Loading video...

Video Failed to Load

Go Home

Claude 4.6 just proved that “building apps = coding” is officially outdated. You give it context. It plans. Builds. Deploys. This is what “AI dev” actually looks like. Give this a minute.

RoundtableSpace's profile picture

0xMarioNawfal

187,739 subscribers

63,294 views • 6 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I just vibe coded a fully playable game with Verse 8 | Why Code, Just Verse 8 in minutes. Huge thanks to Rush for building it with me! > No engine. > No setup. > No infra. You just describe what you want… and it builds, deploys, and runs right away. This isn’t a demo or mockup. It’s a real game you can play right now. This is what vibe coding looks like when it actually works.
0:29

I just vibe coded a fully playable game with Verse 8 | Why Code, Just Verse 8 in minutes. Huge thanks to Rush for building it with me! > No engine. > No setup. > No infra. You just describe what you want… and it builds, deploys, and runs right away. This isn’t a demo or mockup. It’s a real game you can play right now. This is what vibe coding looks like when it actually works.

Param

25,600 views • 7 months ago

We're building a sleep agent that predicts your night before it happens. Then optimizes it while you sleep. This is what AI in health actually looks like.
0:31

We're building a sleep agent that predicts your night before it happens. Then optimizes it while you sleep. This is what AI in health actually looks like.

Matteo Franceschetti

12,320 views • 5 months ago

Two AI models just became a cheat code. Claude 4.6 thinks. Minimax M2.5 executes. That’s the split. Claude: • 1M token context window • Reads entire codebases • Builds full strategies • Reviews complex work Minimax: • 20x cheaper than flagship models • 80%+ on real coding benchmarks • 37% faster than older versions • Built for agent workflows Here’s the play: 1. Claude plans the system. 2. Minimax builds it. 3. Claude reviews it. 4. Minimax refines it. Strategy → Execution → Review → Scale. That loop is unfair.
8:07

Two AI models just became a cheat code. Claude 4.6 thinks. Minimax M2.5 executes. That’s the split. Claude: • 1M token context window • Reads entire codebases • Builds full strategies • Reviews complex work Minimax: • 20x cheaper than flagship models • 80%+ on real coding benchmarks • 37% faster than older versions • Built for agent workflows Here’s the play: 1. Claude plans the system. 2. Minimax builds it. 3. Claude reviews it. 4. Minimax refines it. Strategy → Execution → Review → Scale. That loop is unfair.

Julian Goldie SEO

17,034 views • 6 months ago

POV: You just found a designer who actually gets it. This is what good design looks like
0:27

POV: You just found a designer who actually gets it. This is what good design looks like

Sameer

12,876 views • 6 months ago

PixiJS Skills are live! Give your AI coding agent better context for WebGL/WebGPU builds (games, interactive apps, data viz, and more) Perfect for #vibejam if you want to vibe code a game this weekend Install: npx skills add
0:27

PixiJS Skills are live! Give your AI coding agent better context for WebGL/WebGPU builds (games, interactive apps, data viz, and more) Perfect for #vibejam if you want to vibe code a game this weekend Install: npx skills add

PixiJS

23,454 views • 4 months ago

This is what vibe coding actually looks like in 2026: a capybara food delivery game, built solo in 14 days with zero game dev experience.
0:48

This is what vibe coding actually looks like in 2026: a capybara food delivery game, built solo in 14 days with zero game dev experience.

Big Brain AI

40,785 views • 3 months ago

This is Claude Sonnet 4.6: our most capable Sonnet model yet. It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. It also features a 1M token context window in beta.
1:29

This is Claude Sonnet 4.6: our most capable Sonnet model yet. It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. It also features a 1M token context window in beta.

Claude

7,603,592 views • 6 months ago

What explanstion will you give to Presidente, will you tell him that what he saw is not what it looks like?
1:04

What explanstion will you give to Presidente, will you tell him that what he saw is not what it looks like?

Velvet Storm

13,679 views • 5 months ago

R.I.P App Developers! You can build apps in minutes without knowing coding. This new AI App Builder handles everything, you just describe, and it builds everything from scratch. Here’s how it works:
0:22

R.I.P App Developers! You can build apps in minutes without knowing coding. This new AI App Builder handles everything, you just describe, and it builds everything from scratch. Here’s how it works:

Aakash Kanojiya

54,009 views • 1 year ago

Someone vibe coded a 3D city where every GitHub developer is a building. It is called Git city where more commits means taller building and more repos means wider base. Light windows shows that you were active recently. You can even fly through the entire city and find your building just by searching your username. And honestly, this is what vibe coding actually looks like at its best.
1:30

Someone vibe coded a 3D city where every GitHub developer is a building. It is called Git city where more commits means taller building and more repos means wider base. Light windows shows that you were active recently. You can even fly through the entire city and find your building just by searching your username. And honestly, this is what vibe coding actually looks like at its best.

Prasenjit

132,872 views • 6 months ago

Most AI coding tools still act like “one brain does everything.” Oh My Open Code flips that idea — it orchestrates multiple models like a real engineering team. Claude plans, Gemini builds, GPT reviews… all in parallel.
5:23

Most AI coding tools still act like “one brain does everything.” Oh My Open Code flips that idea — it orchestrates multiple models like a real engineering team. Claude plans, Gemini builds, GPT reviews… all in parallel.

