
Hadley Wickham (Posit)
Location: Memorial Union - Ballroom
Abstract
LLMs are taking over the world, but are surrounded by a near impenetrable wall of jargon, flimflammery, breathless hype, and good old-fashioned snake oil. But despite the noise, LLMs have some genuinely cool and useful features, and seem likely to radically change how we do data science. In this no-nonsense talk, I'll discuss three genuinely useful techniques (structured data, coding, and tool calling) that you can use today.
In this talk I'll interact with LLMs exclusively from R, using the ellmer package. As well as giving you some useful R programming skills, programming with LLMs makes it much easier to understand some of the abstruse jargon that growns around LLMs.
Bio Sketch:
Hadley is Chief Scientist at Posit PBC, winner of the 2019 COPSS award, and a member of the R Foundation. He builds tools (both computational and cognitive) to make data science easier, faster, and more fun. His work includes packages for data science (like the tidyverse, which includes ggplot2, dplyr, and tidyr)and principled software development (e.g. roxygen2, testthat, and pkgdown). He is also a writer, educator, and speaker promoting the use of R for data science. Learn more on his website, http://hadley.nz.