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.

Marlow might be the game-changer for vibe coding. I gave the same insane space startup prompt to Claude and Marlow: Marlow → cinematic visuals, richer depth, smooth motion, interactive sections, and noticeably faster page-to-page navigation once the site was generated Claude → polished and clean, but the overall experience... show more

Dhaval Makwana

44,504 subscribers

66,572 views • 18 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I gave the same “build me a fully functional Notion-level SaaS workspace” prompt to Marlow, Base44, and Lovable. Base44 → built it, but the result felt more basic, and page-to-page navigation was slower. Lovable → gave me no output on the trial and asked me to add credits. Marlow → built the strongest SaaS of the three, with working interactions, project management, customization, 10 aesthetic themes, and noticeably faster navigation across the generated app. That speed advantage comes from Marlow running the app on your own VM. And it still did all of this on the trial plan. Same prompt. Very different results. See prompt in the comments ↓

I gave the same “build me a fully functional Notion-level SaaS workspace” prompt to Marlow, Base44, and Lovable. Base44 → built it, but the result felt more basic, and page-to-page navigation was slower. Lovable → gave me no output on the trial and asked me to add credits. Marlow → built the strongest SaaS of the three, with working interactions, project management, customization, 10 aesthetic themes, and noticeably faster navigation across the generated app. That speed advantage comes from Marlow running the app on your own VM. And it still did all of this on the trial plan. Same prompt. Very different results. See prompt in the comments ↓

Jaynit Makwana

64,307 views • 18 days ago

lol...Kimi really cooked Claude Design tested the same prompt on both Kimi K2.6 and Claude Design, and these are the outputs not to mention Kimi is 7x cheaper and 100% open source... see prompt in the comments👇

lol...Kimi really cooked Claude Design tested the same prompt on both Kimi K2.6 and Claude Design, and these are the outputs not to mention Kimi is 7x cheaper and 100% open source... see prompt in the comments👇

Farhan

325,629 views • 3 months ago

Same prompt. GPT-5.6 Sol vs Opus 5. All in Three.js. Opus produced the better raw visuals. The ocean, waves and atmosphere look noticeably richer. But it also: → cost ~10x more → took much longer → needed an extra prompt just to fix the camera controls Sol got surprisingly close on the first attempt, much faster and far cheaper. Opus wins visual fidelity. Sol wins the actual engineering test.

Same prompt. GPT-5.6 Sol vs Opus 5. All in Three.js. Opus produced the better raw visuals. The ocean, waves and atmosphere look noticeably richer. But it also: → cost ~10x more → took much longer → needed an extra prompt just to fix the camera controls Sol got surprisingly close on the first attempt, much faster and far cheaper. Opus wins visual fidelity. Sol wins the actual engineering test.

Token Gremlin

12,867 views • 9 days ago

🚨 Ox Alpha might actually be AGI I gave it and GPT-5.6 Sol (Ultra) the exact same prompt to build a website with cursor-reactive magnetic motion. Ox Alpha delivered faster and, in this test, far more accurately. the motion feels better, the graphics look cleaner, and even the font choices are way ahead of what GPT-5.6 Sol gave me. I’ll drop the exact prompt I used in the comments for anyone who wants to try it.

🚨 Ox Alpha might actually be AGI I gave it and GPT-5.6 Sol (Ultra) the exact same prompt to build a website with cursor-reactive magnetic motion. Ox Alpha delivered faster and, in this test, far more accurately. the motion feels better, the graphics look cleaner, and even the font choices are way ahead of what GPT-5.6 Sol gave me. I’ll drop the exact prompt I used in the comments for anyone who wants to try it.

m0h

53,425 views • 9 days ago

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Alex Finn

40,955 views • 11 months ago

Same prompt. Same story. Two models. One intense car chase. I put Seedance 2.0 and Seedance 2.5 on CapCut through the exact same 30-second Hollywood style chase sequence to compare vehicle physics, camera stability, motion blur, character consistency, dialogue, and overall cinematic realism. No prompt changes. No shortcuts. Just a direct side-by-side test to see how much the generation quality has evolved. Which version feels more realistic to you? CapCut

