Large Language Models are the technology behind ChatGPT, Google’s Bard and more. They are weird and somewhat intimidating pieces of technology: we’re still trying to figure out how they work and what they can do, in a field that changes radically on an almost weekly basis.
In this talk I’ll break down how they work, what they’re useful for, what you can build with them and how to dodge their many pitfalls.
I’ll show you how to run surprisingly capable models on your laptop, and demonstrate techniques like semantic search and retrieval augmented generation which harness LLMs to help unlock the value in your own data.
I’ll also talk about their many limitations, including new classes of security vulnerabilities that threaten applications built on top of them.
Exploring LLMs has made me more ambitious with the projects I take on. Used thoughtfully, LLMs can unlock new capabilities, both for us and for the communities that we build software to serve.