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 recorded a 47-minute tutorial on how I use Opus 5.5 to create designs with gorgeous three.js scenes. I've been using Mobbin MCP to give my agents strong references, then letting Opus bring them together into a full landing page with multiple sections and a consistent design. Opus also... show more

Meng To

188,488 subscribers

37,319 次观看 • 2 天前 •via X (Twitter)

艺术教育科学技术

Anya Rossi• Live Now

Private livecam show

26 条评论

Giacomo Masseroni 的头像

Giacomo Masseroni2 天前

solar panel render on that roof actually looks physically placed, not pasted on like most ai landing pages

Meng To 的头像

Meng To2 天前

opus understood the assignment

Fireply.ai 的头像

Fireply.ai2 天前

okay that roof at dusk is genuinely pretty

Meng To 的头像

Meng To2 天前

genuinely impressed by opus 5.5's taste in colors

Morten Korshavn 的头像

Morten Korshavn2 天前

Dude you are the goat with AI tutorials 🔥

Meng To 的头像

Meng To2 天前

means a lot! been working hard on those

Morten Korshavn 的头像

Morten Korshavn2 天前

I listened to your latest episode @joindiveclub with @ridd_design and it inspired me to go a step deeper as a designer… Now I’m editing stuff for my clients directly in code via agents and submitting PRs daily 🔥

Meng To 的头像

Meng To2 天前

@joindiveclub @ridd_design can't ask better than this. changing one's workflow from an episode has to be high on that list of outcomes. thanks to @ridd_design

James Malsawm 的头像

James Malsawm2 天前

Opus 5.5's work is clean and amazing. is there a repo to try this out?

Meng To 的头像

Meng To2 天前

will share all the source files

Kai Vail 的头像

Kai Vail2 天前

the brand guide step is the underrated part. most ai landing pages fall apart around section 4, when it stops looking like section 1

jorisx 的头像

jorisx2 天前

👌

Rivaldo A. 的头像

Rivaldo A.2 天前

47 minutes of 'I made this beautiful'? Either you're a saint or you're hiding a 3D-printed unicorn in the code.

Meng To 的头像

Meng To2 天前

maybe opus did hide a 3d-printed unicorn in the code

Kimi Nguyen 的头像

Kimi Nguyen2 天前

combining Mobbin MCP with Opus must save a ton of time

john Harry 的头像

john Harry2 天前

this is the bar now: agent + references + a live page. DevDay has to beat the tutorial, not the keynote trailer.

Math. 的头像

Math.2 天前

Isnt this ThreeJS with mesh models

Meng To 的头像

Meng To2 天前

yep it's all code in three.js

Koosha 的头像

Koosha2 天前

Literally was playing with Mobbin mcp today, it’s the most underrated feature they added, thanks for spreading the word.

Meng To 的头像

Meng To2 天前

so good. mobbin is what models are trained on.

Keith Zhai 的头像

Keith Zhai2 天前

mobbin refs before opus builds the page

DestinaMedia 的头像

DestinaMedia2 天前

claude are handing out credits to its users

⚡ ZERO 🛡️⚡ 的头像

⚡ ZERO 🛡️⚡2 天前

I'm not a designer. I bought one of your old products many years ago and to this day it's the only design-based success I've had (I'm a marketer). You have a great way of teaching.

Rook 的头像

Rook2 天前

giving it strong references up front is the whole trick. scenes come out great that way. characters are the one thing references didnt save for me, had to generate those separately

Brjan | AI Builder 的头像

Brjan | AI Builder2 天前

using Mobbin MCP for strong references sounds like a smart way to ensure consistency

Jeremy Bosma 的头像

Jeremy Bosma2 天前

references are the real leverage

相关视频

I recorded a 41-minute tutorial on how I use Astra to create insane three.js websites in Codex. I've been using DiffUI to brainstorm UIs before moving into code. It's fast and cheap, generates multiple variants and lets me branch ideas, sections, logos, and other components. Then I use "Copy for agent" and bring everything into Codex where I add transparent PNG layers, animations, and three.js skills. Live sites: 3D skills: Get $20 in credits on DiffUI:

I recorded a 41-minute tutorial on how I use Astra to create insane three.js websites in Codex. I've been using DiffUI to brainstorm UIs before moving into code. It's fast and cheap, generates multiple variants and lets me branch ideas, sections, logos, and other components. Then I use "Copy for agent" and bring everything into Codex where I add transparent PNG layers, animations, and three.js skills. Live sites: 3D skills: Get $20 in credits on DiffUI:

Meng To

54,176 次观看 • 7 天前

Forget threejs demos, Opus 5.5 is *incredible* at building apps. This is Letters Abroad, a language-learning app I'm working on. You exchange letters with an AI pen pal, and learn a language through context (plus some brain science magic). (also built by Opus, of course) I've been tinkering with this the last week. I built a prototype with Astra, but wasn't happy with the design. Tried Fable, still wasn't good enough. Then Opus 5.5 dropped. In a few hours, I've made more progress on the visuals than in a week of burning tokens. This model is insane. It reads my mind and nails it every time. All the gorgeous 3D models and fluid transitions are thanks to Opus. Crazy idea, prompt, repeat. No more quota anxiety, just non-stop flow state. I'll be writing about my prompts/skills/learnings from building this. Lots to share; this generation of models is absolutely game-changing for design!

Forget threejs demos, Opus 5.5 is incredible at building apps. This is Letters Abroad, a language-learning app I'm working on. You exchange letters with an AI pen pal, and learn a language through context (plus some brain science magic). (also built by Opus, of course) I've been tinkering with this the last week. I built a prototype with Astra, but wasn't happy with the design. Tried Fable, still wasn't good enough. Then Opus 5.5 dropped. In a few hours, I've made more progress on the visuals than in a week of burning tokens. This model is insane. It reads my mind and nails it every time. All the gorgeous 3D models and fluid transitions are thanks to Opus. Crazy idea, prompt, repeat. No more quota anxiety, just non-stop flow state. I'll be writing about my prompts/skills/learnings from building this. Lots to share; this generation of models is absolutely game-changing for design!

Anshu

151,125 次观看 • 4 天前

Hold on... this is getting crazy I kept iterating with Claude Opus 5.5 and then asked it to create a full two-minute episode based on our session. The result genuinely blew my mind... Introducing: "I Will Never Be a Human" by Claude

Hold on... this is getting crazy I kept iterating with Claude Opus 5.5 and then asked it to create a full two-minute episode based on our session. The result genuinely blew my mind... Introducing: "I Will Never Be a Human" by Claude

✯

52,978 次观看 • 3 天前

I asked Opus 5.5 to try a bunch of redesigns of my personal website using my MAX sub, using workflows to iterate and critique. I was really pleased with how it hit the tone I was looking for. Then I asked it to make a trailer with all of its iterations.

I asked Opus 5.5 to try a bunch of redesigns of my personal website using my MAX sub, using workflows to iterate and critique. I was really pleased with how it hit the tone I was looking for. Then I asked it to make a trailer with all of its iterations.

Thariq

177,236 次观看 • 5 天前

JEV + Opus 5.5 is insane for live design... I built a live site redesigner with JEV + Opus 5.5 Paste any link → press Start → scroll, and Jev + Opus 5.5 rebuild every section of the site in front of you Full production ship in 20 seconds: 1. IntersectionObserver fires when a section is 30%+ in the viewport 2. Jev returns one typed decision in ~0.1s: { layout, copy, drop, type, palette, p } 3. Opus 5.5 writes the component (TSX) + a CSS patch for the chosen style 4. The new section wipes in with clip-path, the old one blurs out 5. Next section enters the queue, one at a time, no race conditions Output: 8 sections of a 2015 hosting site rebuilt in ~20s, streamed line by line in the terminal 3 styles, one renderer: orthographic globe + lambert shading → ASCII / 2-color halftone / ink stipple Scroll yourself and it redesigns whatever you land on Jev decides fast, Opus designs it

