Loading video...

Video Failed to Load

Go Home

Apple's product pages have that scroll effect. The camera flies through a 3D world. Products float. Scenes transition. No cuts. One continuous flight driven by your scroll wheel. Here is what one costs to build in 2026. Big storytelling agencies (Noomo, WithLore, Utsubo): $15,000 to $100,000. Three to six...

heynavtoor's profile picture

Nav Toor

149,355 subscribers

338,032 views • 2 days ago •via X (Twitter)

Science & TechnologyEducationNews & Politics
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Fable 5 and GPT-5.6 built the same scroll-animated website from 1 skill in 32 minutes and only 1 of them made it feel like a film. Same prompt: boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal multiple videos, matched starting frames, frames ripped out 1 by 1 and synced to scroll position. The skill does all of it: Generate 1 anchor image and approve it every scene inherits the style Turn it into video through the Higgs Field MCP (Seedance), straight from the terminal FFmpeg pulls every frame Each frame maps to scroll position, so your scrollbar becomes the playhead Setup is just connecting the MCP and loading the skill works in Claude Code and Codex. It interviews you first about scenes, budget and mobile, then shows the anchor image before burning a single credit on video. Budget reality: 6 scenes runs ~800 credits and is overkill, 4 scenes is the sweet spot, crop-safe mobile is the cheap path. The verdict came down to transitions. GPT-5.6 Soul built strong scenes with incredible detail inside each one then hard cuts between scene 1 and 2, and again between 2 and 3. Fable 5 stitched them together: wires push out of the top of frame while the next scene blurs in behind, gains depth and locks into place. Same skill, same prompts, 10 generations each. Credit to Peter Wang for the original Scroll World skill open source, now forked with budget tiers and mobile fixes. Soul built 4 scenes. Fable built 1 film.
9:48

Fable 5 and GPT-5.6 built the same scroll-animated website from 1 skill in 32 minutes and only 1 of them made it feel like a film. Same prompt: boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal multiple videos, matched starting frames, frames ripped out 1 by 1 and synced to scroll position. The skill does all of it: Generate 1 anchor image and approve it every scene inherits the style Turn it into video through the Higgs Field MCP (Seedance), straight from the terminal FFmpeg pulls every frame Each frame maps to scroll position, so your scrollbar becomes the playhead Setup is just connecting the MCP and loading the skill works in Claude Code and Codex. It interviews you first about scenes, budget and mobile, then shows the anchor image before burning a single credit on video. Budget reality: 6 scenes runs ~800 credits and is overkill, 4 scenes is the sweet spot, crop-safe mobile is the cheap path. The verdict came down to transitions. GPT-5.6 Soul built strong scenes with incredible detail inside each one then hard cuts between scene 1 and 2, and again between 2 and 3. Fable 5 stitched them together: wires push out of the top of frame while the next scene blurs in behind, gains depth and locks into place. Same skill, same prompts, 10 generations each. Credit to Peter Wang for the original Scroll World skill open source, now forked with budget tiers and mobile fixes. Soul built 4 scenes. Fable built 1 film.

Spike 1%

44,834 views • 21 days ago

Fable 5 and GPT-5.6 built the same scroll-animated website from one skill in 32 minutes. Only one of them made it feel like a film. Same prompt. Boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal, so the skill handles everything automatically. Here is how it works: → One anchor image sets the visual style and every scene that follows inherits it automatically → Higgsfield generates the video straight from the terminal through the MCP connection, no manual exporting → FFmpeg rips every frame out of the generated video automatically → Each frame then gets mapped to a scroll position so your scrollbar literally becomes the playhead The verdict came down to transitions. GPT-5.6 built strong individual scenes with incredible detail inside each one, but then hard-cut between them with no connection. Fable 5 stitched everything together. Wires push out of the top of the frame while the next scene blurs in behind it, gains depth and locks into place seamlessly. Same skill, same prompts, 10 generations each from both models. GPT-5.6 built 4 scenes. Fable 5 built one continuous film. Credit: Chase AI
9:48

