Part 3 - Large Language Models

Large Language Models (LLMs) are arguably the most transformative development in AI in the last decade. Built on the transformer architecture, LLMs have moved from research curiosities to indispensable tools used daily by millions of people for writing, coding, analysis, and creative work.

We start with an introduction to the transformer architecture, self-attention, tokenization, and the training techniques that produce modern LLMs. We then move to practical chapters: using LLMs through cloud APIs from Google Gemini and OpenAI, and running open-weights models locally on your own hardware with Ollama.