becomes much more difficult. There's probably a better workflow for this, but I haven't found one yet.

JungheonLee | 이정헌 的头像

JungheonLee | 이정헌1 个月前

@threejs Thanks for your kind response!

Refil 的头像

Refil1 个月前

So amazing🔥

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

thanks

Curtin Liu 的头像

Curtin Liu1 个月前

cooooool!

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

thanks Curtin

Sofiia Matsiutsia 的头像

Sofiia Matsiutsia1 个月前

simple requirements = detailed architecture description of the microscope?! Brilliant as always, @DilumSanjaya 👏

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

thanks Sofiia!

Pitchfork & Torch ♞ 的头像

Pitchfork & Torch ♞1 个月前

I want it and I don’t even know what it’s for

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

😂

BuildWahab 的头像

BuildWahab1 个月前

Wow seeing you first till share the link to test 😅

Dilum Sanjaya 的头像

Dilum Sanjaya1 个月前

haha, most of my posts about things I coded myself do have CodePen/live links. but those were more for developers who are familiar with issues around performance and responsiveness. now my focus is on getting people who aren’t familiar with code to build cool stuff. to them, those might feel like issues with vibe coding rather than me just choosing not to spend time fixing them, since I’d rather use that time to experiment with different ideas. anyway, I might start posting links to at least some of the demos 😅

AI Mastery Guide 的头像

AI Mastery Guide1 个月前

Designed straight from requirements into 3D printable code

SomacoSF 的头像

SomacoSF1 个月前

HECK FN YEAH - this is dope. THIS IS FN AMAZING How can I get the UI/UX prompt -- meaning the UX of buttons and sliders and joystick Should be components for all sorts of experiences. This is one of the best things ive seem in a while.

Damir Wallener 的头像

Damir Wallener1 个月前

Does it work?

oy 的头像

oy1 个月前

提示词是什么

Gabriel 的头像

Gabriel1 个月前

just curious, can i get the prompt you used, if thats ok?

Nicolo 的头像

Nicolo1 个月前

Can you share the cad?

相关视频

Haven't seen any demos of using vibe coding to prototype gadgets like this So I made one. Everything here is generated with code Parts of the code and logic can even be reused on a Raspberry Pi to build the real thing Some tips ↓

Haven't seen any demos of using vibe coding to prototype gadgets like this So I made one. Everything here is generated with code Parts of the code and logic can even be reused on a Raspberry Pi to build the real thing Some tips ↓

Dilum Sanjaya

117,792 次观看 • 3 个月前

i gave the exact same prompt to Opus 5 and Fable 5 and here's what came out Opus 5 dropped yesterday and my feed was instantly full of comparison posts but i wanted to check it myself so i gave it one task build 3d Flappy Bird first thing everyone was saying Opus is 2x cheaper than Fable BUT.. building the game on Max effort cost me 250k tokens and 1 hour on Opus and 130k on Fable but Fable did it in half the time Opus gave me volume control plus 3 separate graphics presets to choose from, Fable gave none of that in Opus the environment shifts dynamically as you play in Fable it's basically the same frame the whole run maybe a day/night change here and there graphics, animations, glow, all of it goes to Opus and now that limits jumped 50% for the near future while Fable went paid for me the call is obvious right now Opus same prompt start to finish zero changes to code or commands want it? i can send it over

i gave the exact same prompt to Opus 5 and Fable 5 and here's what came out Opus 5 dropped yesterday and my feed was instantly full of comparison posts but i wanted to check it myself so i gave it one task build 3d Flappy Bird first thing everyone was saying Opus is 2x cheaper than Fable BUT.. building the game on Max effort cost me 250k tokens and 1 hour on Opus and 130k on Fable but Fable did it in half the time Opus gave me volume control plus 3 separate graphics presets to choose from, Fable gave none of that in Opus the environment shifts dynamically as you play in Fable it's basically the same frame the whole run maybe a day/night change here and there graphics, animations, glow, all of it goes to Opus and now that limits jumped 50% for the near future while Fable went paid for me the call is obvious right now Opus same prompt start to finish zero changes to code or commands want it? i can send it over

savip.

