History and Development of LLMs

This enables junior developers to understand the entire development process from planning to code writing, deployment, and validation by using artificial intelligence as a development tool, allowing them to survive and thrive in the AI era by acquiring the full-spectrum capabilities needed.

Describes the need for LLM, its technical background, and basic concepts.

This lecture is designed for understanding even if you have no prior knowledge of what Secure Coding (Security Coding) is. After covering basic security coding concepts, it focuses on web service security. This was a special lecture presented under the auspices of OO University. It presents over 160 source codes with rich comments, pinpointing core topics and techniques immediately applicable in practice.

This course is a systematic learning process for prompt engineering, which is a core technology for effectively utilizing large language models (LLMs) or generative artificial intelligence. It covers a wide range of topics from basic theory to practical techniques, as well as the latest application cases and security/ethical issues, providing practical help to LLM-based service developers, data scientists, and AI planners alike.

You can quickly understand C language's basic concepts and grammar.

Explains the basic principles of large language models like ChatGPT, focusing on theory.

Now is the era of development using AI. To create better, more accurate code and documents by better utilizing AI, methods are needed, so we propose suitable ones.

👨‍🍳 Like cooking code, neatly and deliciously! 『Clean Coding』 is a code cooking class for chef-like developers, where they joyfully learn clean coding through a cooking analogy. 🍽️

Problematization (문제화) is a term also translated as problem posing, problem framing, problem setting, or problem definition. This concept involves questioning known facts (like requests or common sense) from a new perspective, defining the problem, and devising methods to solve it. Problematization should be the starting point for all development, yet it remains insufficiently discussed within the field. Performing projects or developing programs is, in essence, planning to solve problems. This means they are related to problematization. To solve a problem, it must first be clearly defined. However, problems are mostly presented as vague requests. Therefore, the ability to transform vague requests into clear problems is essential to reduce unnecessary 'development waste,' facilitate smooth collaboration, and accurately grasp users' true needs. This lecture helps train 'the thinking of problem construction' through practical examples and tools.

What should be done when building a generative AI or LLM-based RAG (Retrieval-Augmented Generation) system, but the desired performance isn't achieved and there's no suitable solution? This lecture presents methods to improve RAG performance based on Cognitive Load theory. Through this lecture, you will understand the limitations of LLM context windows and learn how to effectively manage cognitive load in RAG systems. It is a practical-level theoretical lecture covering Chunk size and structure design, high-quality Chunk generation techniques, dynamic optimization, performance evaluation, and practical techniques.

You can learn the concepts and methods of 'service design' necessary when planning applications or web services based on LLMs, a type of generative artificial intelligence (generative AI).

"One name change, code transformed." "The key to readable code, 'naming for readability,' summarized from principles to examples." "Easy-to-read names begin collaboration."

We create an AI judge by combining CrewAI, facilitating LLM-based multi-agent technology, with knowledge graphs and inference systems.

We will examine methods for collecting and analyzing user requirements to plan LLM services.

We explore the limitations of LLMs, methods to overcome them, and the latest research topics.

Let's explore the types of applications or web services that can be built using LLMs.

Describes the need for LLM, its technical background, and basic concepts.

We will learn step by step from the basic concepts of LLM (Large Language Model) to how to fine-tune the Llama 2 model, a high-performance LLM, on the dataset of your choice.

This is a course to master the core technologies of LLM basic theory, LangChain, and RAG. You can easily learn the latest AI technologies used in practice, from LLM basics!

This course will teach you the concept of the Google Gemini model and how to use the Gemini API, and create various AI applications using Streamlit.

RAG (Retrieval-Augmented Generation) from theory to the latest multimodal and agent-based RAG! This is a hands-on lecture designed to be understandable even for non-majors. From paper reviews to practical code implementation, it's designed so that even those encountering RAG for the first time can easily follow along.

"An introductory hands-on course for creating domain-specific customized LLMs with LoRA-based lightweight fine-tuning!" You can now create customized LLMs yourself. This course is designed to help you easily learn the process of creating domain-specific LLMs through LoRA-based lightweight fine-tuning practice, without complex theory. Even those handling LLMs for the first time can follow along, as we guide you step-by-step through the entire process: loading models → inputting data → training → comparing results. Learn the latest techniques for creating LLMs specialized in specific fields with minimal resources through direct hands-on practice!