Demystifying the AI Jungle: Connecting the Dots

Open-weight models, fine-tuning, skills... the list of AI buzzwords grows every day. When I first started digging in, I had the impression that a new technology popped up every month just to replace the old one, but these are not replacements. They are connected building blocks. In this talk, I'll show you exactly how they fit together. We'll start with the foundation: the LLM itself. We will look at what it actually means to create one and how it works. Going from predicting the next token to how Temperature, Inference, and Chain of Thought (CoT) change the results. Once we have the basics, we'll tackle the limits of LLMs and the practical approaches used to solve them. This means: Managing Context: How much can the model actually "remember"? Data Actuality: How do we keep the information up to date? Agents & Tools: Giving the model "hands" to finally interact with the world. The goal is to understand the mechanics of AI well enough to finally separate the facts from the hype.