ml

A one-hour OCaml Workshop 2020 talk on the state of the OCaml Platform, covering IDE support, next steps for the tooling and plans for 2020-2021.

CNBC gets a tour of ASML's cleanrooms in the Netherlands to see how its roughly $200 million EUV lithography machines are built. It covers exploding molten tin, ultra-flat optics and why only one company can make these systems.

ASML's short promotional fly-through of its High NA EUV lithography platform, the TWINSCAN EXE, which supports 8-nanometer resolution. It shows the machine's internals including advanced anamorphic optics.

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.

David Guillot describes how his team replaced a two-year-old React UI of their SaaS product with Django templates and htmx in a couple of months. The talk gives concrete indicators on code size, performance and team impact.

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.

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.

A 38C3 talk on how advanced chips are made, centered on EUV lithography and the global supply chain behind it. It covers technical challenges from raw materials to finished chips and the geopolitical weight of semiconductors.

Ilya Sutskever gives a Simons Institute talk on why neural networks generalize, framing learning as finding short descriptions, like compression. It was part of the Large Language Models and Transformers program.

A Ray Summit 2022 keynote fireside chat between OpenAI's Greg Brockman and Anyscale's Robert Nishihara. They discuss how OpenAI's training infrastructure evolved and its use of Ray.

A 2023 LLVM Developers' Meeting keynote by Abdul Dakkak, Chris Lattner and Jeff Niu introducing Mojo, a Python-family systems language built on MLIR and LLVM for heterogeneous computing.

Andrej Karpathy, then Tesla's head of AI, presents at ScaledML 2020 on how Tesla builds full self-driving using vision-based neural nets and fleet data collection. He covers training custom detectors and neural nets gradually replacing traditional code.

Tom Scott-style absurdist research by tom7 for SIGBOVIK 2021, using machine learning to discover letterforms that are 'uppercaser' than uppercase A and lowercaser than lowercase. It is a comedic, technically inventive deep dive with fonts and a paper.

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.

Lex Fridman's long conversation with Andrej Karpathy on Tesla's self-driving approach, Optimus, neural networks, transformers, AGI and more. It also touches on his OpenAI work and working with Elon Musk.

Sasha Rush surveys linear RNNs and state space models as replacements for attention in transformer-style models, in a talk for MLSys. It covers the foundational preliminaries and predates Mamba.

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.

A five-minute video showing how to build a counter in the Imba web programming language in under a minute, then style it.

GothamChess walks through AlphaZero's famous games against Stockfish, highlighting its unusual pawn sacrifices and positional style. It is aimed at chess fans rather than ML specialists.

Chris Lattner's ASPLOS 2021 keynote on the golden age of compiler design in an era of hardware and software co-design, covering compiler infrastructure for accelerators and unifying hardware IRs.

Hobbyist Wesley Kagan shows his Miata running and driving with a homemade version of Koenigsegg's freevalve camless valve technology. The build uses open CAD files and code and he describes it as an ongoing work in progress.

Developer Voices interviews Chris Lattner about Mojo, a Python-compatible language aimed at CPU/GPU performance built on LLVM and MLIR. It covers performance features, the type system and why Mojo uses Python syntax.

EposVox reviews a very cheap USB 2.0 HDMI capture dongle sold under names like BlueAVS/Goodan, testing whether it works as an alternative to the Elgato Cam Link. He covers its quality and limits for webcam-style and camera capture use.

Stuff Made Here builds a powder-actuated baseball bat designed to hit a ball past Babe Ruth's record distance, with Smarter Every Day contributing. It covers the engineering of the explosive-assisted swing.

Andrej Karpathy's first Neural Networks: Zero to Hero lecture, which builds micrograd, a tiny autograd engine, from scratch in Python. It explains backpropagation and neural network training step by step, assuming only basic Python and some high-school calculus.

Rich Hickey's Strange Loop 2011 keynote distinguishing 'simple' (not intertwined) from 'easy' (familiar or near at hand). It argues that software complexity comes from complecting things and that we should pick simple constructs.

Feature-length documentary following DeepMind's AlphaGo program as it prepares for and plays the 2016 match against Go champion Lee Sedol. It covers the team, the games, and the emotional reaction of the Go world to an AI beating a top human.

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

Andrej Karpathy's three-hour-plus general-audience deep dive into how ChatGPT-style LLMs are built, covering the full training stack from pretraining to post-training. It also gives mental models for their quirks, like hallucination, and how to use them well.

Rich Hickey's Strange Loop 2011 keynote separates 'simple' (not intertwined) from 'easy' (familiar or near at hand) and argues that software complexity comes from complecting things. It offers a vocabulary for judging designs and abstractions.

Lex Fridman interviews legendary chip architect Jim Keller about Moore's Law, microprocessor design, and first-principles thinking. Keller draws on his work at AMD, Apple, Tesla and Intel, discussing instruction sets, transistor budgets, and self-driving.

Andrej Karpathy builds a GPT from scratch in code, following Attention Is All You Need and GPT-2/3, in about two hours using PyTorch. He connects it to ChatGPT and assumes familiarity with his earlier makemore videos.

Jeremy Howard's 90-minute practical tour of language models. It covers how they work, GPT-4's capabilities and limits, using the OpenAI API, code writing, data analysis and fine-tuning.

Chuck Moore, inventor of Forth, presents GreenArrays' 144-core asynchronous chip at Strange Loop 2013. He explains how idle cores draw almost no power and how tight code minimizes energy use.

Jack Rusher's Strange Loop 2022 talk argues that most programming languages are still designed around punchcard-era assumptions. He makes the case for live, interactive programming environments, drawing on Lisp, Smalltalk and REPL-driven development.

Veritasium tells the story of how Shuji Nakamura and others made the blue LED, long thought nearly impossible. It covers the materials challenge of gallium nitride and the persistence it took.

Andrej Karpathy gives a one-hour general-audience introduction to large language models, covering what they are, how they are trained, comparisons to operating systems, and security challenges such as jailbreaks.

Lex Fridman has a three-hour conversation with Joscha Bach about artificial consciousness, the workings of the mind, intelligence and the possibly simulated nature of reality.

Phoenix creator Chris McCord builds a real-time Twitter-style app live with Phoenix LiveView 1.5 in about 15 minutes. It shows interactive, real-time updates without writing JavaScript.

Valve's John McDonald presents at GDC 2018 on how Valve uses deep learning (VACnet) to detect cheaters in Counter-Strike: Global Offensive. He covers training on human-reviewed replays and how model output is confirmed by manual review.