正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Benjamin Bycroft’s 3D interactive tool visualizes an LLM’s layers, weights and matrix operations. This is the best educational tool to understand how an LLM works i've seen. httpx://bbycroft.net/llm

tetsuo

241,397 subscribers

30,150 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

14 条评论

Learn German 的头像

Learn German3 个月前

This is genuinely one of the best LLM explainers I've seen. The way it shows attention turning raw tokens into structured meaning through nothing but matrix multiplies and layer norms is hypnotic. Makes you realize we're just watching a giant optimized calculator hallucinate coherence in real time.

Flash ⚡️ 的头像

Flash ⚡️3 个月前

Learning

the dirty framed pepe 的头像

the dirty framed pepe3 个月前

Nice song

0x999dev 的头像

0x999dev3 个月前

what gets me is watching the residual stream branch at attention heads in real time. most diagrams flatten that into arrows. wish it showed KV cache behavior too, that's where half the inference cost hides

Andrej Szontagh 的头像

Andrej Szontagh3 个月前

I think I will finally take some time to get over this. No more guessing.

JETLAB-X 的头像

JETLAB-X3 个月前

This visualization is really incredible 😎💯

Vito Botta 的头像

Vito Botta3 个月前

Bookmarked. The 3D attention head visualisation finally made transformers click for me visually.

DigitalDaisy 的头像

DigitalDaisy3 个月前

No idea, but the way you slam it together, ok ☕️🥞🍊

mitch morales | xp/acc 的头像

mitch morales | xp/acc3 个月前

matrix ops you can actually click through is the killer learning tool

Tyco Kayson 的头像

Tyco Kayson3 个月前

This is incredible

Aetheron 的头像

Aetheron3 个月前

Wow, awesome! 🙌🏻

Andrej Szontagh 的头像

Andrej Szontagh3 个月前

So I have finally went through this and I have to say that despite the visualization is really nice I didn't learn much. This literally goes over the lowest level, but tells you nothing about 'WHY?'

AlphaOmegaAm1 的头像

AlphaOmegaAm13 个月前

Oh heck yeah! These demos are 🔥

上来透口气的头像

上来透口气3 个月前

Deep-dive content

相关视频

If you are having a hard time visualizing all the layers and matrix operations inside an LLM, then you'll love this website! Check it out:

If you are having a hard time visualizing all the layers and matrix operations inside an LLM, then you'll love this website! Check it out:

Santiago Víquez

135,124 次观看 • 1 年前

Fable 5 is an absolute beast at threejs. It's the best LLM at generating 3D simulations/worlds. Watch how I combine it with gpt-realtime-2 to generate interactive educational 3D worlds DAIR.AI. Comment below if you want to see a breakdown.

Fable 5 is an absolute beast at threejs. It's the best LLM at generating 3D simulations/worlds. Watch how I combine it with gpt-realtime-2 to generate interactive educational 3D worlds DAIR.AI. Comment below if you want to see a breakdown.

elvis

38,026 次观看 • 2 个月前

This is the first time I've ever seen an LLM operate a GUI as fast as a person, and it's surreal.

This is the first time I've ever seen an LLM operate a GUI as fast as a person, and it's surreal.

Ari Weinstein

1,230,415 次观看 • 5 个月前

I needed a quick tool to convert any sort of GitHub links into a format an LLM could read. So I built it. GitHub → LLM It's completely free and works with projects, folders, or files 🪄 Deployed on Replit ⠕

I needed a quick tool to convert any sort of GitHub links into a format an LLM could read. So I built it. GitHub → LLM It's completely free and works with projects, folders, or files 🪄 Deployed on Replit ⠕

Pietro Schirano

120,827 次观看 • 2 年前

How to Get React Router v7 to work with AI This example uses Cursor rules, but the concept is the same no matter the AI tool: - Give the LLM context (I've already done this part for you) - Use an MCP server (GitMCP is great here) for specific questions

How to Get React Router v7 to work with AI This example uses Cursor rules, but the concept is the same no matter the AI tool: - Give the LLM context (I've already done this part for you) - Use an MCP server (GitMCP is great here) for specific questions

Brooks Lybrand

10,183 次观看 • 1 年前

Excited to launch the mem0 Browser Extension. It’s an open-source, cross-LLM tool that lets you own your memories across ChatGPT, Claude, and Perplexity.

Excited to launch the mem0 Browser Extension. It’s an open-source, cross-LLM tool that lets you own your memories across ChatGPT, Claude, and Perplexity.

