AI Agents for Beginners vs How LLMs Work

AI Agents for Beginners is a free, open-source curriculum from Microsoft with 12 Jupyter notebook lessons covering how to build AI agents from first principles. Topics include tool use, memory architectures, multi-agent orchestration, planning patterns, and evaluation — implemented with practical code examples across multiple frameworks. The repo has accumulated over 57,000 GitHub stars and is trending again today with 131+ new stars in 24 hours, suggesting a new lesson drop or curriculum update. It's positioned as the entry point for developers who want to understand agent architecture without getting lost in framework marketing — each lesson teaches concepts with runnable code rather than abstract diagrams. For the AI education space, this repo has become the de facto starting point the way CS50 was for general programming. Its open license means bootcamps, universities, and companies are incorporating it into training programs, which explains the sustained star velocity months after launch.

"How LLMs Work" is a free, browser-based interactive guide that walks through the complete pipeline for building large language models — from raw web scraping to RLHF-trained conversational assistant. Created by Yash Narwal and based on Andrej Karpathy's technical deep-dive lecture, it's been getting significant traction on Hacker News (214+ points) for turning dense ML theory into something genuinely accessible. The site covers data collection and deduplication, Byte Pair Encoding tokenization with a live demo, pre-training and next-token prediction, inference with a probability sampling simulator, post-training with RLHF, and RAG. Each section uses animated visualizations, clickable pipeline diagrams, and canvas-based graphics — not static explainer images. The progressive narrative structure follows a single piece of text through every stage of the pipeline, making abstract concepts concrete. In an era where everyone uses LLMs but few understand how they work, this kind of high-quality educational resource matters for a different reason than tools: it raises the baseline competency of the entire developer ecosystem. Better-informed builders ask better questions, make better design decisions, and push vendors toward more transparency. This is the kind of project the HN community rewards — and deserves the signal boost.