BACKGROUND
Have you started learning coding and wonder how to best integrate Large Language Models (LLMs) into your workflows? Or maybe you learned to code a while ago but haven’t yet started using LLMs effectively?
LLMs can be powerful assistants for scientists who code. They can help generate, debug, and optimize code, but they also have limitations. How can we best leverage these tools while maintaining control, accuracy, and efficiency in our coding process?
WORKSHOP GOAL
This training aims to equip scientists with practical strategies for integrating LLMs into their coding workflow, specifically using Python, whether for writing new code, debugging, or optimizing existing code.
Participants will learn about the strengths and limitations of LLMs and their underlying mechanisms, gaining a deeper understanding of when and how to rely on them effectively.
WORKSHOP CONTENT
In the training, community-perspectives and personal experiences about using LLMs in scientific coding will be systematically explored. The session will alternate between informative presentations and hands-on tests with LLMs, where participants can actively engage.
TARGET AUDIENCE & PRIOR KNOWLEDGE
This event is targeted at researchers from all disciplines who don’t have much experience with LLMs and are interested in hearing about and testing best practices and limitations in code work with LLMs. The example codes shown will be written in Python and will focus on data analyses with quantitative data. Participants should be
comfortable reading basic Python code.
TECHNICAL REQUIREMENTS
ABOUT THE TRAINER
Annika Nolte is a data scientist for training and consulting at the DSC. She holds a master’s degree in Environmental Sciences from the Technical University of Braunschweig (2019). She has over five years of experience in scientific programming, specializing in data management and processing, hydroinformatics, geospatial analysis, and AI for environmental modeling. In training and consulting, Annika draws on her research background and broad interdisciplinary expertise in Earth system sciences.