Fable 5 and GPT-5.6 built the same scroll-animated website from one skill in 32 minutes. Only one of them made it feel like a film. Same prompt. Boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal, so the skill handles everything automatically. Here is how it works: → One anchor image sets the visual style and every scene that follows inherits it automatically → Higgsfield generates the video straight from the terminal through the MCP connection, no manual exporting → FFmpeg rips every frame out of the generated video automatically → Each frame then gets mapped to a scroll position so your scrollbar literally becomes the playhead The verdict came down to transitions. GPT-5.6 built strong individual scenes with incredible detail inside each one, but then hard-cut between them with no connection. Fable 5 stitched everything together. Wires push out of the top of the frame while the next scene blurs in behind it, gains depth and locks into place seamlessly. Same skill, same prompts, 10 generations each from both models. GPT-5.6 built 4 scenes. Fable 5 built one continuous film. Credit: Chase AI

0xMarioNawfal

48,091 views • 20 days ago

THIS GUY UPDATED AN OPEN SOURCE TOOL FOR CLAUDE FABLE 5 THAT TAKES A SINGLE IMAGE AND AUTOMATICALLY REBUILDS IT AS A PREMIUM SCROLL LINKED WEB ANIMATION Instead of slicing videos by hand or exporting individual frames, you just hand it an image and it recreates the entire sequence as a pure scroll mapped experience - Pick an anchor image and set your overall creative direction - The tool automatically scales it into motion clips and uses ffmpeg to rip out every frame in the background - Maps the frames directly to your scroll position, tracking the cursor for an ultra smooth user experience - AND its open source, so you can drop the skill into your own terminal workspace He tested it on a highly detailed origami style travel website and it came out genuinely good for something built completely in one shot Turning a single photo into an automated frame mapped scrolling app is the kind of thing that used to take a developer hours
0:34

THIS GUY UPDATED AN OPEN SOURCE TOOL FOR CLAUDE FABLE 5 THAT TAKES A SINGLE IMAGE AND AUTOMATICALLY REBUILDS IT AS A PREMIUM SCROLL LINKED WEB ANIMATION Instead of slicing videos by hand or exporting individual frames, you just hand it an image and it recreates the entire sequence as a pure scroll mapped experience - Pick an anchor image and set your overall creative direction - The tool automatically scales it into motion clips and uses ffmpeg to rip out every frame in the background - Maps the frames directly to your scroll position, tracking the cursor for an ultra smooth user experience - AND its open source, so you can drop the skill into your own terminal workspace He tested it on a highly detailed origami style travel website and it came out genuinely good for something built completely in one shot Turning a single photo into an automated frame mapped scrolling app is the kind of thing that used to take a developer hours

0xMarioNawfal

111,143 views • 22 days ago

This site looks like it was built by a team of 3D developers It wasn't. It's just video. And that's the part nobody expects > he generated two frames with AI > turned them into a clip with Seedance 2.0 > then gave it to Claude 4.8 to wrap into a full immersive scrollable experience Three effects that make the user feel like they're physically moving through a space: > see-through scrub > 3D scroll > mouse tracking None of them are actually 3D. The browser never renders a single polygon. It's a video being controlled by scroll position and cursor movement Most people assume sites like this require a creative developer who specializes in WebGL and weeks of optimization. The actual pipeline is three steps and fits in an afternoon full walkthrough in the article below. bookmark this before you need it
0:37

This site looks like it was built by a team of 3D developers It wasn't. It's just video. And that's the part nobody expects > he generated two frames with AI > turned them into a clip with Seedance 2.0 > then gave it to Claude 4.8 to wrap into a full immersive scrollable experience Three effects that make the user feel like they're physically moving through a space: > see-through scrub > 3D scroll > mouse tracking None of them are actually 3D. The browser never renders a single polygon. It's a video being controlled by scroll position and cursor movement Most people assume sites like this require a creative developer who specializes in WebGL and weeks of optimization. The actual pipeline is three steps and fits in an afternoon full walkthrough in the article below. bookmark this before you need it

monokern

157,112 views • 27 days ago

SHE CHARGES $7500 FOR A SITE YOU CONTROL BY WAVING AT YOUR WEBCAM no mouse, no scroll, no clicking anything, the camera tracks your hand and the whole site responds as you move it through the air how she built it: render the base clip in seedance 2 open replit and attach your design reference tell it to wire hand tracking with mediapipe map the hand position to the video in a single prompt still in the same chat, switch it to slide mode or a scroll transform whenever you want she never wrote one line of the tracking code, replit stood up the entire gesture layer from that one instruction meanwhile your local dev still thinks interactive means a button that lights up when the cursor grazes it the exact mediapipe prompt is in the guide below, save it before this becomes the standard
0:33

