Why LLMs Live In 12,288 Dimensions
Modern AI systems represent words, images, proteins and entire documents as points in spaces with hundreds, thousands or even tens of thousands of dimensions. But geometry behaves very differently in these spaces. In high dimensions: • Unit spheres disappear • Almost all points lie near the boundary of a cube • Random vectors become nearly orthogonal • Distances become surprisingly predictable • Entire functions become almost constant These phenomena are examples of one of the most remarkable ideas in modern mathematics: concentration of measure. In this video, we explore the strange geometry of high-dimensional spaces, prove several fundamental concentration results, and discuss how these ideas connect to modern machine learning, embeddings, transformers and deep learning. Along the way we'll encounter: • The disappearing sphere • Boundary concentration • Distance concentration • Random orthogonality • Equator concentration • Lévy's concentration theorem • The curse and blessing of dimensionality • Modern AI and representation learning High-dimensional geometry is often counterintuitive, sometimes shocking, and increasingly important for understanding how modern machine learning systems operate. Timestamps 00:00 Introduction 01:03 The Disappearing Sphere 03:37 Distance Concentration 05:31 Random Orthogonality 08:45 Boundary Concentration 10:01 Equator Concentration 13:44 Lévy's Concentration Theorem 17:23 Machine Learning & AI 30:25 Open Questions #MachineLearning #ArtificialIntelligence #DeepLearning #llm #Transformers #NeuralNetworks #ConcentrationOfMeasure #HighDimensionalGeometry #AI

Something strange happens when you "bump the base"

How Divergence and Curl Were Discovered

Autoregressive Models Explained — Why AI Generates One Token at a Time

Double Descent And Other Mysteries Related to LLMs

We're 99.9% sure this pattern is true, but no one can prove it

The FOUR Levels of Understanding Tensors: From Computer Science to Physics to Math
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEnCNACELwBSFryq4qpAxkIARUAAAAAGAElAADIQj0AgKJDeAG4AvMY&rs=AOn4CLD_18b67Sqa4i4Yv09BD3B69fisZQ&usqp=CCY)
Yann LeCun's $1B Bet Against LLMs [Part 1]

How To Think SO CLEARLY People Assume You're A Genius

How To Become Dangerously Self-Educated (with AI)

MIT Just Revealed the AI Bubble's Fatal Flaw

The hidden logic behind #, @, & and §

Diffusion Models: The Generative AI That Learns By Destroying Images

But how do AI images and videos actually work? | Guest video by Welch Labs

Attention in transformers, step-by-step | Deep Learning Chapter 6

THIS is why large language models can understand the world

Die Zombie-Simulation, die niemand erklären kann

Oligarchy is worse than you think

Anthropic is Completely F*cked.

DeepSeek Gave LLMs a Real Memory (It's Not RAG)