JEV + Opus 5.5 is insane for live design... I built a live site redesigner with JEV + Opus 5.5 Paste any link → press Start → scroll, and Jev + Opus 5.5 rebuild every section of the site in front of you Full production ship in 20 seconds: 1. IntersectionObserver fires when a section is 30%+ in the viewport 2. Jev returns one typed decision in ~0.1s: { layout, copy, drop, type, palette, p } 3. Opus 5.5 writes the component (TSX) + a CSS patch for the chosen style 4. The new section wipes in with clip-path, the old one blurs out 5. Next section enters the queue, one at a time, no race conditions Output: 8 sections of a 2015 hosting site rebuilt in ~20s, streamed line by line in the terminal 3 styles, one renderer: orthographic globe + lambert shading → ASCII / 2-color halftone / ink stipple Scroll yourself and it redesigns whatever you land on Jev decides fast, Opus designs it

Movez

101,789 次观看 • 3 天前

I need a minute to process the result of this animation made with Opus 5.5 And I asked it to explain how it pulled it off, and my mind got blown all over again. I'll leave you the prompt too 👇

I need a minute to process the result of this animation made with Opus 5.5 And I asked it to explain how it pulled it off, and my mind got blown all over again. I'll leave you the prompt too 👇

Koldo Huici

67,794 次观看 • 3 天前

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

529,998 次观看 • 1 个月前

Creating high-quality ad creatives doesn't have to take hours. I've been using Ribbi to create AI ad creatives for my campaigns, and it's made the process much faster. What I like most is that Ribbi offers a variety of AI Skills that cover the entire ad creative workflow, making it easy to generate on-brand creatives and test multiple ideas all without complicated prompts. If you're running a DTC brand or creating ads for clients, it's definitely worth trying.

K

30,173 次观看 • 2 个月前

I made a three.js landing page with 3D scrolling for every section of the site. Since AI got so good with 3D, you can replace videos with 3D instead. Apart from images, the whole site is 922 KB on disk, 290 KB gzipped. That's insane when a scrolling video site runs 20-100mb at 1080p depending on length. As usual I had to prompt for improved textures, lighting and alpha masking. I used Claude Code (desktop) with Opus 5, Higgsfield for images, and for the cloth effect on them. Inspiration was Daniel Snow's awesome landing page: Let me know if I should open-source. Don't wanna share too many without people asking.

I made a three.js landing page with 3D scrolling for every section of the site. Since AI got so good with 3D, you can replace videos with 3D instead. Apart from images, the whole site is 922 KB on disk, 290 KB gzipped. That's insane when a scrolling video site runs 20-100mb at 1080p depending on length. As usual I had to prompt for improved textures, lighting and alpha masking. I used Claude Code (desktop) with Opus 5, Higgsfield for images, and for the cloth effect on them. Inspiration was Daniel Snow's awesome landing page: Let me know if I should open-source. Don't wanna share too many without people asking.

Meng To

611,417 次观看 • 1 个月前

i made a working app as a total beginner using claude sonnet & opus 4.6 3 tips when building yours: 1. ask your ai to interview YOU to form a PRD 2. ask your ai to build you a daily checklist 3. don't try and do it all in one sitting full pdf guide with my actual prompts below bookmark this🔖

i made a working app as a total beginner using claude sonnet & opus 4.6 3 tips when building yours: 1. ask your ai to interview YOU to form a PRD 2. ask your ai to build you a daily checklist 3. don't try and do it all in one sitting full pdf guide with my actual prompts below bookmark this🔖

Naomi Metzger

15,881 次观看 • 7 个月前

changed how I design with AI. I show how to build faster by adding a design system directly into the prompt, importing any website URL to get a strong starting point, then polishing everything in my own style. I also mix it with components and skills to keep the design consistent and more unique. GPT-5.5 cloning websites is honestly crazy good. The result can get very close to the original, then you can refine it and make it your own. Full breakdown in the comments.

changed how I design with AI. I show how to build faster by adding a design system directly into the prompt, importing any website URL to get a strong starting point, then polishing everything in my own style. I also mix it with components and skills to keep the design consistent and more unique. GPT-5.5 cloning websites is honestly crazy good. The result can get very close to the original, then you can refine it and make it your own. Full breakdown in the comments.

FHILY👑

57,007 次观看 • 4 个月前

I open-sourced ThreeUI, my library of three.js components and landing pages. 160+ are free, and the tool is free too. It includes procedural 3D hero sections, icons, and motion designs. Copy the prompt or source, give it to your agent, then change the theme, lighting, motion or layout. Live site: Repo: I'm adding a lot more soon. Pro comes with 50+ extra components, MCP, and skills. Early adopters get 50% off right now.

