AI & Generative AI Curriculum, by Packback
Last Updated: August 2023
Table of Contents
About this Resource
This resources was created by the Packback team, specifically by former educators and current AI-fanatics.
This resource contains:
Please Read before continuing:
About the authors...
Kelsey Behringer
CEO, Packback
During her four years in the classroom as a high school chemistry & physics teacher, Kelsey found herself using technology daily to captivate her reluctant students. Looking to widen the scope of her impact on education and help other educators see technology as a superpower, she joined Packback in 2017 as an Experience Manager. It’s been a curiosity fueled journey since!
Ri Cantlin
Curriculum Consultant, Packback
As a former middle school ELA teacher, Ri was dedicated to finding innovative ways to engage in curriculum, amplify student voices and spark a love of reading and writing in every student. Now, as a Packback Curriculum Consultant, they teach higher ed faculty how to use AI-powered technology to do the same.
Much of the content in this guide was created with the collaboration of the generative AI Platforms: ChatGPT (by Open AI), Claude.AI (by Anthropic), and Perplexity.AI
Lesson 1: Introduction to AI
Lesson Objectives
Define artificial intelligence & common language you may hear in regards to AI, including: machine learning, large language models, “narrow” AI and “general” AI
Provide examples of AI in everyday life
Discuss the potential benefits and risks of AI
What is Artificial Intelligence?
Let’s ask AI, “What is Artificial Intelligence”?
Source: OpenAI, GPT-4
Examples of Artificial Intelligence in your Daily Life
Facebook’s Facial Recognition Applications
“Facebook trains DeepFace, a facial recognition programme, to identify people in pictures. According to the company, DeepFace, its most sophisticated picture recognition engine, has a success rate of 97% in determining whether two images of the same person are identical or not when compared to humans' 96%.”
Source - Ashesh Anand, AnalyticsSteps.com
Uber - More Accurate Predictions, Better Navigation
“In 2019, Uber AI’s Sensing and Perception team worked on projects across our mobile and back-end stack to improve the coverage, accuracy, speed, and heading of vehicle locations on the Uber platform. Overcoming the limitations of GPS and having more precise locations makes it easier for riders and drivers to find one another, improves estimated times of arrival (ETAs), reduces rider and driver cancellations, and makes our marketplace operate more efficiently.”
Source (from Uber.com)
Image from article, “How Uber uses AI to serve you better”
Let’s quickly review two buzzwords in AI:
What is Machine Learning?
Machine learning (ML) is just one subset of Artificial Intelligence. ML gives computers the ability to learn without explicitly being programmed.
“Machine learning starts with data — numbers, photos, or text, like bank transactions, pictures of people or even bakery items, repair records, time series data from sensors, or sales reports. The data is gathered and prepared to be used as training data, or the information the machine learning model will be trained on. The more data, the better the program.
From there, programmers choose a machine learning model to use, supply the data, and let the computer model train itself to find patterns or make predictions. Over time the human programmer can also tweak the model, including changing its parameters, to help push it toward more accurate results.”
Source: MIT Sloan School of Management
Video: “Machine Learning Explained in 100 Seconds”, Fireship
What is a Large Language Model?
From the Webinar “Will AI-Generated Text Kill Writing?”, facilitated by Packback on 12/13/22 (Link to Video)
ChatGPT (LLM) In Action
Two more buzzwords you may be hearing…
“Narrow” vs. “General” AI
You may have heard of the terms “narrow AI” and “general AI”
In simple terms, Narrow AI is where we have been, and General AI is where we want to head towards.
“Artificial Narrow Intelligence (ANI), sometimes known as "weak AI", refers to any AI that can outperform a human in a narrowly defined and structured task. It is designed to perform a single function like an internet search, face recognition, chatbot, or speech detection under various constraints and limitations. It is the constraints that lead people to refer to these functions as ‘narrow’ or ‘weak’.”
“Artificial General Intelligence is known as "strong AI" and allows machines to apply knowledge and skills in different contexts.
Where ANI applications can run single, automated, and repetitive tasks, the objective of AGI is to create machines that can reason and think just like a human is capable of doing.”
Think of a robot from a Sci-Fi movie, like “Ava” from ‘Ex Machina’
Source - “General AI vs Narrow AI”, Zoe Larkin, Levity
AI: Benefits and Risks
Benefits
Risks
List of Benefits & Risks created in collaboration with ChatGPT, OpenAI, Version 4
Lesson 1: Optional Pre-Work
3-7 days leading up to your first AI-Lesson, create a “Homework Poll” in your Packback community.