45,764 次观看 • 2 个月前

A visual design experiment built on Replit ⠕. UIs in sci-fi movies were the inspiration. A galactic radar listening for signals across the stars with simulated data. Designed to test how far design and code can merge into something beautiful. See it for yourself:

A visual design experiment built on Replit ⠕. UIs in sci-fi movies were the inspiration. A galactic radar listening for signals across the stars with simulated data. Designed to test how far design and code can merge into something beautiful. See it for yourself:

Levin Stanley

294,007 次观看 • 11 个月前

I asked Opus 5.5 to make this entire motion design piece. It took a lot of steering and code references though. But it really understands animations, transition effects and camera movement. It even created the 3D models for each device and logo. What's cool is that you can ask it to adapt the design to your content and it'll do the research for you whether you give it a URL or a local project. It helps to have a library of 3D devices, buttons, effects, and motion design templates like this. Otherwise, it'll be pretty generic. I used my own open-source library where you can use "Copy Prompt" for templates like this.

Meng To

19,800 次观看 • 4 天前

Here is a game that looks like it was made with 2D sprites on a tilemap But it’s actually a three.js scene Also, no external assets. It’s all code and a bit of shader magic The player can switch between the pixel view and the 3D scene Made with Opus 5

Here is a game that looks like it was made with 2D sprites on a tilemap But it’s actually a three.js scene Also, no external assets. It’s all code and a bit of shader magic The player can switch between the pixel view and the 3D scene Made with Opus 5

Dilum Sanjaya

53,670 次观看 • 1 个月前

I love the design of the Void I'm so glad I can actually run around and see a part of it and even engage with some Voidsent

Sensitive content

I love the design of the Void I'm so glad I can actually run around and see a part of it and even engage with some Voidsent

Brendzun

1,007,279 次观看 • 2 个月前

You can now run MicroPython on an emulated Raspberry Pi Pico - inside a real circuit simulator, on your iPhone, iPad, and Mac. Write the code, wire the GPIOs into analog + digital circuits, and watch it all run. Live. iCircuit 1.16 beta is ready. Testers wanted 👇

You can now run MicroPython on an emulated Raspberry Pi Pico - inside a real circuit simulator, on your iPhone, iPad, and Mac. Write the code, wire the GPIOs into analog + digital circuits, and watch it all run. Live. iCircuit 1.16 beta is ready. Testers wanted 👇

Frank A. Krueger

11,129 次观看 • 2 个月前

✨ For the last few months I have been reverse engineering Magnific AI's famous upscaler It uses MultiDiffusion, ControlNet tiles and details LoRas In true AI spirit, I am open sourcing it for everyone to use for free in your apps It's designed to easily control the amount of hallucination, resemblance and creativity. You can use it on Replicate now: Or run it locally with A1111'a web UI (parameters are in the comments) The code is fully open source:

✨ For the last few months I have been reverse engineering Magnific AI's famous upscaler It uses MultiDiffusion, ControlNet tiles and details LoRas In true AI spirit, I am open sourcing it for everyone to use for free in your apps It's designed to easily control the amount of hallucination, resemblance and creativity. You can use it on Replicate now: Or run it locally with A1111'a web UI (parameters are in the comments) The code is fully open source:

philz1337x

565,773 次观看 • 2 年前

I gave ChatGPT a screenshot of a SaaS dashboard and it wrote the code for it. This is the future.

I gave ChatGPT a screenshot of a SaaS dashboard and it wrote the code for it. This is the future.

Mckay Wrigley

8,207,605 次观看 • 3 年前

I love the chicken game! Only available on roobet. Use code stevewilldoit and 100% of money generated goes to the players under code . I keep zero. We are still figuring out the details on how that works but haven’t checked the code in weeks it’s all for the players . This was my idea and roobet liked it so we are doing it . :)

I love the chicken game! Only available on roobet. Use code stevewilldoit and 100% of money generated goes to the players under code . I keep zero. We are still figuring out the details on how that works but haven’t checked the code in weeks it’s all for the players . This was my idea and roobet liked it so we are doing it . :)