Same prompt. Same story. Two models. One intense car chase. I put Seedance 2.0 and Seedance 2.5 on CapCut through the exact same 30-second Hollywood style chase sequence to compare vehicle physics, camera stability, motion blur, character consistency, dialogue, and overall cinematic realism. No prompt changes. No shortcuts. Just a direct side-by-side test to see how much the generation quality has evolved. Which version feels more realistic to you? CapCut

Natalia

35,789 views • 25 days ago

This is the best 2026 AI workflow for turning game ideas into playable prototypes: GPT Image 2.0 → reference image + tileset Codex + GPT-5.5 → my custom prompt Result → playable browser prototype I generated the Cozy Island Farm concept, turned the same visual direction into clean technical assets, then used one complete prompt to make it playable. Comment “Cozy Island Farm” and I’ll send you my custom prompt.

This is the best 2026 AI workflow for turning game ideas into playable prototypes: GPT Image 2.0 → reference image + tileset Codex + GPT-5.5 → my custom prompt Result → playable browser prototype I generated the Cozy Island Farm concept, turned the same visual direction into clean technical assets, then used one complete prompt to make it playable. Comment “Cozy Island Farm” and I’ll send you my custom prompt.

Givros

32,683 views • 3 months ago

claude opus 4.5 is finally here, so we tested it against gemini 3 to see which one is the better at vibe coding we took a new startup idea and went from idea to landing page to prototype to ad creative in one sitting. you also see how The Boring Marketer uses claude skills to get the most out of claude opus 4.5 (and how you can do the same). if you’re wondering whether opus 4.5 is worth using, this 1hr tutorial will help you decide and learn how to get the most from it.

claude opus 4.5 is finally here, so we tested it against gemini 3 to see which one is the better at vibe coding we took a new startup idea and went from idea to landing page to prototype to ad creative in one sitting. you also see how The Boring Marketer uses claude skills to get the most out of claude opus 4.5 (and how you can do the same). if you’re wondering whether opus 4.5 is worth using, this 1hr tutorial will help you decide and learn how to get the most from it.

GREG ISENBERG

84,982 views • 9 months ago

Everyone complains that Claude gives bad answers. Anthropic just showed that the model usually isn't the problem. In this 24-minute Prompting 101 workshop, Hannah Morgan and Christian Ryan take a weak prompt and rebuild it step by step: → weak prompt → richer context → sharper instructions → much better output With Opus 4.8, prompt quality matters more than ever. Most people still type one vague sentence and then blame the AI for what comes back. This workshop shows you how to talk to Claude the way it was actually built to be used. Watch it and save yourself hours of trial and error on your next prompt.

Everyone complains that Claude gives bad answers. Anthropic just showed that the model usually isn't the problem. In this 24-minute Prompting 101 workshop, Hannah Morgan and Christian Ryan take a weak prompt and rebuild it step by step: → weak prompt → richer context → sharper instructions → much better output With Opus 4.8, prompt quality matters more than ever. Most people still type one vague sentence and then blame the AI for what comes back. This workshop shows you how to talk to Claude the way it was actually built to be used. Watch it and save yourself hours of trial and error on your next prompt.

mireia.

67,827 views • 28 days ago

I've been testing Seedance 2.5 inside LovartAI and it's easily one of the biggest improvements I've seen for cinematic AI generation The motion stays smooth, characters remain consistent across scenes, and even long shots hold together without falling apart What stood out most wasn't just the final result. I could generate, refine, and edit everything in the same workspace instead of switching between tools. From writing the prompt to polishing the output, the entire workflow felt much faster Check the workflow in the video

I've been testing Seedance 2.5 inside LovartAI and it's easily one of the biggest improvements I've seen for cinematic AI generation The motion stays smooth, characters remain consistent across scenes, and even long shots hold together without falling apart What stood out most wasn't just the final result. I could generate, refine, and edit everything in the same workspace instead of switching between tools. From writing the prompt to polishing the output, the entire workflow felt much faster Check the workflow in the video

Amira Zairi

18,270 views • 24 days ago

Same cozy pasta recipe. Same 30-second cinematic cooking vlog. I put Seedance 2.0 and Seedance 2.5 on CapCut through the exact same cooking sequence to compare food preparation, hand movements, steam, camera motion, lighting, character consistency, and overall cinematic realism. No prompt changes. No shortcuts. Just a direct side by side test to see how much the generation quality has evolved. CapCut Which one is your favorite?

