Technical books you can read online for free

Learn the math and intuition behind machine learning algorithms, then implement them in Python

Machine Learning from Scratch is for readers who want to see how algorithms actually work. We derive each method from the math, build the intuition step by step, and implement it in Python so you can inspect every decision.

Start with classical NLP, then work through transformers, LLM training, evaluation, and production

The Language AI Handbook connects the pieces of modern language AI. We begin with classical NLP, build up to transformers and LLM training, then cover retrieval, evaluation, safety, and production deployment.

Build a small GPT in PyTorch, one step at a time, from transformer math to training and text generation

Build a GPT from Scratch takes one small language model from text input to generated output. We work through each tensor operation, connect it to the underlying math, and implement the model in readable PyTorch.

Learn how AI systems represent state, predict dynamics, imagine futures, and choose actions, from classical control to foundation world models

The World Models Handbook explains how an intelligent system can build an internal model of its environment, update that model from observations, use it to imagine possible futures, and choose what to do next. It connects ideas that are often taught separately across control, reinforcement learning, robotics, generative modeling, and cognitive science.

Learn how to build reliable AI agents with reasoning, memory, tools, evaluation, and production safeguards

The AI Agent Handbook shows how the parts of an agent work together in production. We cover reasoning loops, memory, tools, evaluation, safety controls, multi-agent coordination, and observability, with a focus on reliability.

Follow the history of NLP and language models, from information theory and symbolic AI to transformers and LLMs

The History of Language AI traces the people and ideas behind modern language models. We follow the field from information theory and symbolic programs through neural networks and transformers, explaining what each breakthrough changed.

Learn quantitative finance from pricing and portfolio construction through backtesting, execution, and production systems

Quantitative Finance connects mathematical finance with the work of researching, testing, and running trading strategies. We move from pricing and portfolio construction through calibration, backtesting, risk, execution, and production.