5 free courses — Math for LLMs, Python, C, C++, and Rust — each built from first principles, one short lesson at a time.
Courses
Each track stands on its own. Start at lesson one, or jump straight to the topic you need.
Linear algebra, calculus, probability, and optimization — taught through transformers, VAEs, and modern deep learning.
The lingua franca of AI. Data structures, OOP, and scientific computing — built from first principles.
Understand memory, pointers, and how computers actually work. Low-level intuition every serious engineer needs.
Modern C++ for high-performance systems. STL, memory models, and production-grade engineering patterns.
Memory safety without a garbage collector. Ownership, traits, async, and systems programming from first principles.
Papers
The ideas that shaped modern machine learning. Each paper links to the lesson that works through its math.
The seminal transformer architecture replacing recurrence and convolutions entirely with self-attention mechanisms.
Adaptive moment estimation optimizer combining benefits of RMSProp and momentum, computing individual adaptive learning rates.
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale - applying Transformers directly to image patches for vision tasks.
Framework for estimating generative models via an adversarial process.
Blog
Long-form analysis of AI models, the labs that build them, and where the field is heading.
When the U.S. government ordered Anthropic to pull its most powerful AI model offline — and why the internet thought it was a video game.
Read article →How a group of OpenAI defectors built the most important AI company of the decade — and what their journey tells us about the future of intelligence.
Read article →Pick a track and open the first lesson. Everything is free — no sign-up, no account.
Browse courses