This assignment, by Josh Anthony, is from the TextGenEd January 2024 Continuing Experiments collection in the WAC Clearinghouse Repository.
The abstract from the site explains:
The basic mechanics of this activity are simple: choose a reading from class and try to manipulate the LLM to recreate it as close to the original as possible . . . . For students, the limitations of the LLMs become clear almost immediately. With non-scaffolded classes, students will often attempt to put in the name of a text and instruct the LLM to recreate it—often to some hilarious results. Even with the scaffolded and carefully crafted prompts students begin to recognize the limitations. This might come in the form of length, depth, or even understanding of an abstract concept . . . .
Key Features of This Assignment
- Practice in Prompt Engineering
- Students engage in crafting and refining prompts to elicit specific responses from LLMs, enhancing their understanding of precise and effective communication.
- Critical Analysis of Generated Texts
- Students critically analyze the outputs of LLMs, comparing them to the original texts to identify discrepancies in style, tone, and accuracy, thereby improving their analytical skills.
- Collaboration and Discussion
- Through collaborative prompt construction and class discussions, students enhance their ability to articulate and defend their choices in writing, fostering a deeper understanding of rhetorical strategies.
Find the full version of this resource at the WAC Clearinghouse.