SHE CHARGES $7500 FOR A SITE YOU CONTROL BY WAVING AT YOUR WEBCAM no mouse, no scroll, no clicking anything, the camera tracks your hand and the whole site responds as you move it through the air how she built it: render the base clip in seedance 2 open replit and attach your design reference tell it to wire hand tracking with mediapipe map the hand position to the video in a single prompt still in the same chat, switch it to slide mode or a scroll transform whenever you want she never wrote one line of the tracking code, replit stood up the entire gesture layer from that one instruction meanwhile your local dev still thinks interactive means a button that lights up when the cursor grazes it the exact mediapipe prompt is in the guide below, save it before this becomes the standard

Bounce

59,394 views • 24 days ago

HE BUILT A BRAND SITE THAT LOOKS LIKE IT COST $10,000 - IN ONE EVENING WITH CLAUDE CODE What's on screen isn't a template with a color swap It's a full product brand site with effects most designers reach for Figma plugins to get What's actually on the page: > A headline that glows like it's lit from the inside > The product breaking out of the frame and sitting in front of the text > Typography that stops you mid-scroll > Depth that usually takes a motion designer to pull off > Details so considered it looks like someone art directed every pixel What it normally takes: > A brand designer who knows typography at this level > A frontend developer who knows when to reach for z-index and when not to > Back and forth between them until the details land right The price gap: > Brand site at this quality: $5,000 - $8,000+ > Your cost: a Claude subscription > Timeline: an evening Full walkthrough in the article below
0:20

HE BUILT A BRAND SITE THAT LOOKS LIKE IT COST $10,000 - IN ONE EVENING WITH CLAUDE CODE What's on screen isn't a template with a color swap It's a full product brand site with effects most designers reach for Figma plugins to get What's actually on the page: > A headline that glows like it's lit from the inside > The product breaking out of the frame and sitting in front of the text > Typography that stops you mid-scroll > Depth that usually takes a motion designer to pull off > Details so considered it looks like someone art directed every pixel What it normally takes: > A brand designer who knows typography at this level > A frontend developer who knows when to reach for z-index and when not to > Back and forth between them until the details land right The price gap: > Brand site at this quality: $5,000 - $8,000+ > Your cost: a Claude subscription > Timeline: an evening Full walkthrough in the article below

monokern

522,937 views • 1 month ago

This guy with no design background just built a 3D website that would have cost a client $8,000 at any agency. He didn't hire a developer. He didn't open Figma. He opened Claude and started typing what he wanted to see. 3D objects that move on scroll. Animations that follow the cursor. Cinematic transitions between sections. Claude generated the code. Emergent rendered it live. He adjusted with more prompts until the screen showed something he couldn't have built in 6 months of learning. The whole thing took one afternoon. What used to require a senior developer and a $15,000 budget now requires knowing how to describe what you want clearly. That's it. That's the only skill. Most people have Claude. Almost none of them know how to actually use it. This article below fixes that.
0:36

This guy with no design background just built a 3D website that would have cost a client $8,000 at any agency. He didn't hire a developer. He didn't open Figma. He opened Claude and started typing what he wanted to see. 3D objects that move on scroll. Animations that follow the cursor. Cinematic transitions between sections. Claude generated the code. Emergent rendered it live. He adjusted with more prompts until the screen showed something he couldn't have built in 6 months of learning. The whole thing took one afternoon. What used to require a senior developer and a $15,000 budget now requires knowing how to describe what you want clearly. That's it. That's the only skill. Most people have Claude. Almost none of them know how to actually use it. This article below fixes that.

