mach-e

Matt Parker of Stand-up Maths demonstrates MENACE, Donald Michie's 1961 machine made of matchboxes that learns to play noughts and crosses through reinforcement. He builds and trains a physical version.

3Blue1Brown's second neural network chapter explains cost functions and gradient descent, showing how a network learns by minimizing error during training.

3Blue1Brown's first chapter on deep learning explains what neurons and layers are and the math underlying a basic neural network, using handwritten digit recognition with visual animations.

Veritasium explores compliant mechanisms, devices that move by flexing rather than using hinges and joints, with researchers at BYU. It covers advantages such as fewer parts and precision, including uses in nuclear weapon safety.

3kliksphilip summarizes Valve's GDC talk on VACNet, a deep-learning system that flags CS:GO cheaters and feeds the Overwatch review queue. It covers Trust Factor, VAC, and how the data is collected and analyzed.

Veritasium short showing Drew Berry's scientifically accurate animations of the molecular machines that drive cell division. It walks through mitosis, chromosomes and motor proteins.

An illustrated 23-minute summary of David Friedman's talk based on The Machinery of Freedom. It describes how law, police and courts could work as market services in a stateless society, covering private law, polycentric law and objections.

Yannic Kilcher walks through the Attention Is All You Need paper, which introduced the Transformer, a sequence model based solely on attention without recurrence or convolutions. He reviews the architecture and the paper's translation results.

3Blue1Brown's third deep learning chapter gives a visual, intuitive account of backpropagation and what happens to a neural network as it learns. A follow-up video covers the underlying calculus.

Robert Miles explains reward modelling, in which an AI learns what humans want from their preference comparisons instead of a hand-written reward function. He walks through the 2017 paper on deep reinforcement learning from human preferences.

Rob Miles explains on Computerphile how language models generate plausible text and how transformers improved on recurrent networks, with a look at what comes next.

agadmator walks through a game in which DeepMind's AlphaZero beat Stockfish, ending in a famous zugzwang that leaves the engine helpless. He gives commentary on the moves.

Two Minute Papers covers OpenAI's multi-agent hide-and-seek experiment, in which agents learned emergent tool use and found ways to break the game's rules. It summarizes the 'Emergent Tool Use from Multi-Agent Interaction' paper.

A Two Minute Papers episode on NVIDIA's recurrent denoising autoencoder, which cleans up noisy Monte Carlo path-traced image sequences. It shows how a neural network can produce usable renders from very few samples.

3Blue1Brown's chapter 4 on deep learning gives a more formal, symbol-based account of backpropagation calculus, connecting the intuition from the previous chapter to the math found in textbooks and code.

Two Minute Papers covers a paper on speeding up fluid and smoke simulation with convolutional networks. It contrasts the approach with earlier regression forest methods.

The first of four short videos from Bill Hammack (engineerguy) introducing and giving the history of a 100-year-old mechanical computer, Michelson's harmonic analyzer. The series goes on to explain Fourier synthesis, analysis and operation of the machine.

Ray Dalio's 30-minute animated video explains how the economy works through credit, debt, interest rates, and short- and long-term cycles. It is based on his template for understanding the economy.

Episode 4 of Mike Maloney's Hidden Secrets of Money, explaining how currency is created through a chain of IOUs among the Treasury, banks and the Federal Reserve. It covers bonds, Fed checks, debt, taxes and fractional reserve lending, from a gold-and-silver advocate's viewpoint.

A short Al Jazeera animation narrated by Amy Goodman presenting Noam Chomsky's five filters of the mass media: ownership, advertising, media elite sourcing, flak and a common enemy. It is part of the MediaTheorised series.

A short Harvard Online animation, narrated by Professor Rob Lue, showing how ATP synthase works inside mitochondria. It comes from the HarvardX Cell Biology: Mitochondria course.

Technology Connections takes apart a 1940s Sunbeam Radiant Control toaster. It senses the toast's own browning and lowers and raises it automatically using purely mechanical parts and no electronics.

Bill Hammack of Engineer Guy explains the engineering behind the aluminum beverage can: why it is cylindrical, how it is manufactured, why it narrows at the top, the double seam, and how the pull tab works.

Matt Parker talks Numberphile through the different kinds of numbers: algebraic, transcendental, computable, normal, and beyond. It shows how few numbers we can actually name or describe.

Mike Pound explains the discrete cosine transform and how it underpins JPEG compression. It is part two of Computerphile's JPEG series.

The 8-Bit Guy covers IBM's 1981 CGA graphics system, including how composite output and artifacting produced extra colors beyond the nominal palette. He argues CGA looked better in period than it does on RGB monitors.

An 11-minute animated introduction to P vs. NP and the wider landscape of complexity classes, inspired by the Complexity Zoo wiki. It assumes no background in computer science.

A 1936 Chevrolet-sponsored film that explains how a car transmission works by treating gears as spinning levers. It uses physical models to make the mechanism clear.

Bill Hammack of engineerguy uses slow motion video to show how the IBM Selectric typewriter works. He focuses on its fully mechanical digital-to-analog converter, which turns key presses into rotation of the type ball.

Everyday Astronaut explains the basic physics of rocket engines, the main engine cycles and fuel types, then compares SpaceX's methane-fueled full-flow staged combustion Raptor to other engines. It runs nearly 50 minutes with chapter markers.

Scott Manley explains the plumbing of rocket engines, including pressure-fed, gas generator, expander and staged combustion cycles. He shows why more complex designs exist and what they gain.

A Blender-animated explanation of the Toyota Hybrid Synergy Drive, showing how the engine, two motor-generators, planetary gearset and battery work together as an eCVT.

The 8-Bit Guy explains the color limitations of 1980s computers and consoles such as the NES and Commodore 64. It shows how sprites, attributes and palettes shaped the look of old games.

Tech Ingredients explains the principles of magnetohydrodynamics and builds several demonstrations, including propelling liquid metal and electrolytes with magnets and a railgun-style setup.

The first video in a series on extremely large numbers, introducing the topic with examples. Later parts go deep into the fast-growing hierarchy.

An MTA video on communications-based train control, the system meant to replace the New York City subway's century-old signaling. It also shows the mechanical interlocks and signals in use today.

An 8-minute explainer on the Lightning Network and how it relates to Segwit, Bitcoin and Litecoin. It covers how off-chain payment channels route payments to scale blockchain transactions.

Vsauce explores math through card tricks and big numbers, including an animation of how enormous 52 factorial, the number of deck orderings, really is.

An episode of Coding Secrets by Jon Burton on retro copy protection, in particular physically damaging a disk with a laser so copies fail. It explains how this defeated hackers and pirates.

Real Engineering explains the materials science behind metal 3D printing, including crystal structure, laser sintering, and why printed parts develop fatigue cracks. It shows how process imperfections limit the strength of printed metal.