Let's start with how we got here. I'll demo AI systems from the 1960s primordial soup up to the emergence of large language models (LLMs). We'll see a GPT-2 implementation in C code, and train it from scratch on nothing but NDC talks (what will it say??). We'll then build up to modern chat/assistant/agent systems. The point of this is to give you a deep intuition for the capabilities and limitations of LLM-based systems.

This sets the scene for present-day app development. We'll run through practical examples of intelligent features you could add to your products today, coding up features like automatic data cleaning, sentiment scoring, anomaly detection, and the use of vision. Finally we'll consider what this means for the future: will the concept of UIs eventually be obsolete, or can it be reinvented to be much more fluid and intelligent? Let's see what we can do...