ChatGPT for Data Analysis: Dummy data and privacy
ChatGPT collects all the information you feed it. We learn why using non-private dummy data is more practical and less risky in most situations. We also go over how to create dummy data, so you feel empowered to make some when the time comes.
By the end of this session we hope you will:
- understand the privacy risks inherent in LLMs like ChatGPT
- know how to create dummy data suitable for your project
About the series: ChatGPT for Data Analysis consists of four 30-minute workshops that will help you use Large Language Models (LLMs) like ChatGPT to write data analysis code more efficiently. Each workshop focuses on a single topic with 15 minutes of teaching, followed by 15 minutes for questions, discussion, and practice. Register for other workshops in the series:
- How do LLMs work? - Mar 25, 2025
- How to ask for help? - April 1, 2025
- Dummy data and privacy - April 8, 2025
- Coding with ChatGPT - April 15, 2025
- Date:
- Tuesday, April 8, 2025
- Time:
- 2:00pm - 2:30pm
- Audience:
- All Graduate
- Categories:
- Data Research Commons
- Presenter(s):
- Siobhan Schenk, Jeremy Buhler