Dive into LLMs vs How LLMs Work

Dive into LLMs is a structured LLM programming tutorial series from Shanghai Jiao Tong University covering fine-tuning, RLHF alignment, RAG pipelines, jailbreak attacks and defenses, watermarking techniques, GUI agents, and multimodal models. Each module includes slides, Jupyter notebooks with runnable code, and accompanying video lectures. The curriculum is designed for developers and researchers who want to go beyond prompt engineering into actually understanding how large language models work, how they're trained, and how to modify and deploy them. Topics span from transformer fundamentals through modern alignment techniques like DPO and GRPO. Recent additions cover GUI agents and multimodal architectures. The course has partnered with Huawei's Ascend community for localized deployment content. With 29k+ GitHub stars and trending hard today, this is one of the most-starred educational resources in the LLM ecosystem. Unlike blog posts and YouTube tutorials, the Jupyter notebooks mean you can run and modify every example yourself — making abstract concepts like RLHF tangible in a way that passive reading can't match.

"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.