Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Kimi K2.6 just cooked Claude on design 😭 Same prompt. Completely different output. I asked both to build a cinematic, scroll-driven indie game page. Dark. Editorial. Premium. Here's the exact prompt and what happened 👇

Muhammad Ayan

69,227 subscribers

161,823 views • 3 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How I built with Claude 👇 1. Prompt: "Build a storytelling website where each scroll section reveals a new chapter with fluid color transitions" 2. Use Three.js for the painted texture background that reacts to cursor 3. Prompt: "Add GSAP ScrollTrigger so each section animates in as a cinematic scene" 4. Use Lenis.js for that buttery smooth scroll that premium sites have

How I built with Claude 👇 1. Prompt: "Build a storytelling website where each scroll section reveals a new chapter with fluid color transitions" 2. Use Three.js for the painted texture background that reacts to cursor 3. Prompt: "Add GSAP ScrollTrigger so each section animates in as a cinematic scene" 4. Use Lenis.js for that buttery smooth scroll that premium sites have

FHILY👑

326,884 views • 3 months ago

How I built with Claude 👇 1. Prompt: "Build a storytelling website where each scroll section reveals a new chapter with fluid color transitions" 2. Use Three.js for the painted texture background that reacts to cursor 3. Prompt: "Add GSAP ScrollTrigger so each section animates in as a cinematic scene" 4. Use Lenis.js for that buttery smooth scroll that premium sites have

How I built with Claude 👇 1. Prompt: "Build a storytelling website where each scroll section reveals a new chapter with fluid color transitions" 2. Use Three.js for the painted texture background that reacts to cursor 3. Prompt: "Add GSAP ScrollTrigger so each section animates in as a cinematic scene" 4. Use Lenis.js for that buttery smooth scroll that premium sites have

FHILY👑

345,841 views • 2 months ago

Everyone says “Gemini 3 can make games.” So we tested it — with a Metal Slug-style prompt on both Gemini and Gambo. Same input. Completely different output. Here’s the result. #gemini3 #gemini_for_game

Everyone says “Gemini 3 can make games.” So we tested it — with a Metal Slug-style prompt on both Gemini and Gambo. Same input. Completely different output. Here’s the result. #gemini3 #gemini_for_game

gambo.ai

96,044 views • 9 months ago

Hey... so... Claude Code is really good at design?? 👀 This was a ONE SHOT PROMPT. 🤯 We always asked Lovable to build "Design System" pages for our apps and they were always meh. We asked Claude Code to take a swing at it just based on our logo, a font, and brand colors. This is... really, really good for a one-shot prompt.

Jason Zook

102,686 views • 5 months ago

Kimi K3 vs Claude Fables 5 Two models walked into a kitchen… and somehow made two completely different cookies. Which one are you taking a bite of? Prompt in the threads. 👇

Kimi K3 vs Claude Fables 5 Two models walked into a kitchen… and somehow made two completely different cookies. Which one are you taking a bite of? Prompt in the threads. 👇

Flowith

84,428 views • 27 days ago

Look at the difference the tool AND the prompt make. Bad generator + lazy prompt: stiff movement, dead eyes, that obvious "AI look" everyone scrolls past. Seedance + a detailed, structured prompt: natural movement, real lighting, real pacing — looks like it came off an actual production shoot. Same product photo. Completely different result. It's not one or the other. You need the right tool AND the right prompt to get agency-level output. Ready to see the exact setup? Check the comments 👇

Look at the difference the tool AND the prompt make. Bad generator + lazy prompt: stiff movement, dead eyes, that obvious "AI look" everyone scrolls past. Seedance + a detailed, structured prompt: natural movement, real lighting, real pacing — looks like it came off an actual production shoot. Same product photo. Completely different result. It's not one or the other. You need the right tool AND the right prompt to get agency-level output. Ready to see the exact setup? Check the comments 👇

Stijn Feijen

11,813 views • 1 month ago

Can you tell the difference? I tested the exact same prompt, same scene, and identical luxury perfume commercial in Seedance 2.0 4k on EaseMate AI_Official , comparing 4K and 1080p output. From the Mediterranean lighting and glass reflections to skin texture and cinematic depth of field, the difference is clear when viewed side by side. Which version would you choose for your next commercial—4K or 1080p? 👇 Prompt in the comments.

Can you tell the difference? I tested the exact same prompt, same scene, and identical luxury perfume commercial in Seedance 2.0 4k on EaseMate AI_Official , comparing 4K and 1080p output. From the Mediterranean lighting and glass reflections to skin texture and cinematic depth of field, the difference is clear when viewed side by side. Which version would you choose for your next commercial—4K or 1080p? 👇 Prompt in the comments.

