deep learning
26:10Attention in transformers, step-by-step | Deep Learning Chapter 6
4.8M views • 2 years ago
3Blue1Brown
3Blue1Brown's visual walkthrough of the attention mechanism inside transformers, covering self-attention, multiple heads and cross-attention. It is chapter 6 of his deep learning series.
27:14Transformers, the tech behind LLMs | Deep Learning Chapter 5
11.6M views • 2 years ago
3Blue1Brown
3Blue1Brown's visual explanation of how transformers and GPT-style language models work, tracing data through tokens, embeddings and attention.
20:41Training an unbeatable AI in Trackmania
17.7M views • 3 years ago
Yosh
Yosh trains a reinforcement learning agent to drive Trackmania until he can no longer beat it. The video explains how the training works and the design choices involved.
Topic match · Machine learning & deep learning
24:52AlphaFold - The Most Useful Thing AI Has Ever Done
11M views • 1 year ago
Veritasium
A Veritasium video on AlphaFold, DeepMind's protein structure prediction system, and the protein design work it enabled. It features interviews with John Jumper and with David Baker's protein design group and explains why predicting protein folding matters.
Topic match · Machine learning & deep learning
24:07AI can't cross this line and we don't know why.
2.5M views • 2 years ago
Welch Labs
A Welch Labs explainer on neural scaling laws and the compute-efficient frontier, asking why model loss seems to hit a line it cannot cross. It draws an analogy to an ideal gas law for AI.
Topic match · Machine learning & deep learning
14:27The Biggest Myth In Education
15.5M views • 5 years ago
Veritasium
Veritasium debunks the idea of learning styles, such as being a visual learner, with an interview with Daniel Willingham and a memory experiment. It argues that a multimodal approach helps everyone.
11:47We Were Right! Real Inner Misalignment
271K views • 5 years ago
Robert Miles AI Safety
Robert Miles covers a paper where researchers ran real versions of his earlier mesa-optimizer thought experiments. They show inner misalignment, where an AI learns the wrong goal in training and misbehaves when deployed.
Topic match · Machine learning & deep learning
21:42Future Computers Will Be Radically Different (Analog Computing)
13.2M views • 4 years ago
Veritasium
Veritasium explains why analog computing may suit AI workloads, covering old analog computers, The Analog Thing and Mythic's analog chips that use flash memory for neural network inference. It argues digital hardware is hitting limits.
Topic match · Machine learning & deep learning
8:25Large Language Models from scratch
375K views • 4 years ago
Graphics in 5 Minutes
A short cartoon explaining how language models like ChatGPT work, from autocomplete and conditional probabilities to neural networks, gradient descent and backpropagation. It shows how networks act as universal function approximators.
Topic match · Machine learning & deep learning
56:32100%+ short interest in GameStop stock (GME) – fundamental & technical deep value analysis
1.8M views • 6 years ago
Roaring Kitty
Roaring Kitty's July 2020 analysis of GameStop, arguing a bullish deep-value case when the stock was about $4 and short interest exceeded 100%. It covers fundamentals, cash balance and technicals.
26:02Yellowstone Won't Explode And End Civilisation (Sorry) | The Deep Dive
7.8M views • 4 years ago
Soup Emporium
Soup Emporium's deep dive argues that Yellowstone is not a ticking timebomb. It goes through uplift and subsidence, earthquakes and what the caldera really is, to rebut supervolcano doom claims.
55:02GradIEEEnt half decent: The hidden power of imprecise lines
391K views • 3 years ago
suckerpinch
Tom 7 (suckerpinch) delivers a long, comedic digression on gradient descent and floating-point imprecision. He shows how rounding behavior can supply the nonlinearity needed to build a neural network.
Topic match · Machine learning & deep learning
37:20But how do AI images and videos actually work? | Guest video by Welch Labs
2.2M views • 1 year ago
3Blue1Brown
A guest video by Welch Labs on 3Blue1Brown explaining how text-to-image and video models work. It covers CLIP, shared embedding spaces, diffusion models (DDPM, DDIM), conditioning, guidance and negative prompts.