Taranjeet

37,883 次观看 • 1 年前

Something REALLY cool I've seen at hardwear.io => a giant USB-C interface by Marc Omo from Markus Engineering. 👉 The most interactive and educational way to show how an USB interface works 🥇

Something REALLY cool I've seen at hardwear.io => a giant USB-C interface by Marc Omo from Markus Engineering. 👉 The most interactive and educational way to show how an USB interface works 🥇

Sébastien Dudek 📡

10,677 次观看 • 4 个月前

A Stanford professor just gave a public lecture on exactly how GPT, Claude, and LLaMA are built under the hood no insider access required just the clearest breakdown of modern LLM architecture I've seen this lecture reveals the framework professors are paid up to $750K a year to teach the gap between "I use ChatGPT" and "I understand how it works" is smaller than most people think the most complete public breakdown of modern LLM architecture I've seen this year

A Stanford professor just gave a public lecture on exactly how GPT, Claude, and LLaMA are built under the hood no insider access required just the clearest breakdown of modern LLM architecture I've seen this lecture reveals the framework professors are paid up to $750K a year to teach the gap between "I use ChatGPT" and "I understand how it works" is smaller than most people think the most complete public breakdown of modern LLM architecture I've seen this year

rewind

165,059 次观看 • 3 个月前

New short course on LLMOps! LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by Google Cloud's Erwin Huizenga, you'll learn to use automation to make building, tuning and deploying an LLM-based application less manual and more efficient. You'll learn how to: - Apply supervised fine-tuning to tune an LLM to a specific task - Automate and orchestrate LLM-tuning and deployment by customizing a pre-built tuning pipeline - Apply best practices for preparing training data for supervised fine-tuning of an LLM - Create an LLMOps workflow you can adapt to other LLM-tuning jobs This course doesn't assume any prior MLOps or LLMOps experience. Sign up here to learn about this emerging field!

New short course on LLMOps! LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by Google Cloud's Erwin Huizenga, you'll learn to use automation to make building, tuning and deploying an LLM-based application less manual and more efficient. You'll learn how to: - Apply supervised fine-tuning to tune an LLM to a specific task - Automate and orchestrate LLM-tuning and deployment by customizing a pre-built tuning pipeline - Apply best practices for preparing training data for supervised fine-tuning of an LLM - Create an LLMOps workflow you can adapt to other LLM-tuning jobs This course doesn't assume any prior MLOps or LLMOps experience. Sign up here to learn about this emerging field!

Andrew Ng

221,803 次观看 • 2 年前

AI code reviews are promising, BUT they're hard to control and currently all closed source. That's why we built GPTLint: It's an automated code review tool powered by both ASTs and LLMs – the best part is it's a 100% OSS standard that works w/ any LLM 🔥

AI code reviews are promising, BUT they're hard to control and currently all closed source. That's why we built GPTLint: It's an automated code review tool powered by both ASTs and LLMs – the best part is it's a 100% OSS standard that works w/ any LLM 🔥

Travis Fischer

38,139 次观看 • 2 年前

a GPT alternative where each tool is provided by a third party and gets paid by the platform per use the main LLM will just be an orchestrated, selecting what tool to use when and pays it with x402 per task (search, image generation...)

a GPT alternative where each tool is provided by a third party and gets paid by the platform per use the main LLM will just be an orchestrated, selecting what tool to use when and pays it with x402 per task (search, image generation...)

Ash

15,056 次观看 • 10 个月前

new project: cleo (kindle + llm) 📚 cleo is an ios app that pairs whatever book you're reading on kindle with an llm (o3) — ask questions, get recaps/summaries, or listen/discuss (think audiobooks but interactive). the llm has context on exactly where you are + the book contents. best part? no complex setup needed. just link your kindle account and that's it. it just works. reply / rt for testflight invite 👇

new project: cleo (kindle + llm) 📚 cleo is an ios app that pairs whatever book you're reading on kindle with an llm (o3) — ask questions, get recaps/summaries, or listen/discuss (think audiobooks but interactive). the llm has context on exactly where you are + the book contents. best part? no complex setup needed. just link your kindle account and that's it. it just works. reply / rt for testflight invite 👇

jpa

631,051 次观看 • 1 年前

He is 17 sold an LLM system to Anthropic for $2.2M - and at Stanford shared how to build and sell one from scratch: 00:20 - how to build an LLM system that Anthropic will buy for millions 08:34 - one prompt in Opus 5 and the LLM system is ready to sell in 60 minutes 23:47 - how to sell an LLM to Anthropic at 17 with no experience and reach $2.2M a year after watching I built my first LLM system in 60 minutes - and sold it to Anthropic for $120k. save & watch - the article below is one file that builds an LLM system and sells it to Anthropic for $2.2M.