I open-sourced ThreeUI, my library of three.js components and landing pages. 160+ are free, and the tool is free too. It includes procedural 3D hero sections, icons, and motion designs. Copy the prompt or source, give it to your agent, then change the theme, lighting, motion or layout. Live site: Repo: I'm adding a lot more soon. Pro comes with 50+ extra components, MCP, and skills. Early adopters get 50% off right now.

Meng To

1,330,389 次观看 • 1 个月前

It’s incredible that you can let Opus 5 run for two hours in Claude Code and get a cinematic Three.js movie inside one HTML file. It created the story, scenes, transitions, camera moves, and procedural world. Higgsfield generated the narration, sound effects, and music. I mostly helped with references for more realistic grass, added the skills I use, and asked it to keep verifying its work. It’s all open source, so you can play with the code. HTML Site: GitHub: Grass reference:

It’s incredible that you can let Opus 5 run for two hours in Claude Code and get a cinematic Three.js movie inside one HTML file. It created the story, scenes, transitions, camera moves, and procedural world. Higgsfield generated the narration, sound effects, and music. I mostly helped with references for more realistic grass, added the skills I use, and asked it to keep verifying its work. It’s all open source, so you can play with the code. HTML Site: GitHub: Grass reference:

Meng To

68,404 次观看 • 1 个月前

audit and fix your entire developer docs site in under a minute We built an AI agent with Browserbase and Cerebras that audits your entire docs site > point it at any documentation site > agent goes down the link tree > agent crawls and verifies every page, checks every link, reads every code snippet > agent also compares content to your GitHub repo > returns a full report with suggested fixes and source references The full code and tutorial for how to build this yourself is live now.

audit and fix your entire developer docs site in under a minute We built an AI agent with Browserbase and Cerebras that audits your entire docs site > point it at any documentation site > agent goes down the link tree > agent crawls and verifies every page, checks every link, reads every code snippet > agent also compares content to your GitHub repo > returns a full report with suggested fixes and source references The full code and tutorial for how to build this yourself is live now.

Sarah Chieng

26,679 次观看 • 5 个月前

I've used Claude Code to build 20+ projects in the last 6 months. Thousands of new users across them. And I've never written a single line of code. I just dropped a 24-min video with my top 10 tips for non-developers — the exact playbook I use every day to run multiple AI agents that handle work that used to take me a full week. This is the best beginner guide to learning and building with Claude Code out right now. Every tutorial I found assumes you're a developer. This one doesn't. I cover everything from first install to running multi-agent workflows — with live demos and real examples for every single tip. How I set up new projects, how I got Claude to match my writing style, how I automate repeatable workflows with one command, and how I run multiple agents working on different tasks at the same time. I also built a full resource repo to go alongside the video — curated video tutorials, the best skill libraries, plugin directories, MCP server guides, written docs, community links, and a starter template you can copy-paste into your first project today. Comment "GUIDE" and I'll send you the full guide with everything you need to learn Claude Code! (make sure we're connected so I can DM you)

I've used Claude Code to build 20+ projects in the last 6 months. Thousands of new users across them. And I've never written a single line of code. I just dropped a 24-min video with my top 10 tips for non-developers — the exact playbook I use every day to run multiple AI agents that handle work that used to take me a full week. This is the best beginner guide to learning and building with Claude Code out right now. Every tutorial I found assumes you're a developer. This one doesn't. I cover everything from first install to running multi-agent workflows — with live demos and real examples for every single tip. How I set up new projects, how I got Claude to match my writing style, how I automate repeatable workflows with one command, and how I run multiple agents working on different tasks at the same time. I also built a full resource repo to go alongside the video — curated video tutorials, the best skill libraries, plugin directories, MCP server guides, written docs, community links, and a starter template you can copy-paste into your first project today. Comment "GUIDE" and I'll send you the full guide with everything you need to learn Claude Code! (make sure we're connected so I can DM you)

JJ Englert

420,062 次观看 • 7 个月前

Claude Fable 5 makes new things possible. I one shot a full horror game with it. One prompt. I have never seen AI output a game like this. This is the leap I've been waiting for. 80.3 on SWE-Bench Pro vs Opus 4.8 at 69.2, the biggest jump I have ever seen on that benchmark. It passed GPT 5.5 in both coding and intelligence on Artificial Analysis. I already canceled my $200 ChatGPT Pro plan. It fixed a Bridge Voice bug in one shot that GPT 5.5, Opus 4.7, and Opus 4.8 all failed to crack for 2 months. 10/10. Best model I have ever used. Full review below.