Topic match · Machine learning & deep learning
25:57GPT3: An Even Bigger Language Model - Computerphile
446K views • 6 years ago
Computerphile
Rob Miles discusses GPT-3 on Computerphile, covering how scaling parameters kept improving results over GPT-2 and how the model nearly learned arithmetic without anyone knowing exactly how.
Topic match · Machine learning & deep learning
17:59The Expert Myth
16M views • 4 years ago
Veritasium
Veritasium examines which experts have real expertise, drawing on chess research and work by Klein and Kahneman. It explains that expertise comes from pattern recognition built through deliberate practice in valid, feedback-rich environments.
1:03:314.5 Billion Years in 1 Hour
17.9M views • 2 years ago
Kurzgesagt – In a Nutshell
Kurzgesagt's hour-long animated film that compresses Earth's 4.5 billion year history into one hour, roughly a million years per second. It follows the evolution of life through to humanity's tiny final stretch.
18:14We Solved Nuclear Waste Decades Ago
4.5M views • 4 years ago
Kyle Hill
Kyle Hill explains what nuclear waste actually is and how it is stored, arguing that the problem was effectively solved decades ago. It covers solid shielded waste and deep geological storage.
28:39AMD Ryzen Eco Mode Deep-Dive & Benchmarks on R9 7950X (Zen 4)
422K views • 4 years ago
Gamers Nexus
Gamers Nexus benchmarks the Ryzen 9 7950X in its BIOS Eco Mode presets (65W, 105W and stock 170W). It measures the performance cost against the power and heat savings.
34:39Gay Frogs: A Deep Dive
2.2M views • 6 years ago
Oki's Weird Stories
A long video essay on the claim that chemicals such as atrazine are feminizing frogs. It covers the science, the EPA and the role of chemical companies.
6:24You Need a Theme, Not a Goal
5.5M views • 6 years ago
CGP Grey
CGP Grey argues for picking a theme for the year or season instead of setting goals or new year's resolutions. He explains how a theme gives direction without a pass/fail target.
Topic match · Productivity & self-improvement
10:59Your Brain Thinks Your Whole Home Is One Room
6.8M views • 6 years ago
CGP Grey
CGP Grey argues that your brain treats a whole home as one room during lockdown, blurring work, rest and leisure. He recommends creating separate spaces and routines for different activities to stay balanced.
Topic match · Productivity & self-improvement
11:28Here's What's Preventing You From Finishing Projects
147K views • 5 years ago
Zack Freedman
Zack Freedman gives advice on why makers fail to finish projects, including scrapping bad ideas, showing work publicly and writing a plan that keeps projects fun. It is aimed at hardware DIY but generalizes.
Topic match · Productivity & self-improvement
2:45Two Is the Wrong Number of Days Off
14.1M views • 6 years ago
CGP Grey
CGP Grey argues that the two-day weekend is poorly structured and proposes taking days off midweek, such as Wednesday and Sunday, instead.
Topic match · Productivity & self-improvement
5:50You Need to Be Bored. Here's Why.
17.9M views • 1 year ago
Harvard Business Review
Harvard professor Arthur Brooks explains why boredom is useful rather than something to avoid. He describes how a wandering mind engages the brain's default mode network, which supports creativity and curiosity, and suggests it may protect against depression.
Topic match · Productivity & self-improvement
18:20FIXING the ENTIRE SM64 Source Code (INSANE N64 performance)
3.2M views • 4 years ago
Kaze Emanuar
Kaze Emanuar explains how he rewrote and optimized the Super Mario 64 source code so it runs far faster on real N64 hardware. He covers performance bottlenecks and fixes in detail for his ROM hacks.
50:09Old pinball machines are amazingly complex
3.5M views • 3 years ago
Technology Connections
Technology Connections takes a long, detailed look at how a 1970s electromechanical pinball machine works, from relays to stepper motors and mechanical logic. It is the first part of a series.