Jessica Collins

467,998 views • 1 month ago

Seedance 2.5 is officially available on CapCut. To test it, I used the same cinematic prompt in Seedance 2.5 and Seedance 2.0 and compared the results side by side. With support for up to 30-second generation, 50 reference materials, infinite scene extension, and frame-precise editing, Seedance 2.5 gives creators much more control over complex cinematic videos. Same prompt. Same settings. Watch both generations and see how they compare in prompt accuracy, motion quality, and cinematic consistency.

Seedance 2.5 is officially available on CapCut. To test it, I used the same cinematic prompt in Seedance 2.5 and Seedance 2.0 and compared the results side by side. With support for up to 30-second generation, 50 reference materials, infinite scene extension, and frame-precise editing, Seedance 2.5 gives creators much more control over complex cinematic videos. Same prompt. Same settings. Watch both generations and see how they compare in prompt accuracy, motion quality, and cinematic consistency.

Zara

24,291 views • 16 days ago

Claude feels kinda overhyped tbh. I tested the same website design prompt on both Gemini and Claude many times. And every time Claude’s output wasn’t even close to the original. Meanwhile, Gemini got almost identical results, and after a few tweaks, it hit ~99% accuracy. Makes me wonder… maybe models just perform better on ecosystems they’re trained closer to? 🤔 Either way, Gemini is seriously outperforming in frontend dev right now. Remix:

Claude feels kinda overhyped tbh. I tested the same website design prompt on both Gemini and Claude many times. And every time Claude’s output wasn’t even close to the original. Meanwhile, Gemini got almost identical results, and after a few tweaks, it hit ~99% accuracy. Makes me wonder… maybe models just perform better on ecosystems they’re trained closer to? 🤔 Either way, Gemini is seriously outperforming in frontend dev right now. Remix:

The Bugged Dev

31,645 views • 4 months ago

FABLE 5 + HIGGSFIELD TURN A $35,000 ANIMATED SITE INTO A ONE-SESSION, $12 BUILD. HERE'S EXACTLY HOW. a studio runs this across four people and three weeks. you run it across one chat window and one afternoon. THE BUILD, STAGE BY STAGE: STAGE 1 - THE CONCEPT Claude reads your brief and scripts the scroll before a line of code exists - what the visitor feels at second 3, 15, 40. prompt: "read this brief. script the scroll beat by beat, then scaffold the project with GSAP ScrollTrigger + Lenis." STAGE 2 - THE VISUALS (Higgsfield) every hero shot, transition, and ambient loop comes out of 30+ generative models - matched to the story, not pulled from a stock library. prompt: "generate the hero sting and one b-roll clip per section. 3-5s, high-res, cinematic." STAGE 3 - THE MOTION (Claude Code) Claude writes the ScrollTrigger timelines and Lenis smooth-scroll, extracts frames, optimizes every asset. zero hand-coded keyframes. prompt: "wire the scroll: pin the hero, scrub the video, reveal each section on scroll. keep it 60fps on mobile." STAGE 4 - THE POLISH six cinematic effects baked in, no config: film grain, particles, vignette, glass cards, color tints, scroll pacing. prompt: "bake in the cinematic layer, then QA load speed, mobile breakpoints, and whether the scroll actually lands - rewrite what doesn't." CONNECT HIGGSFIELD (MCP): add it as a custom connector in Claude Code: mcp_servers: higgsfield: url: " one OAuth flow. Claude generates and pulls clips directly - no exporting by hand. THE MATH: → what a studio charges: $6,000-$35,000+ → what it costs you: a Claude sub + a few dollars of Higgsfield credits → what it takes: 4 people + 3 weeks → 1 operator + 1 session the pipeline was the moat. it just became four prompts. Follow me, comment "MATH" and I'll send you the full step-by-step Playbook. full breakdown in the article 👇

FABLE 5 + HIGGSFIELD TURN A $35,000 ANIMATED SITE INTO A ONE-SESSION, $12 BUILD. HERE'S EXACTLY HOW. a studio runs this across four people and three weeks. you run it across one chat window and one afternoon. THE BUILD, STAGE BY STAGE: STAGE 1 - THE CONCEPT Claude reads your brief and scripts the scroll before a line of code exists - what the visitor feels at second 3, 15, 40. prompt: "read this brief. script the scroll beat by beat, then scaffold the project with GSAP ScrollTrigger + Lenis." STAGE 2 - THE VISUALS (Higgsfield) every hero shot, transition, and ambient loop comes out of 30+ generative models - matched to the story, not pulled from a stock library. prompt: "generate the hero sting and one b-roll clip per section. 3-5s, high-res, cinematic." STAGE 3 - THE MOTION (Claude Code) Claude writes the ScrollTrigger timelines and Lenis smooth-scroll, extracts frames, optimizes every asset. zero hand-coded keyframes. prompt: "wire the scroll: pin the hero, scrub the video, reveal each section on scroll. keep it 60fps on mobile." STAGE 4 - THE POLISH six cinematic effects baked in, no config: film grain, particles, vignette, glass cards, color tints, scroll pacing. prompt: "bake in the cinematic layer, then QA load speed, mobile breakpoints, and whether the scroll actually lands - rewrite what doesn't." CONNECT HIGGSFIELD (MCP): add it as a custom connector in Claude Code: mcp_servers: higgsfield: url: " one OAuth flow. Claude generates and pulls clips directly - no exporting by hand. THE MATH: → what a studio charges: $6,000-$35,000+ → what it costs you: a Claude sub + a few dollars of Higgsfield credits → what it takes: 4 people + 3 weeks → 1 operator + 1 session the pipeline was the moat. it just became four prompts. Follow me, comment "MATH" and I'll send you the full step-by-step Playbook. full breakdown in the article 👇

