10 In-Class Activities
Here are two sample in-class activities created by Racheal Fest (SUNY Oneonta; The Faculty Center for Teaching, Learning, and Scholarship Specialist in Pedagogy) that would introduce students to AI literacy in a variety of disciplines:
Example 1: Prompt Engineering
This activity invites students to experiment and evaluate a range of prompting strategies with a particular output in mind. Students begin by prompting ChatGPT or Bing to generate a scholarly or popular essay on an assigned topic, likely one derived from shared course content (say, an example of panopticism inspired by Michel Foucault’s well-known chapter).
Students should ask the AI tool to modify, correct, revise, or take a different approach to its output (for instance, give me a different example, or simplify your explanation, or break this down into steps. Online resources, including Wikipedia, list prompt intervention strategies). After students elicit several rounds of changes from the AI tool, they print a record of their engagement.
Finally, students can reflect on their process by assessing the efficacy of their own prompts and the quality of AI outputs. Did they manage to produce desired results? How? What strategies did they employ? How did they struggle? What does AI do well? What does AI do poorly?
Students could begin this work collectively, guided by an instructor who might elicit prompts and enter them into ChatGPT, Bing, etc., on a projector. After modeling this process and discussing prompting strategies, students could go on to complete individual assignments.
Example 2: Evaluating Form and Content of AI Outputs
This activity invites students to think critically about the strengths and challenges of content generated by both AI and other humans. First, students respond to a writing prompt relevant to course content without engaging generative AI.
Once they have completed the exercise, students enter the same writing prompt into ChatGPT, Bing, or another generative AI tool. Students then evaluate the texts, comparing and contrasting their formal features, their approaches to content, and more. What are the strengths and areas of growth for each? What differences and similarities do students notice? How does AI write? How do humans write? How could each improve their compositions and outputs?
Utah Tech University’s Center for Teaching and Learning provides additional examples of rethinking learning outcomes with AI. Their drop-down on Integrating AI in Teaching offers several good suggestions. For example, instead of asking nursing students to summarize research on evidence-based practice, they might compare an AI-generated summary and a summary written by a human to see what the differences are (and therefore, how that could change the outcomes of that scenario).
Example 3: Using AI for Brainstorming and Idea Development
AI can be used as a brainstorming tool to help undergraduates narrow down their ideas for research or to come up with initial ideas.. In a recent Alchemy webinar, “Harnessing the Power of AI: Transforming Assignments and Assessments in Higher Education”, Dr. Danny Liu (University of Sydney) suggested using ChatGPT this way have the students encourage the chatbot to ask them questions and generate text based on their responses. The following example comes from a direct exchange with ChatGPT:
Prompt: I have to write a research paper about a community I belong to and how it uses literacy for my English composition college class. Can you ask me some questions to help me brainstorm for the assignment?
AI: Certainly! Brainstorming is a crucial step in the research process. Here are some questions to help you explore how your community uses literacy and generate ideas for your research paper:
- What is the specific community you belong to, and how would you define it?
- How does your community value literacy, and what role does it play in daily life?
- What are the various forms of literacy within your community? (e.g., reading, writing, digital literacy, cultural literacy)
- Are there particular literacy practices or traditions unique to your community?
- How does literacy impact communication within your community? Does it influence how members interact and express themselves?
- Are there any challenges or barriers related to literacy in your community? (e.g., access to education, language differences, technological limitations)
The AI created 13 additional questions that we did not include here. Students can request that the AI ask one question at a time so they can respond to each one or provide a list so they can consider their options. And with more practice with prompt engineering, students can refine their questions and get even better at asking the AI for help.
Example 5: Using AI for Proofreading
Proofreading often gets neglected by students because it is time-consuming, boring, or they feel that there is not enough time to do it before an assignment is due. In addition to built-in spell checkers in programs like Microsoft and Google, many students also use Grammarly to help them with sentence structure, tone, etc. Students can use ChatGPT for proofreading as well.
For example, pasting a text into the chatbot and simply asking “Can you proofread this for me?” will yield different results than pasting in text with more specific requests like, “Can you identify the analysis in this history paper?” or “Please describe the counterclaim in this argumentative essay.” Students can then compare what the generative AI tool noted and see if they are achieving what they mean to in their writing.
AI can help students in other ways as well: for example, if students are writing in the sciences, they may be required to use passive voice. Asking ChatGPT to specifically check a text for active voice would be a helpful activity. Students can also ask ChatGPT to check their citations or to evaluate their introductory or conclusion paragraphs. However, they should be advised and reminded that generative AI can and does make errors and suggest erroneous information. Students must use their judgment before accepting generative AI suggestions.
Many of the major citation styles have adopted policies around citation and generative chatbots:
Citing generative AI in MLA Style
