Topics / ai-models

AI models

How neural networks learn from data and get shaped into assistants, and the architectures that turn text, images and sound into predictions.

Dives
6
Levels
53
Notes
1
Reading
4.1h
Start with Training
How to read thisEvery line is a diveEach tick is one level, drawn at the layer of the stack it explains. Longer lines go further down, from why a thing exists to the silicon that runs it.6 dives · 53 levels

The path

Read in this order and each dive leans on the ones before it. Every dive also stands on its own.

  1. 01

    How a neural network learns, from loss to all-reduce

    Turn prediction errors into gradients, build a tiny autograd engine, and train a real network in your browser. Then follow one weight update through optimizer memory, GPU collectives, pipeline schedules and the compute budget of a language model.

    Idea to Silicon

    45 min9 levels

  2. 02

    From base model to assistant: post-training

    Follow one coding request through chat templates, supervised fine-tuning, preference learning and reinforcement learning, down to the log-probabilities and memory that make it work.

    Idea to Machine

    40 min9 levels

  3. 03

    Mixture of experts, from router to all-to-all

    Follow a token into a sparse expert layer: router scores, balance and capacity, expert parallelism, token permutation, and the memory traffic behind conditional computation.

    Idea to Silicon

    42 min8 levels

  4. 04

    Vision models, from pixels to an answer

    A receipt says $12.50. Follow its pixels through tensors, patches, attention and a language model to see how an image becomes evidence for an answer.

    Idea to Machine

    38 min9 levels

  5. 05

    How a speech model hears

    Say “We see a cat.” Follow the air pressure through samples, Fourier transforms, mel filters and a Whisper decoder, all the way to the bytes and arithmetic that turn sound into text.

    Idea to Machine

    38 min9 levels

  6. 06

    Diffusion models, from noise to an image

    Turn noise into structure with a real diffusion sampler, then follow an image through denoising, guidance, latent patches and the GPU arithmetic behind every step.

    Idea to Machine

    42 min9 levels

Notes

Practical answers in ai models.

  1. Note3 min read

    Transcribe audio locally with word timestamps

    Use faster-whisper with word_timestamps and VAD, consume its segment generator, and preserve source-time offsets. Choose model size and compute type for your machine.