learning

Martin Gorner's Devoxx talk introduces deep learning with TensorFlow, walking through neural networks for MNIST, how to choose an architecture and how to diagnose networks that fail to train.

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.

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.

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.

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.