Steve Will Do It

131,809 次观看 • 2 年前

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Santiago

64,438 次观看 • 10 个月前

🚨BREAKING: You can now build full websites by just typing. It’s called Youware, and it runs on pure vibe coding. Here’s how it works (with a live demo):👇 1. Create a web page or game just by typing. You can even send a screenshot to make it live. 2. Use built-in tools like Figma, YouTube, and Notion. 3. Change a Figma design into a real website. 4. Change how the webpage looks with one click using the boost button on the profile page. 5. Easily deploy code with a link you can share. 6. Highlights: free online AI coding. Try it today:

Hasan Toor

73,516 次观看 • 1 年前

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

195,173 次观看 • 1 年前

Took 5 phone photos of my living room and Claude Code rebuilt it in 3D. Then I turned it into a skill. Now I can try different layouts and drag furniture around before moving anything heavy. It even flags when a chair gets boxed in. Inspired by Shimecki's room planner

Took 5 phone photos of my living room and Claude Code rebuilt it in 3D. Then I turned it into a skill. Now I can try different layouts and drag furniture around before moving anything heavy. It even flags when a chair gets boxed in. Inspired by Shimecki's room planner

Skylar Kitchen

48,590 次观看 • 2 天前

Gave Gemini 3 Deep Think an image of a 3D spider web and asked for an interactive design tool. It generated a full design suite (procedural control, simulation, optimization) with STL export capability. I used it to engineer new metamaterials and a spider-web inspired bridge design, 3D printed it, then validated the structural integrity with a NVIDIA DGX Spark load test. A mind-blowing example of the future of material and architecture design - image in, fabrication-ready design out! Google Gemini

Gave Gemini 3 Deep Think an image of a 3D spider web and asked for an interactive design tool. It generated a full design suite (procedural control, simulation, optimization) with STL export capability. I used it to engineer new metamaterials and a spider-web inspired bridge design, 3D printed it, then validated the structural integrity with a NVIDIA DGX Spark load test. A mind-blowing example of the future of material and architecture design - image in, fabrication-ready design out! Google Gemini

Markus J. Buehler

98,719 次观看 • 7 个月前

The Raspberry Pi 5 works with AMD 7000-series cards. Yes, it can run Doom (Eternal). And Crysis (Remastered). In 4K. And do hardware video transcoding. Check it out:

The Raspberry Pi 5 works with AMD 7000-series cards. Yes, it can run Doom (Eternal). And Crysis (Remastered). In 4K. And do hardware video transcoding. Check it out:

Jeff Geerling

139,246 次观看 • 1 年前

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

1,441,505 次观看 • 26 天前

🚨 BREAKING: Clone any successful company Claude Code Opus 4.6 in Shipper can take any app and make it yours: design, code, business plan... you can now ship the next duolingo / twitter / airbnb / etc this is THE END of vibe coding.

🚨 BREAKING: Clone any successful company Claude Code Opus 4.6 in Shipper can take any app and make it yours: design, code, business plan... you can now ship the next duolingo / twitter / airbnb / etc this is THE END of vibe coding.

Shipper

243,186 次观看 • 5 个月前

So.. Claude Opus 5 can build a game character, equip, rig and animate it in Three.js with pure code Prompt and demo link below 👇

So.. Claude Opus 5 can build a game character, equip, rig and animate it in Three.js with pure code Prompt and demo link below 👇

Majid Manzarpour

68,363 次观看 • 2 个月前

Raspberry Pi gets a comeback as the Star Trek communicator with OpenClaw! Raspberry Pi was popular in the 2010s and now faces a comeback as the personification of OpenClaw in a Tamagotchi shape - it listens, it thinks and it even talks! And it is not even that expensive! Sebastian Volkl created his Raspberry Pi project with just $100. Do you want your own OpenClaw Tamagotchi? #tamagotchi #openclaw #raspberrypi #ai #tech Sebastian Völkl

Raspberry Pi gets a comeback as the Star Trek communicator with OpenClaw! Raspberry Pi was popular in the 2010s and now faces a comeback as the personification of OpenClaw in a Tamagotchi shape - it listens, it thinks and it even talks! And it is not even that expensive! Sebastian Volkl created his Raspberry Pi project with just $100. Do you want your own OpenClaw Tamagotchi? #tamagotchi #openclaw #raspberrypi #ai #tech Sebastian Völkl

This Week in Startups

16,153 次观看 • 7 个月前