How far has generative model tuning come? - Langcon 2024

An AI that understands Korean well, handles long documents, and even carries out real-world tasks—that is exactly the direction Solar Open 2 is aiming for. This class provides an accessible explanation of Upstage’s Solar Open 2 technical report in the order of “Introduction → Design → Training → Evaluation.” Technical terms are explained through everyday analogies and visual materials, enabling even beginners to understand “what,” “how,” and “why” as one coherent flow.

Do you know the basics but feel overwhelmed when it comes to applying them in practice? Drawing on real-world experience, we make complex LLM architectures easy to understand.

👉 A starting point for those who want to properly understand AI for the first time. If you understand what AI does but aren’t quite sure why it works the way it does, this is the course to start with. In this course, we’ll explain step by step, from the beginning, how artificial intelligence differs from traditional programs and how learning and decision-making take place. Without complicated equations or coding, the course is designed to help you understand the big picture of how AI works.

👉 This course is ideal for those who want to properly understand how AI changes and its limitations. Is AI finished once it’s created? This course explains how AI changes through learning and why the results can differ even with the same AI. It clearly explains the meaning of the learning process and the technical reasons why performance may improve or decline.

If you ask an AI to "build a model with this data," the first few lines might look plausible, but as soon as things get slightly complex, it starts using the wrong columns, introduces data leakage, and results in a model that performs worse despite a higher score. This course does not teach you better prompts. Instead, it covers how to directly design a loop (harness) where an agent understands data, plans, writes code, validates its own results, and backtracks when wrong. After manually walking through the five-piece loop of DS-STAR, you will assemble components one by one, from data profile cards, hooks, and skill hierarchies to independent validators and ablation.

The era of AI simply providing answers is over. Now is the age of LLM Agents that make decisions and take actions on their own. This course is an introductory lecture where you learn the core principles and structure of agents by implementing them yourself in just 90 minutes of hands-on practice. With minimal complex theory and a code-focused practical flow, you can directly experience "how AI makes decisions and uses tools." Beyond prompt engineering, let's take the first step into AI automation together.

You use ChatGPT, but haven’t you found it difficult to explain why it produces answers like these? “I know terms like RAG, agents, and fine-tuning… but it’s difficult to explain them precisely.” “When I hear LLM-related terminology, I’m at a loss for words.” “Explanations of concepts in AI meetings are always vague.” This course was created specifically for people like you. This is a theory course designed to help you understand LLMs not as ‘tools,’ but as ‘structures.’ Rather than teaching you how to use ChatGPT or Gemini, it gives you a framework for explaining why they work the way they do.

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.

This course covers the theory and practical examples of LLMs, based on <Fundamentals of Large Language Models, Quickly!> (Insight, 2025).

You can enhance your development capabilities by deeply exploring the fundamental principles of large language models like ChatGPT and Claude. You will be able to learn a variety of information and development techniques that are not commonly encountered.