Same cozy pasta recipe. Same 30-second cinematic cooking vlog. I put Seedance 2.0 and Seedance 2.5 on CapCut through the exact same cooking sequence to compare food preparation, hand movements, steam, camera motion, lighting, character consistency, and overall cinematic realism. No prompt changes. No shortcuts. Just a direct side by side test to see how much the generation quality has evolved. CapCut Which one is your favorite?

Soulful Ai

45,177 views • 24 days ago

ONE PROMPT AND ONE BUTTON NOW BUILDS A FULL SYSTEM, DATABASE, BACKEND, AND FRONTEND INCLUDED Most people still picture AI as something you ask questions to, then copy the answer into your own code by hand. A builder wired Claude into Obsidian through MCP instead, so a single written prompt becomes the actual spec for the system. Claude breaks that prompt into database schema, UI components, and API endpoints on its own, then writes, runs, and fixes the code until it actually works. MCP is what makes this possible, it lets the agent see the filesystem, installed packages, and running services before it starts building anything. The output isn't a code snippet sitting in a chat window, it's a live local app running on its own server, ready to open in a browser. What used to need a backend developer, a DevOps engineer, and two weeks now finishes in under fifteen minutes. See the full architecture and prompt structure below👇

ONE PROMPT AND ONE BUTTON NOW BUILDS A FULL SYSTEM, DATABASE, BACKEND, AND FRONTEND INCLUDED Most people still picture AI as something you ask questions to, then copy the answer into your own code by hand. A builder wired Claude into Obsidian through MCP instead, so a single written prompt becomes the actual spec for the system. Claude breaks that prompt into database schema, UI components, and API endpoints on its own, then writes, runs, and fixes the code until it actually works. MCP is what makes this possible, it lets the agent see the filesystem, installed packages, and running services before it starts building anything. The output isn't a code snippet sitting in a chat window, it's a live local app running on its own server, ready to open in a browser. What used to need a backend developer, a DevOps engineer, and two weeks now finishes in under fifteen minutes. See the full architecture and prompt structure below👇

wast3

20,348 views • 1 month ago

There is a strategy for Claude Max users that will 3-5X productivity and vibe coding learning curve. Which most vibe coders don't utilize! Most people using Claude Code just sit and watch the terminal while their prompt cooks. That’s dead time. If you’re on Claude Max, you’re paying for parallel capacity you’re probably not using fully. And tokens get wasted. Here’s a methodology to fix that and boost the way you use Claude forever: The Setup & Workflow 1. Add the repos you’re actively working on to your workspace from your IDE 2. Click “new terminal” and open 3-4 terminal instances, each pointed at a different project 3. Toggle between them on the right side of your terminal panel 4. When one terminal is cooking a prompt, look at the others 5. Use the time Claude is working to prompt the next project 6. Continuously rotate and ship across 3-4 projects like this 7. Use your tokens effectively, build more, learn faster The Result You ship 3-4 projects simultaneously. You burn through your token allocation on actual output instead of letting it sit unused. You learn faster because you’re getting more reps in the same amount of time, too. As long as you work on different projects at the same time like this, it will only be a boost in productivity, with no chance for code to get spaghetti. In the video, you can see where to find add workspace, run new terminal, and change between terminals:

There is a strategy for Claude Max users that will 3-5X productivity and vibe coding learning curve. Which most vibe coders don't utilize! Most people using Claude Code just sit and watch the terminal while their prompt cooks. That’s dead time. If you’re on Claude Max, you’re paying for parallel capacity you’re probably not using fully. And tokens get wasted. Here’s a methodology to fix that and boost the way you use Claude forever: The Setup & Workflow 1. Add the repos you’re actively working on to your workspace from your IDE 2. Click “new terminal” and open 3-4 terminal instances, each pointed at a different project 3. Toggle between them on the right side of your terminal panel 4. When one terminal is cooking a prompt, look at the others 5. Use the time Claude is working to prompt the next project 6. Continuously rotate and ship across 3-4 projects like this 7. Use your tokens effectively, build more, learn faster The Result You ship 3-4 projects simultaneously. You burn through your token allocation on actual output instead of letting it sit unused. You learn faster because you’re getting more reps in the same amount of time, too. As long as you work on different projects at the same time like this, it will only be a boost in productivity, with no chance for code to get spaghetti. In the video, you can see where to find add workspace, run new terminal, and change between terminals:

Meta Alchemist

82,000 views • 7 months ago

I made Claude compete against itself. The smartest model does not automatically make the best agent. To prove it, I took the same Opus 4.6 model, initial prompt, and empty repo and but it inside two different coding harnesses: Claude Code vs. Factory Droid. The task: clone Excalidraw from scratch, inspect the original in a browser, implement its key interactions, and verify the result. Factory Droid: 8 minutes, 20 tool calls, $1.60 Claude Code: 19 minutes, 40 tool calls, $1.87 The only difference was the harness. Get Free Factory credits here:

I made Claude compete against itself. The smartest model does not automatically make the best agent. To prove it, I took the same Opus 4.6 model, initial prompt, and empty repo and but it inside two different coding harnesses: Claude Code vs. Factory Droid. The task: clone Excalidraw from scratch, inspect the original in a browser, implement its key interactions, and verify the result. Factory Droid: 8 minutes, 20 tool calls, $1.60 Claude Code: 19 minutes, 40 tool calls, $1.87 The only difference was the harness. Get Free Factory credits here:

Sarah Chieng

76,824 views • 9 days ago

Fresh off the launch of Opus 5, Claude Code creator Boris Cherny (Boris Cherny) joins YC's Diana at Startup School 2026 to talk about what the newest models can do, how Claude Code came to be, and what it means to build products when the underlying capabilities keep accelerating. 00:07 — What Makes Opus 5 Different 02:06 — Solving Prompt Injection 03:21 — Why Claude Code Deleted 80% of Its System Prompt 06:37 — Press Delete on Your AI Product 07:20 — How to Rebuild Your System Prompt 10:30 — Product Overhang and “Unhobbling” AI 14:26 — Give Claude Harder Problems 19:32 — Prompt Engineering Is Changing 21:57 — The Two-Week Claude Code Prompt 24:42 — Running Thousands of AI Agents 30:15 — Coding Is (Almost) Solved 32:20 — What Every CS Student Should Still Learn Anthropic Claude

Fresh off the launch of Opus 5, Claude Code creator Boris Cherny (Boris Cherny) joins YC's Diana at Startup School 2026 to talk about what the newest models can do, how Claude Code came to be, and what it means to build products when the underlying capabilities keep accelerating. 00:07 — What Makes Opus 5 Different 02:06 — Solving Prompt Injection 03:21 — Why Claude Code Deleted 80% of Its System Prompt 06:37 — Press Delete on Your AI Product 07:20 — How to Rebuild Your System Prompt 10:30 — Product Overhang and “Unhobbling” AI 14:26 — Give Claude Harder Problems 19:32 — Prompt Engineering Is Changing 21:57 — The Two-Week Claude Code Prompt 24:42 — Running Thousands of AI Agents 30:15 — Coding Is (Almost) Solved 32:20 — What Every CS Student Should Still Learn Anthropic Claude

