It’s great to be able to hear the examples and explanations together. Thank you.

It’s a lecture that’s easy to follow if you have even a basic understanding of data structures! The explanations were clear, and it was easy to keep up. I’ve been considering introducing Valkey in practice, and this was very helpful!

A brilliant lecture that organizes intuition-driven LLM quality management using numbers and code While developing LLM services, I was always concerned about how difficult it was to clearly verify whether the quality of responses had genuinely improved or whether something had broken elsewhere whenever I changed a prompt or model. This lecture systematically covers everything from rule-based scoring and LLM-as-a-Judge to bias prevention and building a regression testing pipeline before deployment, going beyond simple API calls. In particular, I was able to gain a solid understanding of the underlying principles by implementing an evaluation harness from the ground up in a local environment, without relying on external paid APIs or heavyweight frameworks. I highly recommend this essential course to engineers who want to deploy and operate LLM features reliably at a production level.

This is the best course for truly understanding the underlying principles beyond simply using APIs. Even though I had been using LLM and embedding APIs, I had always wanted to understand exactly what mathematical and structural principles were at work under the hood. Starting with text preprocessing, this course guides you through implementing Word2Vec, automatic differentiation, the Transformer architecture, and even a mini GPT directly from scratch in code, helping you fully grasp how AI works. Even complex and difficult concepts are explained clearly and intuitively, allowing me to stay engaged and complete the course. I highly recommend it to anyone who wants to understand the fundamental principles underlying models rather than merely using libraries.