liquid networks

A five-minute animated explainer of liquid democracy, in which voters can delegate their vote to trusted people. It starts from the origins of democracy and contrasts direct and representative models.

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

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

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.

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.

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.

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.

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.

Engineering Explained examines BMW's Hydrogen 7, a V12 that burns liquid hydrogen or gasoline. He covers cryogenic storage at -253C and why the approach is impractical.

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.

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.

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.

Veritasium explains how trees lift water from roots to the top of tall trunks, using transpiration pull and the negative pressure that liquid water can sustain. It explains why trees do not need pumps or valves.

Benn Jordan explains how Flock Safety's license plate cameras log and share vehicle locations, and explores how adversarial AI can defeat them. It covers weak security and the surveillance risks of private police-camera networks.

A 2011 remix of over six hours of talks by Kirk Sorensen and other thorium advocates, explaining thorium as a nuclear fuel and the liquid-fluoride thorium reactor (LFTR). It argues LFTRs could produce energy without long-lived transuranic waste.

An Economics Explained video on the different kinds of billionaires, from founders to oligarchs. It explains how wealth is held in illiquid stock and why diversification is a problem for some.

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.

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.

A Vox explainer from the 2020 election series on why American public transit is so poor. It traces the effect of the interstate highway system on cities and the resulting car dependence.

A four-minute minutephysics video arguing that causal models and causal networks let statistics infer causation from correlation. It touches on Reichenbach's principle, common causes, feedback and quantum causal discovery.