Thinking Outside the AI Chatbox - Luke Vanderhart

• 6pm Dinner
• 6:30-7:30 Presentation
• 7:30-7:45 Group Discussion
• 7:45 Door prizes

Thinking Outside the Chatbox

Language models have a great deal of potential for helping us build powerful systems, but the epithet "AI" has in many ways done us a disservice. It has steered our collective imagination towards applications in which the LLM adopts a human or at least agent-like role.
But it isn't actually clear that this is the best way to use them. A language model is a powerful thing, and its ability to emulate a human is almost incidental. This talk will explore ways of thinking about LLMs first and foremost as models, instead of pseudo-people, and how this can unlock a new landscape of creativity about how to apply them.

Luke VanderHart is a developer, author and consultant with an emphasis on system design, data ontologies and functional programming. He has worked in a variety of domains for over 20 years including security, healthcare, intelligence, finance and energy. He has a B.A. in Philosophy and Linguistics, and views software technology as an exercise in applied philosophy and a tool to both learn about and create the world.
His current project is a startup that builds tools integrating LLMs and ontologies, to deeply ground them in verifiable fact and formal reasoning.

Thanks to UJUG Sponsors, Tek Systems, STG, and O.C. Tanner