Következő
Transformers, the tech behind LLMs | Deep Learning Chapter 5 28 perc 
Inside the 29 minutes that captured 9/11: CBS News cameraman reflects on what he saw at Ground Zero 9 perc 
Antique Steam Tractor Kills Five | Fascinating Horror 11 perc 
A message from Sir David Attenborough on the eve of his 100th birthday 💌 #DavidAttenborough100 1 perc 
Can Frogs Power a Lightbulb? | Fascinating Horror Shorts 1 perc 
The US Is Hiding a Geographic Nightmare Nobody Talks About 24 perc 
The Biggest Aquarium Collapse in History | Fascinating Horror Shorts 1 perc 
DefunctTV: The History of Under the Umbrella Tree 26 perc 
9/11 reports from 60 Minutes 215 perc 
The Most Surreal Holiday Photo | Fascinating Horror Shorts 1 perc 
McBarge 2026 Update 15 perc 
SNEAKING A Painting Next To The Mona Lisa 15 perc 
4,000,000 - Q&A 11 perc 
Scientists Just Found Non-Human DNA in Our Bodies 11 perc 
Alaska 8K - Scenic Relaxation Film With Calming Music 61 perc 
Scientists Found a Spider With a Nightmare Superpower 22 perc 
Old Florida - The Last Outlaws of the Everglades 79 perc 
The vulnpocalypse might not be so bad after all 34 perc 
6 Asians vs 1 Secret Fake Asian 70 perc 
Inside America’s Fastest-Shrinking City 65 perc 
Disgusting Freak Should Be Arrested 12 perc 
Michael Kratsios: Inside the White House's AI Strategy 40 perc 
Sci-fi fantasy action THE WILD - Werewolves, shape-shifters creatures future experiments short-story 1 perc 
The Ultimate Smartphone Camera Test 1 perc 
Supersized Upgrade for Otis... 2 perc 
This Mechanism Scratches My Brain 1 perc 
Becoming a CYBORG with TWO ROBOT ARMS! 28 perc 
Hybrid Power Systems! | Real Life Power Armor (Part 4/6) 23 perc 
Meet SAM… Meta’s latest AI model 1 perc 
TOMBSTONE vs ORBITRON (VIDEO #6/6) 15 perc 
I put the NEWEST CPU in the OLDEST Motherboard 14 perc 
History's Worst Elevator Accident: Vaal Reefs | Fascinating Horror 10 perc 
Why won’t AI agents just follow the rules? 36 perc 
NVIDIA's Open Source Strategy🤖 1 perc 
BREAKING: YouTube Just Changed Monetization 20 perc 
This was a hard year. 13 perc 
5 Ways to Connect AI Agents to Tools: From APIs to MCP 12 perc 
How AI Is Changing Code Reviews & Software Development 15 perc 
The Bath Curse Tablets | Fascinating Horror Shorts 1 perc 
Where Claude Mythos can help 1 perc 
Ranking #1 Is Barely Half the Game Now #shorts 1 perc 
The Power Armor Legs Are Complete! ⚡| Real Life Power Armor (Part 7/6) 27 perc 
Come Down, Baby Goat | Safety Rules for Kids | Nursery Rhyme & Kids Songs | BabyBus 40 perc 
Should Kids Still Go To College? (Answering All Your Questions) 48 perc 
Becoming A Test Pilot: Do You Have What It Takes? 46 perc 
The World's Most Ignored War Explained 33 perc 
Pedro Pony Is Late ⏰ #shorts #peppapig 1 perc 
The New ChatGPT Playbook & Prompting Guide 39 perc 
Fishy Friend for Goldie Song 🐟 #shorts #peppapig 1 perc 
When the Sky Turns Dark | Fun Muddy Adventure | Funny Family Song for Kids | BabyBus 24 perc 
Take a Bath, Dirty Monster! | Good Habits Song | Bath Song | Nursery Rhymes | BabyBus 24 perc Breaking down how Large Language Models work, visualizing how data flows through. Instead of sponsored ad reads, these lessons are funded directly by viewers: https://3b1b.co/support --- Here are a few other relevant resources Build a GPT from scratch, by Andrej Karpathy https://youtu.be/kCc8FmEb1nY If you want a conceptual understanding of language models from the ground up, @vcubingx just started a short series of videos on the topic: https://youtu.be/1il-s4mgNdI?si=XaVxj6bsdy3VkgEX If you're interested in the herculean task of interpreting what these large networks might actually be doing, the Transformer Circuits posts by Anthropic are great. In particular, it was only after reading one of these that I started thinking of the combination of the value and output matrices as being a combined low-rank map from the embedding space to itself, which, at least in my mind, made things much clearer than other sources. https://transformer-circuits.pub/2021/framework/index.html History of language models by Brit Cruise, @ArtOfTheProblem https://youtu.be/OFS90-FX6pg An early paper on how directions in embedding spaces have meaning: https://arxiv.org/pdf/1301.3781.pdf Звуковая дорожка на русском языке: Влад Бурмистров. --- Timestamps 0:00 - Predict, sample, repeat 3:03 - Inside a transformer 6:36 - Chapter layout 7:20 - The premise of Deep Learning 12:27 - Word embeddings 18:25 - Embeddings beyond words 20:22 - Unembedding 22:22 - Softmax with temperature 26:03 - Up next
Packages published by the creator behind this video.
This creator has not set their rates yet. Send a request and we will pass it on — the price is agreed before anything is charged.
A recurring seat in my content. Subscribers enter a queue — or a random draw when there are more subscribers than slots — and appear in the video itself, in the credits, or in the description.
per month
Price on request
A guaranteed appearance of at least 10 seconds in my next video. Price depends on where in the runtime the insert lands.
Price on request
A guaranteed appearance of at least 10 seconds inside a Short cut from one of my existing videos.
one-off
Price on request