Generative AI and Assessing Module COMP0233

The augmentation of everyday software development and productivity tools with Large Language Model (LLM) capabilities is increasing and will become as ubiquitous as spelling and grammar checking tools. But, what do LLMs really mean in terms of assessed work? We thought we’d find out.

Research Software Engineering with Python (COMP0233) is a large-ish level 7 module taken by students from predominantly Physics and related fields. The assessment is 100% coursework, split between an individual assignment and a group assignment.

First, we had to find out what an LLM could do with regards to the assignments, then decide what we would tell students, and finally reflect on what they did and why. This is the story of those tasks and what we learnt in the process.

 

View and download the transcript.

GenAI and Assessing COMP0233 (.pptx file)

Samantha Ahern co-leads the Centre for Advanced Research Computing’s (ARC’s) Education activity with Dr David Pérez-Suárez (Learn more about ARC Education).

The 2023/24 delivery team for COMP0233 comprised of:

  • Module Lead: Dr David Pérez-Suárez
  • Module Deputy: Dr Will Graham
  • Samantha Ahern
  • Toni Mlinarević (PGTA)

Additional ARC colleagues assisted with the marking of both the individual and group assignments.

print

Leave a Reply

Your email address will not be published. Required fields are marked *

Please sign in first
You are on your way to create a site.