Mervin Praison

39,392 views • 8 months ago

This Is What It Looks Like When You Give Zionists Everything They Want "Zionism is a failed experiment. How do we know? Look around you. " Reading by Tim Foley.
2:48

This Is What It Looks Like When You Give Zionists Everything They Want "Zionism is a failed experiment. How do we know? Look around you. " Reading by Tim Foley.

Caitlin Johnstone

48,528 views • 5 months ago

WTF Dude... this is like PDF parsing on steroids, NGL. 🤯 OpenDataLoader PDF is a free, open-source PDF parser that converts PDFs into AI-ready Markdown, JSON, and HTML. It can also use OCR for scanned PDFs and handle complex content like tables, formulas, and charts. Perfect for building RAG pipelines, AI agents, search systems, and other AI apps that need to actually understand PDF documents :) Follow me for more amazing AI, Coding & Web Dev insights 💎
0:32

WTF Dude... this is like PDF parsing on steroids, NGL. 🤯 OpenDataLoader PDF is a free, open-source PDF parser that converts PDFs into AI-ready Markdown, JSON, and HTML. It can also use OCR for scanned PDFs and handle complex content like tables, formulas, and charts. Perfect for building RAG pipelines, AI agents, search systems, and other AI apps that need to actually understand PDF documents :) Follow me for more amazing AI, Coding & Web Dev insights 💎

Ram Maheshwari

26,115 views • 7 days ago

Claude 4.6 and Gemini 3 together are wild. This is the new AI product stack 🧵 Claude 4.6: – 1M token context window – Reads entire codebases – Handles multi-step workflows – Connects APIs cleanly – Automates backend logic Gemini 3: – Multimodal (text, image, video, audio) – Designs UI + layout – Structures landing pages – Powers AI-native dev (AntiGravity IDE) Here’s the play: 1. Prompt Gemini to design the landing page. 2. Take output to Claude. 3. Prompt Claude to build backend automation. Result? Lead form → email list → CRM tag → welcome sequence. All built from prompts. This is what a 2-person AI team looks like.
8:03

Claude 4.6 and Gemini 3 together are wild. This is the new AI product stack 🧵 Claude 4.6: – 1M token context window – Reads entire codebases – Handles multi-step workflows – Connects APIs cleanly – Automates backend logic Gemini 3: – Multimodal (text, image, video, audio) – Designs UI + layout – Structures landing pages – Powers AI-native dev (AntiGravity IDE) Here’s the play: 1. Prompt Gemini to design the landing page. 2. Take output to Claude. 3. Prompt Claude to build backend automation. Result? Lead form → email list → CRM tag → welcome sequence. All built from prompts. This is what a 2-person AI team looks like.

Julian Goldie SEO

25,802 views • 6 months ago

This 20-minute podcast with Head of Multi-Agents at Anthropic will teach you more about vibe coding with Claude than 100 YouTube video guides. Bookmark it & give it 20 minutes today. It will change the way you build with Claude forever.
18:39

This 20-minute podcast with Head of Multi-Agents at Anthropic will teach you more about vibe coding with Claude than 100 YouTube video guides. Bookmark it & give it 20 minutes today. It will change the way you build with Claude forever.

Movez

38,719 views • 4 months ago

Okay this is actually insane. OpenArt just dropped vibe directing and the quality doesn't look like typical AI video. You just tell what you want in chat and it builds the whole thing. 5 wild examples:
1:30

Okay this is actually insane. OpenArt just dropped vibe directing and the quality doesn't look like typical AI video. You just tell what you want in chat and it builds the whole thing. 5 wild examples:

Nav Toor

262,109 views • 2 months ago

That's me... and my weekend looks like this. If you had to give this video a caption, what would it be?
0:42

That's me... and my weekend looks like this. If you had to give this video a caption, what would it be?

RUTU

47,384 views • 1 month ago

Being broke in 2026 is a choice. And this girl just brutally exposed exactly why. This girl just exposed one of the biggest cheats in 2026. She’s building real mobile apps and putting them on the App Store… …without knowing how to code God damn it. It called Vibecoding. You just describe what you want in plain English, open newly . app, and the AI builds the entire thing for you. No coding. No developers. No massive budget Just vibes + AI. While most of Crypto Twitter is still crying about the job market and gambling on shitcoins… This girl is out here creating and shipping actual apps like it’s nothing. This is the new meta. Vibecoding is going to create a wave of new millionaires who barely know what a line of code looks like. We are ridiculously early. Most people will watch this and still stay stuck. The dangerous ones are already experimenting. Follow me for more raw breakdowns on vibecoding, AI money printers, and faceless cash machines that actually work in 2026.
1:08

Being broke in 2026 is a choice. And this girl just brutally exposed exactly why. This girl just exposed one of the biggest cheats in 2026. She’s building real mobile apps and putting them on the App Store… …without knowing how to code God damn it. It called Vibecoding. You just describe what you want in plain English, open newly . app, and the AI builds the entire thing for you. No coding. No developers. No massive budget Just vibes + AI. While most of Crypto Twitter is still crying about the job market and gambling on shitcoins… This girl is out here creating and shipping actual apps like it’s nothing. This is the new meta. Vibecoding is going to create a wave of new millionaires who barely know what a line of code looks like. We are ridiculously early. Most people will watch this and still stay stuck. The dangerous ones are already experimenting. Follow me for more raw breakdowns on vibecoding, AI money printers, and faceless cash machines that actually work in 2026.

Frogify

11,642 views • 3 months ago