Anatoli Kopadze

363,251 views • 3 months ago

Notch Clips. every other ad tool ignores the footage sitting in your dropbox and generates new clips from a prompt. notch opens your library instead. it watches every clip you have ever shot and understands what is inside each one. the mood. who is in frame. what they are doing. the quality. so when you ask it to build an ad, it does not start from scratch. it reaches into your past shoots, finds the clip that fits, and slots it into the exact moment that needs it. here is what that looks like. you had thirteen versions of one reaction shot. notch picked the one that worked and left the other twelve. not by filename. not by guessing from a reference image. it watched all thirteen and could tell the difference. that is the whole idea. the right clip was already in your library. every other tool was about to make a worse one. footage you already shot, turned into every ad you still need. drop your site and a few clips you have. notch builds the first ad from them.
0:40

Notch Clips. every other ad tool ignores the footage sitting in your dropbox and generates new clips from a prompt. notch opens your library instead. it watches every clip you have ever shot and understands what is inside each one. the mood. who is in frame. what they are doing. the quality. so when you ask it to build an ad, it does not start from scratch. it reaches into your past shoots, finds the clip that fits, and slots it into the exact moment that needs it. here is what that looks like. you had thirteen versions of one reaction shot. notch picked the one that worked and left the other twelve. not by filename. not by guessing from a reference image. it watched all thirteen and could tell the difference. that is the whole idea. the right clip was already in your library. every other tool was about to make a worse one. footage you already shot, turned into every ad you still need. drop your site and a few clips you have. notch builds the first ad from them.

Vinay Jain

406,286 views • 2 months ago

Today we're launching Goose Ads in Claude. This is a skill /goose-ads that lets anyone make high-performing ad creatives directly in Claude, Claude Code, Cowork, or Codex. Here's how it works: 1. Install the skill: npx gooseworks install --all 2. Run this prompt: /goose-ads create ads for my brand 3. (Optional) Pick templates you like on the platform The skill finds top-performing ads that companies are already spending $ on and generates creatives for your brand. It also ensures that generated creatives are accurate to your brand's messaging, logo, assets, etc. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.
0:28

Today we're launching Goose Ads in Claude. This is a skill /goose-ads that lets anyone make high-performing ad creatives directly in Claude, Claude Code, Cowork, or Codex. Here's how it works: 1. Install the skill: npx gooseworks install --all 2. Run this prompt: /goose-ads create ads for my brand 3. (Optional) Pick templates you like on the platform The skill finds top-performing ads that companies are already spending $ on and generates creatives for your brand. It also ensures that generated creatives are accurate to your brand's messaging, logo, assets, etc. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.

Shiv

600,338 views • 1 month ago

Today we're launching iMessage video ads in Claude. Faceless video is the best-performing ad format right now — and Claude can now generate a full one end to end, in one prompt. Here's how it works: 1. Install: npx gooseworks install --all 2. Run: /goose-video make an iMessage ad for [your product] Claude writes the script, generates the photos in the thread, animates the conversation, and closes on your brand. SFX, music, end card, all of it. The trick: it's just HTML. No video generation models, so it's fast and cheap — and it works because it doesn't look like an ad. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.
0:28

Today we're launching iMessage video ads in Claude. Faceless video is the best-performing ad format right now — and Claude can now generate a full one end to end, in one prompt. Here's how it works: 1. Install: npx gooseworks install --all 2. Run: /goose-video make an iMessage ad for [your product] Claude writes the script, generates the photos in the thread, animates the conversation, and closes on your brand. SFX, music, end card, all of it. The trick: it's just HTML. No video generation models, so it's fast and cheap — and it works because it doesn't look like an ad. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.

