“A complete walkthrough of how large language models like ChatGPT are built — from raw internet text to a conversational assistant. Based on Andrej Karpathy’s technical deep dive. Built from Andrej Karpathy’s “Intro to Large Language Models” lecture — all facts, figures, and framings traced back to that source. Interactive visualizations built with AI assistance. The most important takeaway: every word generated is a probabilistic sample — a biased coin flip, at 100K-way scale, billions of times. This was posted to Hacker News and drew heated debate about it being LLM-generated. That’s a fair observation — the implementation was AI-assisted. But the content isn’t the AI’s: every claim, figure, and framing in this guide comes directly from Karpathy’s lecture, not from a model hallucinating about LLMs.”

• HN discussion · GitHub · Full lecture transcript · HN update note · LLM council report · v1 (original) · Part 2: How to Use LLMs →