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.

Introducing the Illustrated Transformer in 3D 🚀 Fly through LLaMA like never before. See every tensor and operation in motion. Click any component to reveal the exact lines of code that run it. A new way to learn and teach LLMs. Try it out in the link below 👇

alphaXiv

50,023 subscribers

50,503 views • 8 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

You can now add a live browser to Claude Code to click any element and edit it 🤯 Your app runs embedded. You click a button. Claude instantly knows the exact selector, the exact component, the exact location in your code. No more “the red button in the top left of the third card.” Just click it. 100% open source.

You can now add a live browser to Claude Code to click any element and edit it 🤯 Your app runs embedded. You click a button. Claude instantly knows the exact selector, the exact component, the exact location in your code. No more “the red button in the top left of the third card.” Just click it. 100% open source.

Alvaro Cintas

47,136 views • 2 months ago

I pasted the Three.js code from the previous 3D scene in Grok 4 from xAI and prompted it to create a variation with new shapes. The scene leverages custom GLSL shaders for particle behavior and click morphs between shapes. Open source code and workflow in the thread below. 🧵👇

I pasted the Three.js code from the previous 3D scene in Grok 4 from xAI and prompted it to create a variation with new shapes. The scene leverages custom GLSL shaders for particle behavior and click morphs between shapes. Open source code and workflow in the thread below. 🧵👇

Techartist

3,103,803 views • 1 year ago

Introducing the "Preview" component... Try any shader in your project codebase, including Pro presets, in 60 seconds ⚡️ npm install, copy a single component tag, see it live 👀

Introducing the "Preview" component... Try any shader in your project codebase, including Pro presets, in 60 seconds ⚡️ npm install, copy a single component tag, see it live 👀

shaders

15,894 views • 5 months ago

Introducing DuoNano🐸 Become the star of your own epic language adventure. -Just upload a pic of yourself or any character you like and dive right into the story in our Adventure Mode🐸 -One second you're wandering a lively market in Mexico City, the next you're uncovering some ancient temple in Kyoto, and through it all, it's still totally you in the mix. -Use your camera to upload pictures with Visual Vocabulary to learn how to say anything in a new language! Our visual model will detect the objects in the image and explain it to you in whatever language you select. -If you want to test your mettle, try the conversation practice tutor to test your skills against a native speaking AI. Try DN today. You're gonna love it. Link Below 👇

Introducing DuoNano🐸 Become the star of your own epic language adventure. -Just upload a pic of yourself or any character you like and dive right into the story in our Adventure Mode🐸 -One second you're wandering a lively market in Mexico City, the next you're uncovering some ancient temple in Kyoto, and through it all, it's still totally you in the mix. -Use your camera to upload pictures with Visual Vocabulary to learn how to say anything in a new language! Our visual model will detect the objects in the image and explain it to you in whatever language you select. -If you want to test your mettle, try the conversation practice tutor to test your skills against a native speaking AI. Try DN today. You're gonna love it. Link Below 👇

bone

40,423 views • 10 months ago

English Is The New SQL LLMs have made it easy for everyone to create on-the-fly dashboards and plots. You can connect to your database and then use a SOTA LLM like 4o, Opus, or Gemini to generate SQL and Python code to create on-the-fly dashboards and plots. ChatLLM makes it possible across all state-of-the-art LLMs -

English Is The New SQL LLMs have made it easy for everyone to create on-the-fly dashboards and plots. You can connect to your database and then use a SOTA LLM like 4o, Opus, or Gemini to generate SQL and Python code to create on-the-fly dashboards and plots. ChatLLM makes it possible across all state-of-the-art LLMs -

Bindu Reddy

50,564 views • 2 years ago

Today, I invite you to learn the Browser Mode in Vitest. Unlock the true value out of your React component tests in the real browser! 📢 A new workshop is OUT at Epic Web. The link below.

Today, I invite you to learn the Browser Mode in Vitest. Unlock the true value out of your React component tests in the real browser! 📢 A new workshop is OUT at Epic Web. The link below.

Artem Zakharchenko

34,130 views • 1 year ago

🔔Want to learn more about #Bitroot? We've just released a brand new introductory video that showcases Bitroot's features and benefits in detail. 🎉🔥 Hurry up and click the link to watch it! 🚀

Bitroot

123,518 views • 2 years ago

🚀 Introducing MCP Agents in Magentic-UI! Spin up custom agents that wrap one (or many) MCP tools, and let the Orchestrator pick the best agent for every step of the plan. Check out the demo below to see them in action 👇 #MCP #MagenticUI #AIagents

🚀 Introducing MCP Agents in Magentic-UI! Spin up custom agents that wrap one (or many) MCP tools, and let the Orchestrator pick the best agent for every step of the plan. Check out the demo below to see them in action 👇 #MCP #MagenticUI #AIagents