Soham Mehta

49,148 views • 26 days ago

most people spend hours describing what they want to Claude Code this guy just browsed a catalog of thousands of animated UI components, found one he liked, and hit "copy prompt" that's it. the prompt goes into Claude Code and it builds it. > 21st(.)dev - a library of community-made components built for React, Next.js, Tailwind > every component has a ready-made prompt attached > you pick the effect, copy, paste, done no describing animations from scratch. no explaining what "smooth scroll" or "hover glow" means. someone already figured out the exact prompt that produces it. gap between people who know this exists and people who don't is measured in hours per project full walkthrough in the article below
0:41

most people spend hours describing what they want to Claude Code this guy just browsed a catalog of thousands of animated UI components, found one he liked, and hit "copy prompt" that's it. the prompt goes into Claude Code and it builds it. > 21st(.)dev - a library of community-made components built for React, Next.js, Tailwind > every component has a ready-made prompt attached > you pick the effect, copy, paste, done no describing animations from scratch. no explaining what "smooth scroll" or "hover glow" means. someone already figured out the exact prompt that produces it. gap between people who know this exists and people who don't is measured in hours per project full walkthrough in the article below

monokern

64,484 views • 25 days ago

Today we're launching Brand Skills in Claude. This is a set of skills /gooseworks that gives Claude full context on your brand — logo, colors, voice, positioning — so anyone can make on-brand ads and content directly in Claude, Claude Code, Cowork, or Codex. Here's how it works: 1. Install the skills: npx gooseworks install --all 2. Run this prompt: /gooseworks --skill brand-intel-branddev [your-website] — pulls your logo, brand colors + company data in ~15 seconds 3. Run brand-voice-extractor, brand-research and update-brand-kit — Claude learns how you sound, your positioning and audience, and saves it all as a reusable brand kit Every other skill reads your brand kit automatically. So every ad and post you generate is accurate to your brand's messaging, logo, assets, etc. By default. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.
0:27

Today we're launching Brand Skills in Claude. This is a set of skills /gooseworks that gives Claude full context on your brand — logo, colors, voice, positioning — so anyone can make on-brand ads and content directly in Claude, Claude Code, Cowork, or Codex. Here's how it works: 1. Install the skills: npx gooseworks install --all 2. Run this prompt: /gooseworks --skill brand-intel-branddev [your-website] — pulls your logo, brand colors + company data in ~15 seconds 3. Run brand-voice-extractor, brand-research and update-brand-kit — Claude learns how you sound, your positioning and audience, and saves it all as a reusable brand kit Every other skill reads your brand kit automatically. So every ad and post you generate is accurate to your brand's messaging, logo, assets, etc. By default. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.

Soham Mehta

139,623 views • 1 month ago

I plugged ChatGPT Luna 5.6 and Claude Opus 5 into Blender through MCP, and one of them is one-shotting entire 3D scenes now. Top is Luna 5.6 in fast mode modeling ship cannons with a firing animation. Watching the scene grow mesh by mesh in real time is a separate kind of dopamine. Bottom is Opus 5 building a full carriage scene with terrain, rocks and lighting. This one is simply built for 3D -- the whole thing from a single prompt with zero retries and zero corrections. The entire bridge is one open-source repo, no Python and no modeling skills required: > The repo is with 16.9k stars under MIT license. > It works with any model -- Claude, GPT, Cursor, any MCP client. > The model sees your scene through a live socket and edits it in real time. A year ago this workflow didn't exist, and now the gap between an idea and a rendered 3D scene is one prompt. Save this one -- you will come back for the repo ↓
0:58

I plugged ChatGPT Luna 5.6 and Claude Opus 5 into Blender through MCP, and one of them is one-shotting entire 3D scenes now. Top is Luna 5.6 in fast mode modeling ship cannons with a firing animation. Watching the scene grow mesh by mesh in real time is a separate kind of dopamine. Bottom is Opus 5 building a full carriage scene with terrain, rocks and lighting. This one is simply built for 3D -- the whole thing from a single prompt with zero retries and zero corrections. The entire bridge is one open-source repo, no Python and no modeling skills required: > The repo is with 16.9k stars under MIT license. > It works with any model -- Claude, GPT, Cursor, any MCP client. > The model sees your scene through a live socket and edits it in real time. A year ago this workflow didn't exist, and now the gap between an idea and a rendered 3D scene is one prompt. Save this one -- you will come back for the repo ↓