ZEUS⚡️

47,174 views • 1 month ago

We tested a lot of design skills in Codex and other AI agents. They fix the old AI slop. But they often create a new one: the “taste skill look.” - Same premium sections. - Same editorial typography. - Same generated-design smell. Open Design does not rely on one taste prompt. It combines skills, systems, critique loops, and local harnesses to make AI pages feel less generated and more designed. This page was generated directly in Open Design.

We tested a lot of design skills in Codex and other AI agents. They fix the old AI slop. But they often create a new one: the “taste skill look.” - Same premium sections. - Same editorial typography. - Same generated-design smell. Open Design does not rely on one taste prompt. It combines skills, systems, critique loops, and local harnesses to make AI pages feel less generated and more designed. This page was generated directly in Open Design.

Open Design

44,061 views • 2 months ago

🚨 Everyone's talking about ChatGPT Agents. But what happens when you ask two agents to create a pitch deck? I ran the same prompt in Genspark and ChatGPT Agent. The results? Wildly different. Let me show you what happened 👇

🚨 Everyone's talking about ChatGPT Agents. But what happens when you ask two agents to create a pitch deck? I ran the same prompt in Genspark and ChatGPT Agent. The results? Wildly different. Let me show you what happened 👇

Kelsey

116,567 views • 10 months ago

Same reference image. Same prompt. Different models. I put MiniMax H3 and Seedance 2.0 head-to-head on Pollo AI to see how each handles the exact same scene. Also excited that Seedance 2.5 is coming soon on PolloAI Check it out 👇

Same reference image. Same prompt. Different models. I put MiniMax H3 and Seedance 2.0 head-to-head on Pollo AI to see how each handles the exact same scene. Also excited that Seedance 2.5 is coming soon on PolloAI Check it out 👇

Synthia

19,776 views • 14 days ago

I gave Kimi K3 and Opus 5 the exact same prompt to build a car racing game. I expected Opus 5 to take the lead. Instead, Kimi K3 finished in ~25 min for ~$8.9, while Opus 5 took 19 min and cost $14. The biggest surprise wasn’t the speed or the price. Kimi K3 built the better game. Smoother controls, better physics, and a driving experience that felt ready from the start. Opus 5 looked cleaner visually but Kimi won where it actually mattered. Nearly half the cost and the better gameplay.

I gave Kimi K3 and Opus 5 the exact same prompt to build a car racing game. I expected Opus 5 to take the lead. Instead, Kimi K3 finished in ~25 min for ~$8.9, while Opus 5 took 19 min and cost $14. The biggest surprise wasn’t the speed or the price. Kimi K3 built the better game. Smoother controls, better physics, and a driving experience that felt ready from the start. Opus 5 looked cleaner visually but Kimi won where it actually mattered. Nearly half the cost and the better gameplay.

Aman

111,571 views • 23 days ago

Grok 4.5 in Grok Build created an FPS game in under an hour. The prompt was simple. I told it to write a game design document and pull free assets from the web. Then I had it create a TODO.md with implementation phases and run a loop to build out each phase. SpaceXAI and Cursor cooked here. This model is insane.

Grok 4.5 in Grok Build created an FPS game in under an hour. The prompt was simple. I told it to write a game design document and pull free assets from the web. Then I had it create a TODO.md with implementation phases and run a loop to build out each phase. SpaceXAI and Cursor cooked here. This model is insane.

tetsuo

1,810,289 views • 1 month ago

This is wild. Higgsfield Games lets you build and deploy a full multiplayer game from a single prompt. Any genre, 2D or 3D, with characters, props, and worlds generated on the fly. Powered by Claude Fable 5. Huge W for indie devs.

This is wild. Higgsfield Games lets you build and deploy a full multiplayer game from a single prompt. Any genre, 2D or 3D, with characters, props, and worlds generated on the fly. Powered by Claude Fable 5. Huge W for indie devs.

