Hadley Wickham
Posit, PBC

In this keynote, I’ll explore the evolving relationship between data scientists, statisticians, and large language models through a unique experiment: this entire talk was created in collaboration with an LLM. From outline to slides, from code examples to key insights, I’ll share the practical realities of using AI as a thought partner in the R ecosystem. Drawing on my experience developing tidyverse packages and teaching data science, I’ll demonstrate how LLMs can augment (rather than replace) the R user’s workflow. We’ll examine specific examples where AI assistance shines—rapid prototyping, documentation generation, and creative ideation—alongside areas where human expertise remains irreplaceable. Most importantly, I’ll reflect on what this experiment reveals about the future of our community: How might AI change the way we teach R? What new skills should we prioritize? And how can we ensure that the tools we build remain accessible and empowering for all users? Join me for this meta-exploration of AI’s role in our work, with honest reflections on both the promise and limitations of these new collaborators in our statistical computing journey. ✨ This abstract was generated by Claude Sonnet 3.7 and lightly edited by me. I used the prompt: I am Hadley Wickham, chief scientist at RStudio/Posit and I’ve been invited to give a keynote on AI at the useR conference. Please write a talk abstract for a talk entitled ‘I wrote this talk with an LLM’ ✨