Microsoft AI Frontiers

10,616 views • 1 year ago

THIS GUY ADDED A LIVE BROWSER TO CLAUDE CODE SO YOU CAN CLICK ANY ELEMENT AND EDIT IT INSTANTLY biggest issue with vibe coding UI is that you have to describe what you want to change. if you prompt it the wrong selector or wrong component, Claude can't find it. now you just click it. your app runs in an embedded browser with Claude Code. you can click any button, any text, any div. Claude instantly knows exactly what you're pointing at. click. instruct. done. no more "change the button in the top right corner of the second card component." all you have to do now is just click the button. AND its open source

THIS GUY ADDED A LIVE BROWSER TO CLAUDE CODE SO YOU CAN CLICK ANY ELEMENT AND EDIT IT INSTANTLY biggest issue with vibe coding UI is that you have to describe what you want to change. if you prompt it the wrong selector or wrong component, Claude can't find it. now you just click it. your app runs in an embedded browser with Claude Code. you can click any button, any text, any div. Claude instantly knows exactly what you're pointing at. click. instruct. done. no more "change the button in the top right corner of the second card component." all you have to do now is just click the button. AND its open source

Om Patel

152,845 views • 3 months ago

Introducing EntelligenceAI extension for VS Code, Cursor & Windsurf! 🚀 Review your code directly in your IDE before you even merge & get instant feedback as you vibe with your code! ⚡️ Check it out in the link below

Introducing EntelligenceAI extension for VS Code, Cursor & Windsurf! 🚀 Review your code directly in your IDE before you even merge & get instant feedback as you vibe with your code! ⚡️ Check it out in the link below

Entelligence AI

93,426 views • 1 year ago

From global trade routes to the exact crater of the Moon landing. Meet **Gauth Atlas**. Visualizing human achievements through an interactive geographic lens. Dive into the details of the Age of Discovery with just a click. Type in any topic and try it now!

From global trade routes to the exact crater of the Moon landing. Meet Gauth Atlas. Visualizing human achievements through an interactive geographic lens. Dive into the details of the Age of Discovery with just a click. Type in any topic and try it now!

Gauth: AI Study Companion

3,293,474 views • 2 months ago

🚨 BREAKING: Introducing 𝗦𝗶𝗺𝘂𝗹𝗮𝗿 𝗖𝗹𝗼𝘂𝗱 The future of autonomous computers starts today. A full Linux desktop in the cloud—fully operated by Agent S that see, click, and type like you do. No setup. No code. Just ask. Try it yourself →

🚨 BREAKING: Introducing 𝗦𝗶𝗺𝘂𝗹𝗮𝗿 𝗖𝗹𝗼𝘂𝗱 The future of autonomous computers starts today. A full Linux desktop in the cloud—fully operated by Agent S that see, click, and type like you do. No setup. No code. Just ask. Try it yourself →

Ang Li

327,929 views • 1 year ago

Announcing How Transformer LLMs Work, created with Jay Alammar and Maarten Grootendorst, co-authors of the beautifully illustrated book, “Hands-On Large Language Models.” This course offers a deep dive into the inner workings of the transformer architecture that powers large language models (LLMs). The transformer architecture revolutionized generative AI; in fact, the "GPT" in ChatGPT stands for "Generative Pre-Trained Transformer." Originally introduced in the Google Brain team's groundbreaking 2017 paper "Attention Is All You Need," by Vaswani and others, transformers were a highly scalable model for machine translation tasks. Variants of this architecture now power today’s LLMs such as those from OpenAI, Google, Meta, Cohere, Anthropic and DeepSeek. In this course, you’ll learn in detail how LLMs process text. You'll also work through code examples that illustrate that transformer's individual components. In details, you’ll learn: - How the representation of language has evolved, from Bag-of-Words to Word2Vec embeddings to the transformer architecture that captures a word's meanings taking into account the context of other words in the input. - How inputs are broken down into tokens before they are sent to the language model. - The details of a transformer's main stages: Tokenization and embedding, the stack of transformer blocks, and the language model head. - The inner workings of the transformer block, including attention, which calculates relevance scores, and the feedforward layer, which incorporates stored information learned in training. - How cached calculations make transformers faster. - Some of the most recent ideas in the latest models such as Mixture-of-Experts (MoE) which uses multiple sub-models and a router on each layer to improve the quality of LLMs. By the end of this course, you’ll have a deep understanding of how LLMs actually process text and be able to read through papers describing the latest models and understand the details. Gaining this intuition will improve your approach to building LLM applications. Please sign up here:

Announcing How Transformer LLMs Work, created with Jay Alammar and Maarten Grootendorst, co-authors of the beautifully illustrated book, “Hands-On Large Language Models.” This course offers a deep dive into the inner workings of the transformer architecture that powers large language models (LLMs). The transformer architecture revolutionized generative AI; in fact, the "GPT" in ChatGPT stands for "Generative Pre-Trained Transformer." Originally introduced in the Google Brain team's groundbreaking 2017 paper "Attention Is All You Need," by Vaswani and others, transformers were a highly scalable model for machine translation tasks. Variants of this architecture now power today’s LLMs such as those from OpenAI, Google, Meta, Cohere, Anthropic and DeepSeek. In this course, you’ll learn in detail how LLMs process text. You'll also work through code examples that illustrate that transformer's individual components. In details, you’ll learn: - How the representation of language has evolved, from Bag-of-Words to Word2Vec embeddings to the transformer architecture that captures a word's meanings taking into account the context of other words in the input. - How inputs are broken down into tokens before they are sent to the language model. - The details of a transformer's main stages: Tokenization and embedding, the stack of transformer blocks, and the language model head. - The inner workings of the transformer block, including attention, which calculates relevance scores, and the feedforward layer, which incorporates stored information learned in training. - How cached calculations make transformers faster. - Some of the most recent ideas in the latest models such as Mixture-of-Experts (MoE) which uses multiple sub-models and a router on each layer to improve the quality of LLMs. By the end of this course, you’ll have a deep understanding of how LLMs actually process text and be able to read through papers describing the latest models and understand the details. Gaining this intuition will improve your approach to building LLM applications. Please sign up here:

Andrew Ng

259,421 views • 1 year ago

INTRODUCING THE FEYRIN!! 💫 A complete remake of my original kirin! 🔗 Links in comments, use code "ULTRA" to get 20% off now through Furality, and be sure to check out my booth and give it a try!! #VRChat #furry

INTRODUCING THE FEYRIN!! 💫 A complete remake of my original kirin! 🔗 Links in comments, use code "ULTRA" to get 20% off now through Furality, and be sure to check out my booth and give it a try!! #VRChat #furry

Callista @ AC!

40,764 views • 2 months ago

Introducing Claude Code Hook - Context Timeline (Saving this to try later) Install with: npx claude-code-templates@latest --hook monitoring/context-timeline Managing the context window and the subagents running in Claude Code is hard to keep track of That's why I built this hook... It starts the moment you open a session and shows a timeline with the main agent's context window and how subagents start working in their own separate context Every subagent you have running will show up in real time This way you can manage the context and the subagents you run, and see everything in a much simpler way than in the console

Introducing Claude Code Hook - Context Timeline (Saving this to try later) Install with: npx claude-code-templates@latest --hook monitoring/context-timeline Managing the context window and the subagents running in Claude Code is hard to keep track of That's why I built this hook... It starts the moment you open a session and shows a timeline with the main agent's context window and how subagents start working in their own separate context Every subagent you have running will show up in real time This way you can manage the context and the subagents you run, and see everything in a much simpler way than in the console

Daniel San

51,690 views • 2 months ago

I just created my own OCR app using Llama 3.2 vision! Upload an image, and it converts it into structured markdown using Llama 3.2 multimodal! Here's what I used: - Ollama for serving Llama 3.2 vision locally. - Streamlit for the UI. Everything in just 50 lines of code! Find the code in the next tweet. -- Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. Find me → Avi Chawla

I just created my own OCR app using Llama 3.2 vision! Upload an image, and it converts it into structured markdown using Llama 3.2 multimodal! Here's what I used: - Ollama for serving Llama 3.2 vision locally. - Streamlit for the UI. Everything in just 50 lines of code! Find the code in the next tweet. -- Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. Find me → Avi Chawla

Avi Chawla

131,139 views • 1 year ago

Introducing Audio in Workflows! Type it. Clone it. Vibe with it. Welcome to the future of sound. This isn’t a feature, it’s a cheat code for creators. Try now: Link in bio!

Introducing Audio in Workflows! Type it. Clone it. Vibe with it. Welcome to the future of sound. This isn’t a feature, it’s a cheat code for creators. Try now: Link in bio!

ImagineArt

287,488 views • 3 months ago

The reveal in The Others (2001) reframes every shadow and whisper that came before it. When the truth settles in, the silence in the theater feels heavier than any jump scare.

The reveal in The Others (2001) reframes every shadow and whisper that came before it. When the truth settles in, the silence in the theater feels heavier than any jump scare.

cinesthetic.

307,925 views • 5 months ago

🚀 I always wanted to just run some React web code in a native app—that's why I created the new "use dom" directive! ⚡️ Try it today in @Expo SDK 52 and watch my full React Universe Summit | June 23, 2026 talk to learn more...

🚀 I always wanted to just run some React web code in a native app—that's why I created the new "use dom" directive! ⚡️ Try it today in @Expo SDK 52 and watch my full React Universe Summit | June 23, 2026 talk to learn more...

Evan Bacon 🥓

49,833 views • 1 year ago