Tutorial: Responsible use of large language models

Large language models (LLMs), like GPT, are powerful tools for generating text that can be used for coding and doing data analysis. This is at once empowering (LLMs are powerful and can save you time) and risky (LLMs can make mistakes that are hard to detect).

Our general view is that LLMs are powerful tools that you will encounter and use when you leave this classroom, so it’s important to learn how to use them responsibly and effectively. As described in the syllabus, you are generally permitted to use LLMs in this course, but ultimately, you are responsible for guaranteeing, understanding, and interpreting your results, and you can’t do this if you don’t understand the code that you are running (this isn’t exclusive to code generated by LLMs – it also applies to code that you copy from the internet!).

The use of LLMs for coding is a new and rapidly evolving area. Rather than provide a lesson plan for you, this page will provide some resources for self-learning.