Y Combinator

85,554 views • 1 month ago

My AI made Shopify pages are getting better and better everyday Here’s an example of a Shopify section I built with the reference page and the result on my store 👇 Guide: To make good AI landing pages, you need to use the same method as making good AI UGC or AI product images you have to take something that's already good as a reference for Claude/gemini to analyze and adapt for your product/brand for now you can't adapt full landing pages to your product because the Claude context gets bloated fast and you get poor output. Listicles are the only kind of page you can "one shot" with Claude. But Product pages are another story Analyze an existing page and adapting it to your product section by section is the way to go. The results are 10x better. here's an example (on the video): 1- I found this good product section from im8's product page. I screen-recorded the section on both desktop and mobile, going through the animations to capture the dynamism that a screenshot wouldn’t show. Then I asked Claude Web or Gemini to analyze the recording and produce a very detailed report. Full prompt is on my TG channel, it's quite long. 2- then ask Claude (inside your Shopify brand project folder): "I have a detailed UI/UX specification document for a product page section I want to adapt to my product. Recreate this exactly on Shopify as a section template and adapt it to [name of the product] using the brand guidelines" (paste the result prompt from step 1 ). 3- you will have your section ready after 3-4 minutes. you'll probably have to change a few things. spacing, small visual bugs, price not appearing correctly. it will take you 5 minutes maximum. 4- then you can ask Claude to make 4 different variations of the section using different designs and pick the best one using this prompt: "Create 4 design variations of this section. Keep the content and layout structure identical across all, only vary the visual treatment (color usage, typography hierarchy, spacing, component styling). I will choose the one I like the most." after that you have a pretty good section, and you can do the process again for all sections of the page. The less complex the section, the faster the process will be. note: I know the AI result is not perfect, but it's pretty impressive imo and it will only get better.

Olivier

84,679 views • 5 months ago

Same prompt. Same settings. Two distinct results from Pollo AI—one Coca-Cola commercial, two creative paths. MiniMax H3 leans natural and polished, while Seedance 2.0 leans cinematic with a bold visual edge. The model you choose shapes the final look as much as the prompt itself. Already looking ahead—can’t wait for Seedance 2.5 to go live on Pollo AI and see how far this can go. For your ad creatives, which would you pick—MiniMax H3 or Seedance 2.0?

Same prompt. Same settings. Two distinct results from Pollo AI—one Coca-Cola commercial, two creative paths. MiniMax H3 leans natural and polished, while Seedance 2.0 leans cinematic with a bold visual edge. The model you choose shapes the final look as much as the prompt itself. Already looking ahead—can’t wait for Seedance 2.5 to go live on Pollo AI and see how far this can go. For your ad creatives, which would you pick—MiniMax H3 or Seedance 2.0?

George

103,923 views • 27 days ago

I gave Wan3.0 an 18-page PDF and it generated this entire 30-second commercial in one run. The document contained an original character, fictional product, location, visual direction and full story. I uploaded it directly to Wan3.0 through WonderClip. The result is honestly insane: > No separate AI clips. > No stitching. The character consistency, lighting, product details and overall realism are insane. Watch the full result

I gave Wan3.0 an 18-page PDF and it generated this entire 30-second commercial in one run. The document contained an original character, fictional product, location, visual direction and full story. I uploaded it directly to Wan3.0 through WonderClip. The result is honestly insane: > No separate AI clips. > No stitching. The character consistency, lighting, product details and overall realism are insane. Watch the full result

Orikan

78,139 views • 13 days ago

This is our second head-to-head test between Kling 3.0 and Seedance 2.0. This time, we pushed both models further, including dialogue-driven Sci-fi comedy shots and even a singing scene. Every single shot was generated using: • The exact same base image • The exact same prompt • No re-generate • No second attempt • No prompt refinements. What you see is the pure first output from each model under identical conditions. So… which one performs better? Seedance 2.0 generated by Ilham Setyawan on BytePlus

This is our second head-to-head test between Kling 3.0 and Seedance 2.0. This time, we pushed both models further, including dialogue-driven Sci-fi comedy shots and even a singing scene. Every single shot was generated using: • The exact same base image • The exact same prompt • No re-generate • No second attempt • No prompt refinements. What you see is the pure first output from each model under identical conditions. So… which one performs better? Seedance 2.0 generated by Ilham Setyawan on BytePlus

Dinda Prasetyo

196,658 views • 6 months ago