Ask them a multiple choice question that would require them to also write a written response.
Remember, a “homework poll” requires students to justify their multiple-choice answer with a written response. If you do not want to require students to follow up with a written response, use an in-class poll instead!
Here are a few examples to the right:
Optional Pre-Work (Packback User, Homework Poll)
Q: Are you concerned or excited about the evolution of AI and its impact on society?
A: I’m concerned
B: I’m excited
C: A little bit of both
D: It’s too soon to tell
Q: Have you used Generative AI. If yes, how? If no, why not? Please explain your personal sentiment towards the use of generative AI!
A: Yes, I’ve used it, and I use it often
B; Yes, I’ve used it, but I don’t use if often
C: No, I haven’t used it
Optional Pre-Work (Packback User, Homework Poll)
3-7 days leading up to your first AI-Lesson, use your LMS discussion board to facilitate a pre-lesson discussion, or create a “quick write” assignment for them to complete a quick, ~200 word reflection before class.
Discussion: Ask your students to reflect on their sentiment towards AI, familiarity with AI, and their predictions regarding AI. Ask them to reply to one of their classmate’s discussion posts, specifically, a peer who doesn’t share the same opinion or sentiment as them!
Writing Assignment: If you do not wish to use LMS discussion (this doesn’t fit in your course, or you do not want students’ responses to be visible by classmates), then create a quick writing assignment with a similar prompt as the discussion.
Optional Pre-Work (Not a Packback User)
Discussion/Writing Prompt
Before class on [date], I want to hear your thoughts & opinions on AI.
First and foremost, how have you been using AI? Have you used any of the chatbots? Which ones? What are your general observations on their performance and applications?
Second, I’d love to hear how you feel AI will personally affect your future - your dream job? Society? Your hobbies? Are you concerned? Are you excited?
Lastly, how would you like to use AI in this course?
Once you write your own reflection (I encourage you to share links and news stories, by the way!), reply to a peer. My one ask is you reply to a peer who has a different opinion than you!
Note: If you do not wish to use discussion but rather a standard writing assignment, simply remove the last call to action.
Lesson 1: Optional In-Class Activity
Use Polls to Gauge Interest & Maintain Engagement
If you’re a Packback user, use an “in-class poll”
If you’re not a Packback user, use your desired polling software.
Not a huge fan of using technology during class? No worries. Ask your students to raise their hands to answer the poll or get up and “go to a side of the room”
Note: Some of these poll questions overlap with the Homework Poll Questions presented in the “pre-work” assignment suggestion
Optional In-Class Activity (In-Class Poll)
Poll Questions
Lesson 1: Optional Follow Up Assessment
After your first AI Lesson, assign a short writing assignment.
If you’re a Packback user, set this up as a “Deep Dive.”
You could also assign this in the form of a discussion using the following prompt:
Ask 1 question about how your life may be impacted by existing AI, and respond to 2 peers with answers based on personal experience or examples of existing tools related to their question. Example:
Optional Follow Up Assessment (Writing or Discussion)
AI in Your Daily Life Writing or Discussion Prompt:
For this assignment, you will conduct research into how you already interact with AI on a regular basis.
Choose 3 examples of AI you encounter in your daily life, such as digital assistants, social media feeds, shopping recommendations, etc. For each example, write a paragraph addressing the following:
How could AI help me diversify what I eat each week?
Halla Taste Intelligence Engine is a human preference engine built for grocery stores. It leverages over 100 billion grocery shopper + product data points to accurately display products a shopper will want to buy next. https://halla.io/capabilities/
Lesson 2: How to Use Generative AI as a Collaborator
This lesson is meant to be a highly interactive “start and stop” lesson with students.
The way that this is built, students should be on their laptop/computer, with ChatGPT, Claude, or another chatbot open.
The general flow of the lesson is:
We do NOT recommend you work through all scenarios, but rather the scenario(s) that mosts relates to your course material.
Lesson 2 Notes
Lesson Objectives
Identify platforms available for written, visual, and audio AI-generation and collaboration
Review recommendations for writing high-quality prompts for genAI
Discuss specific use cases for AI utilization… in an appropriate & academic way
Share examples of ways we can use AI for personal collaboration
Popular Generative AI Chatbots:
Image Generator:
Sound Generator:
Popular Generative AI Platforms
What other generative AI platforms have you used? For what purpose?
We’re about to discuss ways you can use genAI chatbots in academically honest ways.
