How LLMs Really Work

Exploring Language Models, Code Prediction, and AI Agents

26 August 2025

Tags

To watch this video on our website please or view it directly on YouTube

In this episode, we explore how Large Language Models (LLMs) work behind the scenes — from predicting the next word to powering tools like GitHub Copilot. Jesper introduces insights from his master’s thesis, Jan explains the core mechanics, and we discuss how agents extend LLMs beyond simple text generation.

Chapters

00:00 Welcome

02:06 Jesper's master thesis - the setup for the discussion

04:07 Jan's explantion

07:39 ...but how can it guess next word with code?

09:18 How tools differentiate

12:05 How co-pilot learns about my algorithm library?

13:50 Agents

18:22 What's next?

Links:

Tags:

Jan Marker

Senior Software Engineer

Jan Marker has a Master's degree in computer science with a focus on computational neuroscience. He has been working with Qt since 2009 when he started contributing to the KDE project and has been teaching developers in Qt and QML since 2017. He is currently overseeing KDAB's LLM R&D effort.

Jesper K. Pedersen

HR Director / COO

Jesper K. Pedersen – COO/HR director at KDAB. Jesper has actively developed with Qt since 1998 and, despite his fancy title, still does so.

He has held almost 100 training classes in Qt since 2000. Today, his greatest claim to fame is the QML youtube series and more recently his youtube series called Qt Widgets and More.

How LLMs Really Work

Exploring Language Models, Code Prediction, and AI Agents

Sign up for the KDAB Newsletter