educational

A YouTube video demonstrating how to build all Linux file utilities from scratch in C by hand in 52 minutes, without using AI assistance. Shared via Lobsters with discussion from the developer community.

BBRouter 是一个在 3D 面包板上模拟 Ben Eater 经典 8 位 SAP-1 计算机的网页工具，用户可以交互式地点击按钮、元件和孔位来逐步搭建和学习。

Part 6 of an open-source Inference Engineering repo is released, covering KV cache memory allocation, growth, release, and capacity-aware scheduling using real model inference and DynamicCache.

GuppyLM is a small ~9M-parameter language model that can be trained from scratch in 5 minutes on a single Colab notebook. It simulates a fish named Guppy talking about water, food, and light, aiming to prove that training your own language model isn't magic — it's something anyone can do.

A minimal, self-contained manual autograd implementation for a transformer-based classifier in PyTorch, designed to build intuition for how autograd works under the hood and how gradients flow through attention blocks.

A free online book and GitHub repository, 'Harness Engineering 101', that teaches how to build AI agents from first principles — treating the LLM as the brain and the surrounding harness program as the body, across 16 chapters with a growing ~300-line Python toy agent.

A university lecture (CS 463) explaining how Galois finite fields GF(2^8) underpin the Advanced Encryption Standard, covering field addition as XOR and polynomial-based multiplication for substitution tables.

ai-agents-zero-to-hero is a zero-dependency, pure Python educational framework that teaches AI agent fundamentals from first principles through to production, covering the agent loop, tool calling, memory, and runtime harness.

该推文总结了优化 LLM 推理的 12 种 KV 缓存技术，包括滑动窗口、跨层共享、MLA、量化、前缀复用、分页、驱逐和 GQA/MQA 等，帮助开发者根据具体瓶颈选择合适的组合。

A tutorial-style walkthrough for software engineers that formalizes a constructive proof about regular languages in the Lean theorem prover, explaining specification, implementation, induction, and the anatomy of a formal proof step by step. The piece demonstrates how Mathlib's existing theorems make formalizing textbook automata theory accessible to developers.

This article clarifies the confusion between Agent and Harness in the AI field, proposing the formula Agent = Harness + Model to aid understanding.

GitHub hosts several high-star open-source guides that provide free advice on life optimization, financial management, and English learning, making valuable knowledge accessible to everyone.

感谢读者 LiNan1984 将《深入理解 AI Agent》提炼为 22 项技能，方便代理开发和人类阅读。

OpenTrainDNN is an open-source, client-side web application that provides real-time visualization of deep neural network training, including backpropagation and weight updates, directly in the browser.

Prof. Tom Yeh shares a PDF with math problems on agentic AI topics like token costs and system prompts, encouraging manual solving for learning.

The article explores mathematical billiards, including varieties like inner billiards, and discusses using computer experiments to study trajectories in dynamical systems.

The book 'Hands-On Large Language Models' offers a comprehensive, open-source guide to large language models with runnable code on Colab, covering topics from basics to multimodal applications.

The author announces the physical release of their book 'The Secret Life of Circuits', a full-color hardcover guide to modern circuit design and problem-solving.

MIT professor Peter Shor gives advice to aspiring computer scientists in a throwback video shared by MIT_CSAIL.

MIT CSAIL shares a beginner's guide to statistics, providing foundational educational content for data science and AI.