In the famous words of Pink Floyd: "No one told you when to run, – you missed the starting gun." If you, like so many developers, were hesitant to jump on this whole "AI" fad and now find yourself playing a bit of catch-up, this talk is for you.

We'll take a peek into the "black box" of generative AI and explore how this stuff actually works. Why do hallucinations happen (and can they be avoided)? What happens when we change the temperature of a model? Why do LLMs work in tokens instead of words? What's the difference between pre-training and post-training (and are both necessary)? Why does the wording of a prompt change the output so drastically?

If you're a developer who has already been working extensively with building AI integrations, agents, and skills, this will likely be too low-level for you (but hey, never hurts to refresh on the basics!). However, if you “missed the on-ramp” or have been tentatively working with AI in your applications without truly understanding what’s happening behind the scenes: you’re in the right place! Let's de-mystify AI: it's not magic, it's just technology.