NoticeThis site demonstrates one possible use of this domain. For acquisition, partnership, or investment inquiries, please use our contact form.

Library / Technical

Technical deep dives

The textbooks, courses, and surveys most worth your time if you want to genuinely understand how modern AI systems work.

The list is balanced across foundations, current frontier architectures, training, and interpretability. Most entries are free. Pair one textbook with one current paper for the fastest progress.

  1. 01

    Deep Learning

    Book
    Goodfellow, Bengio, Courville · 2016

    The free, comprehensive textbook on deep learning.

    Why read this. Foundational; still the standard reference.

  2. 02

    The Little Book of Deep Learning

    Book
    François Fleuret · 2023

    A 200-page modern introduction to deep learning in PDF.

    Why read this. The fastest way to refresh the maths.

  3. 03

    Stanford CS336: Language Modeling from Scratch

    Course
    Tatsunori Hashimoto et al. · 2025

    Build a modern LLM end-to-end across one semester.

    Why read this. Unmatched depth on the production stack.

  4. 04

    The Transformer Family v2

    Post
    Lilian Weng · 2023

    A 100-page survey-style post mapping transformer variants.

    Why read this. Best single-document reference for architecture choices.

  5. 05

    A Mathematical Framework for Transformer Circuits

    Paper
    Anthropic · 2021

    Foundational interpretability paper analysing 1- and 2-layer attention-only transformers.

    Why read this. Required reading for interpretability work.

  6. 06

    Scaling Laws for Neural Language Models

    Paper
    Kaplan et al. · 2020

    The original empirical scaling laws.

    Why read this. Explains why scaling is taken so seriously.

  7. 07

    Training Compute-Optimal Large Language Models

    Paper
    Hoffmann et al. · 2022

    Chinchilla rebalances compute toward more tokens.

    Why read this. Reset the field's understanding of optimal training.

  8. 08

    Reinforcement Learning: An Introduction

    Book
    Sutton & Barto · 2018

    The canonical RL textbook, free online.

    Why read this. RL is back at the centre of frontier training via RLHF and reasoning models.

  9. 09

    Spinning Up in Deep RL

    Course
    OpenAI · 2018

    OpenAI's pragmatic introduction to deep RL with code.

    Why read this. Best onramp into modern policy-gradient methods.

  10. 10

    Probabilistic Machine Learning

    Book
    Kevin Murphy · 2022

    Two-volume modern probabilistic ML textbook, free online.

    Why read this. Deep statistical grounding most ML curricula skip.

  11. 11

    The Annotated Transformer

    Post
    Harvard NLP / Sasha Rush · 2018, updated 2022

    The original Transformer paper, line-by-line with executable code.

    Why read this. Learn by running, not just reading.

  12. 12

    Foundations of Diffusion Models

    Paper
    Calvin Luo · 2022

    A clean tutorial on the mathematics behind diffusion models.

    Why read this. Best single document for diffusion intuition.

  13. 13

    Karpathy: Neural Networks Zero to Hero

    Course
    Andrej Karpathy · 2022–2024

    Code-along video series from autograd to GPT.

    Why read this. Builds intuition no textbook can.

  14. 14

    Sparse Autoencoders Find Highly Interpretable Features

    Paper
    Cunningham et al. · 2023

    Demonstrates that SAEs extract monosemantic features from language models.

    Why read this. The breakthrough behind modern mechanistic interpretability.

  15. 15

    Survey of LLM Reasoning

    Paper
    Sun et al. · 2024

    Survey of reasoning methods, including chain-of-thought, search, and verifier-based approaches.

    Why read this. Catch up on the reasoning-model wave.