slash1s

150,102 views • 7 days ago

Motion graphics used to take me an hour per scene (or more) Now I'm creating them in 3-5 minutes — without After Effects, without Premiere, without writing a single line of code. I'm a former LA filmmaker (still PGA). My entire video stack is now 3 tools: Claude Code + HyperFrames (from HeyGen) + Descript Here's how the workflow runs: 1. Drop my brand style guide into a folder (colors, fonts, components Claude reuses forever) 2. Paste a line from my Descript transcript into Claude Code: "Create a scene for this part of the video" 3. Claude Code reads my brand, generates the HyperFrames scene, renders it to MP4 4. Drag the MP4 into Descript, drop it on the matching line of the transcript 5. Done. 3-5 minutes per scene. The unlock is the brand style guide. Once Claude has your colors, fonts, and reusable components, every scene inherits your look automatically. Bonus — you can take a Claude Design export (.zip), hand it to Claude Code, and it'll convert the HTML into a HyperFrames video you can render and edit. I built a GitHub repo with all the skills pre-loaded. Non-developers can clone it, open Claude Code, and be rendering scenes in under 10 minutes. Full walkthrough (20 min video) below Repo (skills + brand template + music-from-transcript plugin): Bookmark this if you make videos. The brand-style-guide pattern alone will save you hours every week. If you're a creator or operator using AI for content — share this with someone who's still living in After Effects.
23:55

Motion graphics used to take me an hour per scene (or more) Now I'm creating them in 3-5 minutes — without After Effects, without Premiere, without writing a single line of code. I'm a former LA filmmaker (still PGA). My entire video stack is now 3 tools: Claude Code + HyperFrames (from HeyGen) + Descript Here's how the workflow runs: 1. Drop my brand style guide into a folder (colors, fonts, components Claude reuses forever) 2. Paste a line from my Descript transcript into Claude Code: "Create a scene for this part of the video" 3. Claude Code reads my brand, generates the HyperFrames scene, renders it to MP4 4. Drag the MP4 into Descript, drop it on the matching line of the transcript 5. Done. 3-5 minutes per scene. The unlock is the brand style guide. Once Claude has your colors, fonts, and reusable components, every scene inherits your look automatically. Bonus — you can take a Claude Design export (.zip), hand it to Claude Code, and it'll convert the HTML into a HyperFrames video you can render and edit. I built a GitHub repo with all the skills pre-loaded. Non-developers can clone it, open Claude Code, and be rendering scenes in under 10 minutes. Full walkthrough (20 min video) below Repo (skills + brand template + music-from-transcript plugin): Bookmark this if you make videos. The brand-style-guide pattern alone will save you hours every week. If you're a creator or operator using AI for content — share this with someone who's still living in After Effects.

JJ Englert

103,435 views • 3 months ago

how beginners build WEBSITES vs higgsfield ai plugin... most people treat ai website builders as faster templates. you pick a theme, swap the copy, change the background image, and ship something someone else designed. the fable 5/claude build works differently because of what's connected to it. the higgsfield mcp gives claude direct access to nano banana pro and seedance 2.0 during the build. it generates the stills and the video clips itself, in the same session, and drops them straight into the page without downloading assets and reuploading them somewhere else. having that access changes the order it works in. it produces the images first and writes the code after, because scroll frames get sliced out of visuals that already exist. it figured out that dependency before it started. the wix tutorial is a beginner level of exactly that. where to click, how to add a section, how to change a background, how to hide an element on mobile. halfway through, it tells you to avoid customizing too much because the design will break. every color in that template was picked to sit next to every other color, so your own taste is a liability inside it. you're editing someone's existing template. changing an asset after the build is one prompt. the mcp regenerates it, the code updates around it, nothing else in the page moves. inside a template that same change means rebuilding the section.
1:00

how beginners build WEBSITES vs higgsfield ai plugin... most people treat ai website builders as faster templates. you pick a theme, swap the copy, change the background image, and ship something someone else designed. the fable 5/claude build works differently because of what's connected to it. the higgsfield mcp gives claude direct access to nano banana pro and seedance 2.0 during the build. it generates the stills and the video clips itself, in the same session, and drops them straight into the page without downloading assets and reuploading them somewhere else. having that access changes the order it works in. it produces the images first and writes the code after, because scroll frames get sliced out of visuals that already exist. it figured out that dependency before it started. the wix tutorial is a beginner level of exactly that. where to click, how to add a section, how to change a background, how to hide an element on mobile. halfway through, it tells you to avoid customizing too much because the design will break. every color in that template was picked to sit next to every other color, so your own taste is a liability inside it. you're editing someone's existing template. changing an asset after the build is one prompt. the mcp regenerates it, the code updates around it, nothing else in the page moves. inside a template that same change means rebuilding the section.

