Using ChatGPT is one thing. Understanding what’s happening underneath makes it much more useful.

This course takes you deeper into the ideas shaping modern LLMs, from custom instructions and memory to the hierarchy that determines which instructions a model follows. You'll also look at newer reasoning approaches and research into keeping models from revealing information they shouldn't.

Then things get multimodal.

You'll explore how language models work across text, images, audio, and other inputs, with practical examples that make these combinations easier to understand. You'll even examine topics like voice cloning to see where the technology can get complicated and even downright spooky!

Finally, you'll get into tools and function calling: how an LLM can move beyond generating text and interact with external systems. By the end, you'll have a much clearer mental model of what ChatGPT can do, why it behaves the way it does, and how today's AI applications are put together.