optimization

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.

Matthias Wandel tests old and new code on a range of PCs, including a new mini PC, to measure how much faster modern hardware really is. He also shows optimization techniques such as branchless code, with benchmark programs on GitHub.

Kaze Emanuar searches for the best sine approximation for the Nintendo 64, comparing the lookup tables in Mario 64 and Ocarina of Time with polynomial alternatives. It walks through numerics and 3rd, 4th and 5th order approximations.

Matt Parker follows the community effort to speed up his slow Wordle-solving code, which ended up running hundreds of millions of times faster. He walks through the techniques contributors used.

Wes Bos breaks down the techniques behind the McMaster-Carr website's speed: server-rendered HTML, prefetching, CDN and service worker caching, preloading, critical CSS and fixed-size images. He also notes its old-school jQuery and YUI JavaScript.

A walkthrough of the Quake III fast inverse square root, explaining where the constant 0x5f3759df comes from. It covers IEEE 754 floats, the bit hack that approximates a logarithm, and a Newton's method refinement.

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.

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

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 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.

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.

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

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 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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

3Blue1Brown visualizes high-dimensional spheres to explain a surprising puzzle about how a sphere fits in a box as dimensions grow. It builds geometric intuition for counterintuitive properties of high-dimensional space.