educational

An open-source book that builds the mathematical foundations of large language models, covering linear algebra, calculus, probability, and transformer architectures, with over 1000 pages of clear explanations and practical examples.

A tweet announces a GitHub repository that decodes Claude Code's architecture using source maps, providing an educational 18-chapter book on the internals of Anthropic's AI coding agent.

This paper presents MiniGPT, a compact from-scratch implementation of GPT-style autoregressive language modeling in PyTorch, built after studying nanoGPT. It evaluates the model on the Tiny Shakespeare dataset using character-level tokenization, achieving a validation loss of 1.4780 with a 10.77M-parameter configuration.

A tweet highlights that Citadel pays quants $800K/year for skills in probability theory and PDEs, and recommends an MIT lecture on stochastic differential equations.

Discovered an open-source GitHub project hello-agents, which organizes a complete open-source course from theory to practice on AI Agents, covering core skills like Agentic RL, SFT, GRPO, and has reached the top of GitHub trending.

A free interactive tool called Transformer Explainer runs a live GPT-2 model in the browser, visualizing the internal workings of Transformers with a Sankey diagram and live inference.

A collection of 333 hours of Q&A footage with astronauts, offering extensive educational content about space and astronaut life.

This article from Harvard's CS 61 course covers Unix concepts of pipes, forks, and zombies, explaining how pipes automatically kill programs on closure and how to use pipes to implement blocking waits on child processes.

A blog post guides readers through setting up a Raspberry Pi cluster for distributed training and inference, part of a series aimed at making distributed AI accessible using affordable hardware.

LLMs-from-scratch is a GitHub repository that accompanies the book "Build a Large Language Model," providing complete code to implement GPT from scratch with PyTorch, covering the full pipeline including pretraining, fine-tuning, and RLHF. It has gained 93K+ stars and is ideal for developers who want to deeply understand the principles behind large language models.

Tiny-Lua-Compiler is an educational, self-hosting Lua 5.1 compiler and VM written in pure Lua, designed to be small enough to study but complete enough to handle real language features.

This guide explains the end-to-end inference pipeline of LLMs, serving as a mock interview resource for understanding text generation.

The article presents an elegant geometric proof for Buffon's Needle problem by extending the concept to curved 'noodles' and using a circle to determine the probability constant, avoiding complex integrals.

This article explains Behavioral Cloning, an imitation learning technique used to train policies from expert demonstrations, discussing its theoretical basis in maximum likelihood estimation and its historical applications like AlphaGo.

A GitHub repository providing visual and simple explanations of complex system design concepts, covering topics like APIs, load balancing, HTTP, and networking.

A comprehensive, free, open-source AI engineering curriculum with 428 lessons across 20 phases, covering math foundations to autonomous swarms in Python, TypeScript, Rust, and Julia.

The repository provides open-source code to build, pretrain, and fine-tune a GPT-like large language model from scratch, serving as the official code companion to Sebastian Raschka's book of the same name.

Datawhale社区发布的开源中文教程《从零开始构建智能体》，系统性讲解AI原生智能体的理论与实践，涵盖从基础原理到自研框架HelloAgents的完整学习路径。