Please note while I may allow use of appropriate use of genAI, not all of your instructors will or do.
Please make sure to read all of your syllabi carefully before assuming how you may/may not use AI
How to write a strong genAI prompt
A helpful analogy
GPT is like a toddler, but if that toddler had almost all of the knowledge in the World.
What you need to know about this toddler:
How would you coax an astonishingly knowledgeable toddler into doing what you want?
Image generated by DALL-E 2 “Super Knowledgeable Toddler”
5 Rules for Creating Great Prompts
Prompt Example
You are a logical fallacy detector. If there are clear logical fallacies in this text, list them and describe why.
Your output format is a csv with two columns, "fallacy" and "reason", with no other explanation.
[INSERT TEXT]
Define Role
Provide context
State the Task or Question
Set Constraints or Limitations
Offer Additional Guidance
Prompt Example, Refined
You are a logical fallacy detector. If there are clear logical fallacies in this text, list any of them that appear in this list
Describe why in a way that is appropriate for a sixth grade class to understand.
Your output format is a csv with two columns, "fallacy" and "reason", with no other explanation.
[INSERT TEXT]
Define Role
Provide context
State the Task or Question
Set Constraints or Limitations
Offer Additional Guidance
AI Collaboration Use Case:
Generative AI as a Writing Tutor
Using Generative AI Chatbots as a Writing Tutor
When using AI Chatbots as a writing tutor, be mindful of violating academic integrity policies, and also remember the purpose of completing a writing assignment is to strengthen your understanding of the content, and help you build the skills necessary to be a strong researcher, writer, editor, and communicator.
If you lack strong fundamental research, writing, and editing skills, you will not be able to effectively use GPT as a writing collaborator.
Here are some ways you could use AI Chatbots as a Writing Tutor
*just make sure you use it as inspiration, don’t copy & paste unless your instructor tells you otherwise
Writing Tutor - Scenario
You’re writing a paper on why University athletes should be compensated.
The thesis statement: University athletes should be compensated for their service to the university, as it is difficult for these students to procure and hold a job with busy academic and athletic schedules. Many student athletes on scholarship also come from low-income neighborhoods and it is a struggle to make ends meet when they are participating in athletics.
Writing Tutor - Discussion and Reflection
GPT Output when I ask for feedback:
Of course! Crafting a strong and engaging thesis statement is essential for capturing your readers' attention and guiding your paper effectively. Here are some tips to help you create a compelling thesis that makes your argument both strong and enjoyable to read:
Remember, your thesis statement serves as a roadmap for your paper, so make it exciting and captivating to set the tone for an engaging read.
When I ask GPT to rewrite my thesis statement…
"In the heart of the roaring stadium crowds and the hushed libraries, a fundamental inequity persists: college athletes, who pour their sweat and dedication into both academics and sports, are left grappling with an unjust reality. The call for fair compensation reverberates through the labyrinthine schedules of these driven individuals, whose arduous academic and athletic commitments deny them the luxury of part-time jobs. Moreover, a significant number of these athletes emerge from the crucible of low-income neighborhoods, their dreams colliding with the harsh financial constraints of university life. This essay champions the urgent need to rectify this imbalance, proposing that compensating college athletes is a moral imperative that speaks not only to the essence of justice but also to the true spirit of collegiate athletics."
If you copied & pasted the new thesis from GPT instead of following the feedback and writing it yourself, what would you have learned in the process? Do you think you’d write an better paper using your own thesis or the GPT-thesis? Why?
AI Collaboration Use Case:
Generative AI Chatbots for Professional and Academic Advice
Using Generative AI Chatbots for Professional and Academic Advice
AI Chatbots can be incredible resources for writing intimidating pieces of content like cover letters and resumes.
I recommend not asking the chatbot to write these for you, but rather:
Future employers want to hear your voice. I recommend only asking for feedback from a chatbot and perhaps asking for ideas on how to phrase/rephrase portions of text. Why? Nobody wants to read something written by a robot.
Make sure to fact check and thoroughly review any content you do get from the Chatbot. I’ve personally found myself editing 25%-50% of any text generated by AI for accuracy, clarity, or tone.
Here are some ways you could use AI Chatbots for Professional and Academic Advice
Using Generative AI Chatbots for Professional and Academic Advice - Scenario
You’re interviewing for a post-graduation job at a tech company in a sales role. You have completed two interviews thus far, one with their recruiter, Maggie, and the next with the team manager, Anne. Your interview with Anne was on Monday, it’s now Thursday and you haven’t heard back on next steps.