46:33Heat Pumps are Not Hard: Here's what it will take to start pumping
1.2M views • 4 years ago
Technology Connections
Technology Connections' long closing video in his heat pump series, arguing that adopting heat pumps is well within reach. It explains how they work and what it takes to start using them.
35:33How does Computer Memory Work? 💻🛠
5.5M views • 4 years ago
Branch Education
A 36-minute animated deep dive from Branch Education into how DRAM works. It shows how memory connects to the CPU and how billions of bits are stored in nanoscale capacitor cells. It also covers why DRAM sits between SSDs and the processor.
20:57Atari's Quadrascan Explained
239K views • 5 years ago
Retro Game Mechanics Explained
Retro Game Mechanics Explained dissects how Atari's Quadrascan vector displays and vector generator hardware drew games like Asteroids and Tempest.
8:45Plastic Recycling is an Actual Scam | Climate Town
1.9M views • 5 years ago
Climate Town
Climate Town gives a comedic, fast-paced account of how the plastics industry promoted recycling, including the resin-code recycling symbol, while knowing most plastic could not be economically recycled. It points viewers to the Frontline documentary Plastic Wars for a deeper treatment.
38:31The $200M Machine that Prints Microchips: The EUV Photolithography System
2.4M views • 1 year ago
Branch Education
Branch Education's animated deep dive into ASML's EUV photolithography machine and how it prints nanometer-scale transistors onto chips. It covers the system's components and the process of chip manufacturing.
22:36Computer Scientist Explains One Concept in 5 Levels of Difficulty | WIRED
7.2M views • 4 years ago
WIRED
WIRED has UCLA professor Amit Sahai explain zero-knowledge proofs to a child, a teen, a college student, a grad student and an expert. Each round goes deeper into the cryptography and why it matters.
18:04How the Higgs Mechanism Give Things Mass
1.9M views • 4 years ago
PBS Space Time
A PBS Space Time episode on how the Higgs mechanism gives particles mass, prompted by Fermilab's heavier-than-expected W boson measurement. It goes beyond the usual pop-science treatment without heavy math.
55:00The Closest Thing We Have to Alien Technology
64.9M views • 10 months ago
Veritasium
Veritasium explains how ASML's EUV lithography machines make the most advanced computer chips, covering the engineering of the light source, mirrors and the supply chain around them. It is a long-form explainer on the world's most complex commercial machine.
22:13what did you do
1.5M views • 11 months ago
Noodle
Noodle explores how retro pixel art was designed for CRT displays and why games look different on LCDs, with input from pixel artists and CRT researchers.
1:00:26Why Starting A Rocket Engine Is So Hard!
2.3M views • 3 years ago
Everyday Astronaut
Tim Dodd's hour-long deep dive on how rocket engines start, from solid motors to liquid engines. It covers thermal conditioning, spin-up, ignition methods, starting in space, and a step-by-step RS-25 startup.
33:01The Strangest Implication of Quantum Mechanics
20.6M views • 1 year ago
Veritasium
A Veritasium video that follows the principle of least action from Bernoulli and Newton to quantum mechanics, asking whether light takes all possible paths at once. It includes experiments showing quantum waves.
28:11Why Everyone Is Talking About Data Centers In Space
408K views • 10 months ago
Scott Manley
Scott Manley examines why SpaceX, Google and others are looking at orbital data centers. He walks through the economics, heat rejection and solar power arguments, with links to the Lumen/Starcloud and Google Suncatcher papers.
21:58Group theory, abstraction, and the 196,883-dimensional monster
3.8M views • 6 years ago
3Blue1Brown
3Blue1Brown introduces group theory and abstract groups, then builds toward classification of finite simple groups and the enormous Monster group with its 196,883 dimensions.
10:29Are There Lost Alien Civilizations in Our Past?
14.2M views • 4 years ago
Kurzgesagt – In a Nutshell
Kurzgesagt asks whether advanced civilizations could have existed on Earth in the deep past and left little evidence. It looks at time as a dimension for searching for alien civilizations and the limits of the geological record.