Sulfur

22,938 views • 6 days ago

THIS TOOL LETS ANYONE BUILD A 3D WORLD FROM ONE PHOTO - AND THE MONEY IS ALREADY THERE FOR WHOEVER MOVES FIRST World Labs raised $230 million to build exactly this - upload one image from your phone, get a full explorable 3D world you can walk through no team, no 3D modeling skills, no development budget - just one photo and a few minutes architects, game developers and film studios pay hundreds of millions and years of work to build what this does in minutes anyone can now sell 3D world generation as a service - virtual tours, game environments, film sets, architectural visualization - clients who used to pay $10,000-50,000 for this still need it done the barrier just dropped from millions of dollars to one photo the people making money from this in 12 months are the ones who started today
0:46

THIS TOOL LETS ANYONE BUILD A 3D WORLD FROM ONE PHOTO - AND THE MONEY IS ALREADY THERE FOR WHOEVER MOVES FIRST World Labs raised $230 million to build exactly this - upload one image from your phone, get a full explorable 3D world you can walk through no team, no 3D modeling skills, no development budget - just one photo and a few minutes architects, game developers and film studios pay hundreds of millions and years of work to build what this does in minutes anyone can now sell 3D world generation as a service - virtual tours, game environments, film sets, architectural visualization - clients who used to pay $10,000-50,000 for this still need it done the barrier just dropped from millions of dollars to one photo the people making money from this in 12 months are the ones who started today

Cortex

12,123 views • 1 month ago

I found a skill that turns Claude into an AI ad creative maker. It’s called Goose Ads by Gooseworks, and it works directly inside Claude, Claude Code, Cowork, or Codex. You can now create ad creatives for your brand with one command. How it works: → Install Gooseworks npx gooseworks install --all → Run this prompt /goose-ads create ads for my brand → Optional Pick templates you like on the platform Goose Ads finds creatives that companies are already spending money on, studies what is working, and generates new ad creatives for your brand. It also keeps everything aligned with your website, messaging, logo, assets, and positioning, so the final output feels brand-ready instead of generic. And this is bigger than one ad skill. Gooseworks has 100+ open-source growth skills for ads, content, competitor research, GTM, SEO, lead generation, and more. Claude is slowly becoming more than a chatbot. It is becoming a growth operator. Comment 'Goose' and I’ll DM you the full open-source skill library.
0:28

I found a skill that turns Claude into an AI ad creative maker. It’s called Goose Ads by Gooseworks, and it works directly inside Claude, Claude Code, Cowork, or Codex. You can now create ad creatives for your brand with one command. How it works: → Install Gooseworks npx gooseworks install --all → Run this prompt /goose-ads create ads for my brand → Optional Pick templates you like on the platform Goose Ads finds creatives that companies are already spending money on, studies what is working, and generates new ad creatives for your brand. It also keeps everything aligned with your website, messaging, logo, assets, and positioning, so the final output feels brand-ready instead of generic. And this is bigger than one ad skill. Gooseworks has 100+ open-source growth skills for ads, content, competitor research, GTM, SEO, lead generation, and more. Claude is slowly becoming more than a chatbot. It is becoming a growth operator. Comment 'Goose' and I’ll DM you the full open-source skill library.