How To Prompt

61,717 views • 2 months ago

A WEB STUDIO CHARGES $35,000 FOR AN ANIMATED SITE. THE SAME BUILD NOW COSTS $12 - CLAUDE CODE WRITES, HIGGSFIELD RENDERS. Every agency billing $100-149/hr is just three departments. Here's each one, collapsed into a single agentic session. SYSTEM 1 - THE MOTION STUDIO (Higgsfield) Cinematic clips pulled from 30+ generative models - hero shots, transitions, ambient loops. → This used to be a motion artist on retainer. Now it's a prompt. SYSTEM 2 - THE DEV TEAM (Claude Code) Scaffolds the site, writes the GSAP ScrollTrigger timelines and Lenis smooth-scroll, extracts frames, optimizes every asset. → A full scroll-driven build with zero hand-coded keyframes. SYSTEM 3 - THE DESIGN DEPT (baked-in cinematic layer) Six effects with no config: film grain, particles, vignette, glass cards, color tints, scroll pacing. → The polish that justified the invoice - now it ships by default. Three departments. One operator. One pass. What used to take a designer, a motion artist, and a developer through weeks of handoffs now runs in a single session - for a Claude subscription and a few dollars of Higgsfield credits. The studio was never the talent. It was the overhead. And the overhead just became three systems. Reply "web-site" to this post and I will send you the step-by-step Playbook 👇

A WEB STUDIO CHARGES $35,000 FOR AN ANIMATED SITE. THE SAME BUILD NOW COSTS $12 - CLAUDE CODE WRITES, HIGGSFIELD RENDERS. Every agency billing $100-149/hr is just three departments. Here's each one, collapsed into a single agentic session. SYSTEM 1 - THE MOTION STUDIO (Higgsfield) Cinematic clips pulled from 30+ generative models - hero shots, transitions, ambient loops. → This used to be a motion artist on retainer. Now it's a prompt. SYSTEM 2 - THE DEV TEAM (Claude Code) Scaffolds the site, writes the GSAP ScrollTrigger timelines and Lenis smooth-scroll, extracts frames, optimizes every asset. → A full scroll-driven build with zero hand-coded keyframes. SYSTEM 3 - THE DESIGN DEPT (baked-in cinematic layer) Six effects with no config: film grain, particles, vignette, glass cards, color tints, scroll pacing. → The polish that justified the invoice - now it ships by default. Three departments. One operator. One pass. What used to take a designer, a motion artist, and a developer through weeks of handoffs now runs in a single session - for a Claude subscription and a few dollars of Higgsfield credits. The studio was never the talent. It was the overhead. And the overhead just became three systems. Reply "web-site" to this post and I will send you the step-by-step Playbook 👇

ZEUS⚡️

173,851 views • 1 month ago

I compared MiniMax H3 and Seedance 2.0 on Pollo AI using the exact same prompt, and the results were surprisingly different. The output from MiniMax H3 feels noticeably more realistic, with natural motion, authentic facial expressions, and fewer artificial-looking details. MiniMax H3 shows how prompt refinement and model capability can significantly improve AI-generated video quality. What are your thoughts? Which version do you find more realistic?

I compared MiniMax H3 and Seedance 2.0 on Pollo AI using the exact same prompt, and the results were surprisingly different. The output from MiniMax H3 feels noticeably more realistic, with natural motion, authentic facial expressions, and fewer artificial-looking details. MiniMax H3 shows how prompt refinement and model capability can significantly improve AI-generated video quality. What are your thoughts? Which version do you find more realistic?

Theo

36,206 views • 14 days ago

Tested Muse Spark 1.2, Kimi K3, and GLM 5.2 with our FlappyBench 3 models, same prompt with the /design command. Reviewed gameplay features, UX/UI, and cost. 🔹 Kimi K3 → 9.5/10 · $0.0740 🔹 GLM 5.2 → 9/10 · $0.0480 🔹 Muse Spark 1.2 → 8/10 · $0.0187 Muse Spark 1.2 delivered a completely different game style despite being super cheap. Kimi K3 and GLM 5.2 outputs are comparable and close in cost.

Tested Muse Spark 1.2, Kimi K3, and GLM 5.2 with our FlappyBench 3 models, same prompt with the /design command. Reviewed gameplay features, UX/UI, and cost. 🔹 Kimi K3 → 9.5/10 · $0.0740 🔹 GLM 5.2 → 9/10 · $0.0480 🔹 Muse Spark 1.2 → 8/10 · $0.0187 Muse Spark 1.2 delivered a completely different game style despite being super cheap. Kimi K3 and GLM 5.2 outputs are comparable and close in cost.

Command Code

21,838 views • 12 days ago