machine learning

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.

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.

3Blue1Brown's visual explanation of how transformers and GPT-style language models work, tracing data through tokens, embeddings and attention.

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.

Johnny Harris investigates why McDonald's ice cream machines are so often broken, covering the Taylor machines, the repair restrictions on franchisees and the Kytch workaround device.

Technology Connections takes apart the step-by-step electromechanical logic of a 1970s pinball machine. He shows how relays, steppers and switches track state and score without electronics.

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.

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.

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.

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.

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.

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.

Jared Owen's 3D animated breakdown of how a Brunswick GS-X bowling pinsetter works, showing its mechanisms for sweeping, lifting and resetting pins and balls.

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.

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.

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.

A Business Insider World Wide Waste episode on H&M's garment recycling machines, which turn used clothing into new apparel. It asks whether a fast fashion company can solve the waste problem it helped create.

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.

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.

Veritasium traces analog computers from the Antikythera mechanism and Kelvin's tide-predicting machines to fire control and modern analog approaches. It explains how these machines computed continuously rather than digitally.

Asianometry explains the EUV light source inside ASML's lithography machines, where lasers hit falling tin droplets twice to produce 13.5 nm light. It walks through the engineering of the droplet generator, the pre-pulse and main laser, and the plasma that results.

Technology Connections explains how the simple American drip coffee maker works, including the bimetal valve and bubble-pump heating, and compares the original Mr. Coffee with modern machines.

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.

Linus Tech Tips reviews the first Framework Laptop, a fully repairable and upgradeable machine. The reviewer expected a flimsy chunky device and was happily surprised.

Steve Mould shows Spintronics, a set of mechanical components such as resistors, capacitors and transistors linked by chains, that give an intuitive feel for how electrical circuits work.

2swap explores lambda calculus using John Tromp's lambda diagrams, with animated beta-reductions, asking what PLUS times PLUS gives. It touches on Church encodings and the equivalence of Turing machines and lambda calculus.

Steve Mould explains motion amplification and video magnification, techniques that find tiny changes in video invisible to the eye and exaggerate them. He covers the MIT research and industrial uses such as diagnosing vibrating machinery.