Jaynit Makwana

53,922 views • 1 month ago

I am stocked to announce that I won the OpenAI Developers Codex x Mollie Hacka Worldwide Hackathon in Paris. 60+ builders, every one of us working solo, one day to ship. I built mine around a single question: who gets to own intelligence? The default answer is scary. You hand your data to a handful of labs, they train the model, they own it, and you rent back a thin slice of what your own data made possible. That is the bargain on the table today. I do not accept it. So I built Lensemble: a Tapestry like distributed training platform for JEPA based World Models. What does it enable: World Models that a community improves together, keeps sovereign, and co-owns. Two bets sit underneath it. First, the paradigm. Language models predict the next token. Powerful for text, a dead end for the physical world. A robot does not need to autocomplete sentences, it needs to predict what happens next in the world. That is what JEPA does: it learns by predicting representations instead of pixels or tokens. I am convinced world models are the most underrated paradigm in AI right now, and the closest thing we have to a ChatGPT moment for robotics. Second, the politics. Your raw trajectories never leave your machine. Each participant trains locally against a shared protocol and ships only an update, never the data. A federated round folds those updates into one shared world model, a LeWorldModel based model, and the gain is measured, not claimed: a 12k-parameter adapter on a frozen backbone, held-out prediction error down about 12 percent, the model measurably less surprised by the world. Then the upside is split by contribution weight, so the people who improved the model own a share of what it earns. This is the thesis behind Project Tapestry, the AI Alliance and Yann LeCun's push for federated, sovereign frontier AI, carried into world models and robotics. Call it Tapestry for the physical world. All of it built solo, in a single day, with Codex as my pair the whole way. Thank you to OpenAI Codex and Mollie for backing builders who ship real things, and to Boris and the organizing crew for the room and the standard you set. Intelligence the world improves, and the world owns. That is the future I want for my kids, and the one I will keep building.
1:13

I am stocked to announce that I won the OpenAI Developers Codex x Mollie Hacka Worldwide Hackathon in Paris. 60+ builders, every one of us working solo, one day to ship. I built mine around a single question: who gets to own intelligence? The default answer is scary. You hand your data to a handful of labs, they train the model, they own it, and you rent back a thin slice of what your own data made possible. That is the bargain on the table today. I do not accept it. So I built Lensemble: a Tapestry like distributed training platform for JEPA based World Models. What does it enable: World Models that a community improves together, keeps sovereign, and co-owns. Two bets sit underneath it. First, the paradigm. Language models predict the next token. Powerful for text, a dead end for the physical world. A robot does not need to autocomplete sentences, it needs to predict what happens next in the world. That is what JEPA does: it learns by predicting representations instead of pixels or tokens. I am convinced world models are the most underrated paradigm in AI right now, and the closest thing we have to a ChatGPT moment for robotics. Second, the politics. Your raw trajectories never leave your machine. Each participant trains locally against a shared protocol and ships only an update, never the data. A federated round folds those updates into one shared world model, a LeWorldModel based model, and the gain is measured, not claimed: a 12k-parameter adapter on a frozen backbone, held-out prediction error down about 12 percent, the model measurably less surprised by the world. Then the upside is split by contribution weight, so the people who improved the model own a share of what it earns. This is the thesis behind Project Tapestry, the AI Alliance and Yann LeCun's push for federated, sovereign frontier AI, carried into world models and robotics. Call it Tapestry for the physical world. All of it built solo, in a single day, with Codex as my pair the whole way. Thank you to OpenAI Codex and Mollie for backing builders who ship real things, and to Boris and the organizing crew for the room and the standard you set. Intelligence the world improves, and the world owns. That is the future I want for my kids, and the one I will keep building.

abdel

17,370 views • 1 month ago

how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour: 1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time. 2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional. 3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file. 4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer. 5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent. 6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded. 7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded. 8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge. you can watch below shoutout to Meng To for coming on The Startup Ideas Podcast (SIP) 🧃 and walking through his full workflow. if you want to use AI to actually build gorgeous designs, you'll want to use see this. watch
51:01

how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour: 1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time. 2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional. 3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file. 4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer. 5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent. 6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded. 7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded. 8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge. you can watch below shoutout to Meng To for coming on The Startup Ideas Podcast (SIP) 🧃 and walking through his full workflow. if you want to use AI to actually build gorgeous designs, you'll want to use see this. watch

GREG ISENBERG

507,444 views • 2 months ago

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!
0:53

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Akshay 🚀

86,515 views • 2 months ago