Claude Fable 5 makes new things possible. I one shot a full horror game with it. One prompt. I have never seen AI output a game like this. This is the leap I've been waiting for. 80.3 on SWE-Bench Pro vs Opus 4.8 at 69.2, the biggest jump I have ever seen on that benchmark. It passed GPT 5.5 in both coding and intelligence on Artificial Analysis. I already canceled my $200 ChatGPT Pro plan. It fixed a Bridge Voice bug in one shot that GPT 5.5, Opus 4.7, and Opus 4.8 all failed to crack for 2 months. 10/10. Best model I have ever used. Full review below.

BridgeMind

19,020 次观看 • 3 个月前

Opus 5.5 sculpted every part of this ship in code, including the dragon, sails, and architecture. I can't say it has bad taste anymore. But it still needs steering, so I tried a new way of prompting. Live site: I asked Opus to score every part of the scene: the ship, water, landscapes, buildings, and their individual parts. Then I asked it to keep improving each part until it scored at least 8 out of 10, depending on my token and time budget. The key is to let it work as long as possible. The longer it works, the better it gets, until it reaches a point where I need to course correct. For me, Opus 5.5 reaches a level of detail and realism that no other model does.

Opus 5.5 sculpted every part of this ship in code, including the dragon, sails, and architecture. I can't say it has bad taste anymore. But it still needs steering, so I tried a new way of prompting. Live site: I asked Opus to score every part of the scene: the ship, water, landscapes, buildings, and their individual parts. Then I asked it to keep improving each part until it scored at least 8 out of 10, depending on my token and time budget. The key is to let it work as long as possible. The longer it works, the better it gets, until it reaches a point where I need to course correct. For me, Opus 5.5 reaches a level of detail and realism that no other model does.

Meng To

44,509 次观看 • 3 天前

i should never be sharing this but f*ck it Seedance + GPT Images 2 is insane for AI video you can generate ads for almost any product, even really complex ones that Omni or Kling struggle to create without issues i've been using this for videos with complicated movements, multiple actions, and comedy scenes, and it's been perfect for it here's what you can do with it: - create realistic product ads with complex movements or product looks - generate consistent characters across multiple scenes - pull off comedy skits with natural actions and timing - animate almost any product without weird AI artifacts - turn a single image into a high-quality ad in minutes i put together a step-by-step breakdown on how i create them, with all the prompts and everything i'm using - literally my complete workflow RT + reply "SEEDANCE" and i'll send it over (must follow so i can DM)

i should never be sharing this but f*ck it Seedance + GPT Images 2 is insane for AI video you can generate ads for almost any product, even really complex ones that Omni or Kling struggle to create without issues i've been using this for videos with complicated movements, multiple actions, and comedy scenes, and it's been perfect for it here's what you can do with it: - create realistic product ads with complex movements or product looks - generate consistent characters across multiple scenes - pull off comedy skits with natural actions and timing - animate almost any product without weird AI artifacts - turn a single image into a high-quality ad in minutes i put together a step-by-step breakdown on how i create them, with all the prompts and everything i'm using - literally my complete workflow RT + reply "SEEDANCE" and i'll send it over (must follow so i can DM)

MAX

10,900 次观看 • 1 个月前

I found a site with 1,000+ of FREE landing page templates. Its literally ONE CLICK: - Pick a design, copy the prompt, paste into Claude Code or Codex - Full pages and individual sections both available - Animated hero sections you keep seeing on Twitter? They're all here It takes < 2 minutes to go from template to frontend

I found a site with 1,000+ of FREE landing page templates. Its literally ONE CLICK: - Pick a design, copy the prompt, paste into Claude Code or Codex - Full pages and individual sections both available - Animated hero sections you keep seeing on Twitter? They're all here It takes < 2 minutes to go from template to frontend

Harshil Tomar

29,634 次观看 • 3 个月前