He is 17 sold an LLM system to Anthropic for $2.2M - and at Stanford shared how to build and sell one from scratch: 00:20 - how to build an LLM system that Anthropic will buy for millions 08:34 - one prompt in Opus 5 and the LLM system is ready to sell in 60 minutes 23:47 - how to sell an LLM to Anthropic at 17 with no experience and reach $2.2M a year after watching I built my first LLM system in 60 minutes - and sold it to Anthropic for $120k. save & watch - the article below is one file that builds an LLM system and sells it to Anthropic for $2.2M.

Noisy

25,396 次观看 • 18 天前

Claude Code + Obsidian is the most powerful AI combo I've ever used. I literally built an AI second brain that runs my entire life. Inspired by Andrej Karpathy's LLM Knowledge Wiki, this tool has been a complete game-changer. Here's EXACTLY how to build one for yourself:

Claude Code + Obsidian is the most powerful AI combo I've ever used. I literally built an AI second brain that runs my entire life. Inspired by Andrej Karpathy's LLM Knowledge Wiki, this tool has been a complete game-changer. Here's EXACTLY how to build one for yourself:

Miles Deutscher

976,436 次观看 • 5 个月前

JSX Tool (@jsxtool) is an in-browser IDE for building React UIs. Click on any element in the browser to jump straight to the relevant line of code and edit it yourself or provide precise context to an LLM to make updates.

JSX Tool (@jsxtool) is an in-browser IDE for building React UIs. Click on any element in the browser to jump straight to the relevant line of code and edit it yourself or provide precise context to an LLM to make updates.

Y Combinator

49,755 次观看 • 10 个月前

The new o1 canvas is quite impressive: "create an interactive tool that visually shows me how correlation works, and why correlation alone is not a great descriptor of the underlying data in many cases. make it accessible to nonmath people and highly interactive and engaging"

The new o1 canvas is quite impressive: "create an interactive tool that visually shows me how correlation works, and why correlation alone is not a great descriptor of the underlying data in many cases. make it accessible to nonmath people and highly interactive and engaging"

Ethan Mollick

137,714 次观看 • 1 年前

I built a free internal linking tool using TypeSafe AI Jev for classifying and selecting the links. BYOK or pay $1 to use mine. It works for up to 500 pages and gives you a CSV or JSON to pass to an LLM to implement.

I built a free internal linking tool using TypeSafe AI Jev for classifying and selecting the links. BYOK or pay $1 to use mine. It works for up to 500 pages and gives you a CSV or JSON to pass to an LLM to implement.

Ian Nuttall

34,221 次观看 • 8 天前

He is 18 built an LLM and sold it to Anthropic for $3.2M - and at Stanford shared how to repeat it from scratch: 00:30 - how to build an LLM worth $100k in one evening 21:34 - how one LLM controls 1000 processes at the same time 43:47 - from first prompt to $3.2M from Anthropic after watching I built my first LLM in 60 minutes- a week later Anthropic offered me $100k for the system. save & watch - the article below shows how to build an LLM and sell it to Anthropic for $3.2M from scratch

He is 18 built an LLM and sold it to Anthropic for $3.2M - and at Stanford shared how to repeat it from scratch: 00:30 - how to build an LLM worth $100k in one evening 21:34 - how one LLM controls 1000 processes at the same time 43:47 - from first prompt to $3.2M from Anthropic after watching I built my first LLM in 60 minutes- a week later Anthropic offered me $100k for the system. save & watch - the article below shows how to build an LLM and sell it to Anthropic for $3.2M from scratch

Noisy

46,671 次观看 • 16 天前

Here's an example process on how I shade (Watch me struggle for the sake of this tutorial) The lasso tool and blur tool is your best friend, use it wisely

Here's an example process on how I shade (Watch me struggle for the sake of this tutorial) The lasso tool and blur tool is your best friend, use it wisely

FazFuri 💜✨️

45,880 次观看 • 1 年前

Microsoft just released an impressive tool OmniParser V2 can turn any LLM into an agent capable of using a computer 🔥 You can enable GPT-4o, DeepSeek R1, Sonnet 3.5, Qwen... to understand what's on your screen and take actions. 100% free & open source

Microsoft just released an impressive tool OmniParser V2 can turn any LLM into an agent capable of using a computer 🔥 You can enable GPT-4o, DeepSeek R1, Sonnet 3.5, Qwen... to understand what's on your screen and take actions. 100% free & open source

Paul Couvert

460,138 次观看 • 1 年前