language learning

Andrej Karpathy builds a bigram character-level language model from scratch, introducing torch.Tensor and the framework of training, sampling and loss evaluation. It is the first step toward a GPT-style Transformer in his makemore series.

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.

Ben Eater writes a program in a made-up machine language and walks through the control logic an 8-bit breadboard CPU needs to execute it. It is part of his build-an-8-bit-computer series.

British Museum curator Irving Finkel teaches how to write cuneiform, with a colleague following along. It is a short, lively introduction to the script.

The first of a short series by Welch Labs on building a complete neural network in Python. It introduces the data and the architecture of a simple network before later parts cover forward propagation, gradient descent, and backpropagation.

A 1930s Chevrolet training film explaining the principles and development of the differential gear. It builds the idea step by step from first principles to the finished mechanism.

David Beazley's PyCon 2019 tutorial derives the lambda calculus from the ground up in Python, using only single-argument functions. He builds booleans, numerals and more with no other language features.

Jon Gjengset's long live-coding stream explains Rust's Pin and Unpin types: why they exist, how they work, and how they connect to futures and async/await. It also covers moving from pre-pinning code to the new model.

Harry Schwartz gives a roughly hour-long tour of Emacs Org mode as an outliner, task manager, markup language and agenda tool. He demonstrates how he uses it for documents, presentations and todo lists.

Markus Triska tours Prolog's most distinctive features, including its use as a database and query language, rule processing, constraint solving and compile-time rewriting. It also covers concise meta-interpreters.

Jon Gjengset's long live-coding Crust of Rust episode on async/await, focused on the mental model for using it rather than on Futures, Pin and Wakers internals. Topics include awaiting multiple futures, cancellation, executors and select.

A screencast showing how to use the fzf command-line fuzzy finder in the shell and in Vim. It covers searching files and also using the Vim plugin for help tags, buffers, lines and grep matches.

LifebyMikeG lists 15 common mistakes beginner sourdough bakers make, with advice on fixing sticky, wet dough and other issues.

Wim Hof guides viewers step by step through his breathing method, with some explanation of the science he cites behind it. It stresses learning from the source and avoiding unsafe settings.