Toronto Metropolitan University
This assignment engages undergraduate students in the hands-on practice of procedural creativity through playing with, ‘hacking,’ or building text generators that produce creative outputs. Students are asked to draw upon the material covered in lectures and their own experience as procedural creators to reflect upon ideas of creativity, authorship, and potential futures for the literary in a digital age.
Dana LeTriece Calhoun
University of Pittsburgh
This assignment invites undergraduate students to create "spells," a poem based on a wish, and prompt an LLM to write a spell of its own, then reflect on their input and LLM output compared to their original compositions. Students analyzed the function of language and intent in manual and LLM composition, drawing together meaning and expression, and how LLM technology replicates or revises that expression. This assignment can be adapted to most rhetoric, composition, and cultural studies courses.
This assignment asks undergraduate students to explore image and text generation technologies to create a short, illustrated children's book. Although text and image generation technologies are different, experimenting with them in parallel challenges students to reflect critically on the co-constitutive relationship between writing and technology. This approach was particularly useful for making "visible" how technologies can participate in, create, and sustain biases.
As new context-aware generative models challenge the human relationship to language, students benefit from first-hand observation of these models’ successes and limitations. Using these models often requires using “prompts” (natural language-based directions) to guide their output. The method of developing these directives has quasi-formalized into a practice known as “prompt engineering.” Serving as a gentle introduction to the intentionality, opportunities, and limits of the prompt engineering process, this work proposes and describes initial outcomes from an assignment that uses similarities between model prompting and the constraint-based literary work of the Ouvroir de littérature potentielle (“Oulipo”) to focus student attention on precision and specificity of prompts and their execution. Beyond familiarizing students with contemporary technologies (particularly OpenAI’s GPT platform) and the nascent practices developing around them, this assignment also aims to give students first-hand experience with the reflexivity of using language to describe language in preparation for larger conversations about language as a technology and the roles of large language models (LLM) in human expression.
Mark C. Marino, University of Southern California
Rob Wittig, University of Minnesota Duluth
The Grand Exhibition of Prompts, a netprov
In this collaborative creative writing game on a threaded discussion platform students experiment with AI image-making programs, but concentrate on the expressive, literary power of the verbal prompts they write. As language arts, image-making prompts are concentrated, evocative, use sentences, fragments, lists and non-sequiturs. In other words they are poetic (but don’t tell them that until later!). Students can be evaluated on their contributions, and on their support and encouragement of other writers.
Massachusetts Institute of Technology
Students are assigned to generate variations of an underlying story using a system designed for this purpose. The goals are (1) to use the core aspects of narrative, events and their representation; (2) to link narrative terms to concepts; and (3) to discover how events can be narrated in different, lively ways. The assignment requires instructor familiarity with my system, Curveship-js, but works well. Sharing and discussing the results enhances learning.
Brown Literary Arts
This assignment asks undergraduate students to generate text using both analog cut up techniques, as well as a simple Markov procedure, and discuss the power relations inherent in found writing processes. Through reading and making, students will encounter and critically develop their own articulations of found art—its questions of property and power—and how it relates to generative text and its corpuses.