You craft an email for the recruiter and manager:
Dear Maggie and Anne,
I'm following up on my interview from Monday. I know it's only been a couple days, but I just wanted to check in on the status of the hiring process. Do you have an update on next steps or a timeline for when I can expect to hear back?
I enjoyed learning more about the company and position. This is my top choice for a job right now, and I’m looking forward to hearing from you soon!
Best, [Your Name]
Using Generative AI Chatbots for Professional and Academic Advice - Example One
Using Generative AI Chatbots for Professional and Academic Advice - Example Two
Using Generative AI Chatbots for Professional and Academic Advice - Scenario Reflection
Share your prompt, 1-3 pieces of feedback you received from ChatGPT on the email copy, and describe how you approached your edits
AI Collaboration Use Case:
Generative AI Chatbots for Content Tutoring
Using Generative AI Chatbots as a Content Tutor
Sometimes concepts are just hard to understand. And when you go to search more about the concept in your textbook or on the web, you run into even more vocabulary or concepts you don’t understand. It can be frustrating to hit a wall.
This is where AI can be useful. Use generative AI to break down content, ask for analogies, walk you through a process, and more.
JUST be sure to be cautious - AI isn’t always right. You’re going to need to be cautious to not accept content from AI at face value. Generative AI should be one tool you use to help understand difficult concepts. Rely on text, course resources, ME!, and office hours. You have many tools at your disposal.
Using Generative AI Chatbots as a Content Tutor
Example of AI as a content tutor!
Using Generative AI Chatbots as a Content Tutor - Scenario
Examples of AI as a Personal Assistant and Collaborator
Ask generative AI to help create a study plan
Ask generative AI to help come up with Vacation Ideas
Ask generative AI to help you make a decision
Lesson 2: Optional Pre-Work
Right before you start this lesson, have your students ask ChatGPT (or a chatbot of your choice) a simple question related to your class.
This could be done synchronously in-class or asynchronously prior to arriving to class.
For example: “What are the best jobs in [discipline]?”
Ask students to share out the responses. Note: assuming you encourage them to all use the same chatbot, their answers will all be similar, if not the same.
Optional In-Class Follow-Up Activity:
Have students brainstorm how they could refine the original prompt to provide a better answer (unique to them).
Optional Pre-Work
“Chatbot Prompt Practice” Prompt
Emerging chatbots like ChatGPT demonstrate the power of large language models to generate human-like text. However, the quality of their output depends heavily on how well we frame our prompts.
In this pre-work assignment, you will practice prompting an AI assistant to give you career advice.
Go to the ChatGPT website or another chatbot of your choosing. Ask the Chatbot about the best careers in [Discipline]. Record your input and the response you receive.
Lesson 2: Optional Follow Up Assessment
After your lesson, give students time to refine their original prompt.
If you use Packback, you could post and pin a question and have students respond to you.
Remember, any responses on Packback will count toward their grade for that assignment.
Ex: How did you prompt the AI to get a more tailored career recommendation? Posts your screenshots and summary in your response below.
This exercise will help develop their skills for prompting AI chatbots while also providing some new perspectives on careers tailored to them.
Optional Follow Up Assessment
Prompt Refinement Assignment
Refine the original prompt to provide the chatbot with more context and get a more tailored career recommendation. You may want to include details like:
Example: What are the best jobs in [discipline] for someone who loves to be outside, wants to work remotely, and wants to leverage their writing ability on a daily basis.
Take screenshots showing your original prompt and refined prompt with the chatbot responses.
In a paragraph, summarize:
Lesson 3: AI Ethics
Lesson Objectives
Understand how to appropriately utilize generative AI without sacrificing academic integrity (in this course)
Discuss why it’s important to be academically honest
Understand how to cite use of generative AI
Define key ethical principles relevant to AI like transparency, fairness, accountability, privacy, etc.
Recognize the potential risks and biases of AI systems through review and discussion of recent stories regarding AI ethics
We’re about to discuss a few topics regarding academic integrity and use of AI.
This is a reminder that this lesson applies to this course. Please defer to your other instructors and syllabi for other courses.
What I may allow and encourage in my course may not be allowed nor encouraged in others.
Before we get started
Let’s discuss AI and academic integrity
Academic Honesty vs. Dishonesty
Utilizing Generative AI 👍
Academically Honest, in this course
Utilizing Generative AI 👎
Academically Dishonest, in this course
How to Cite Generative AI - MLA
MLA Style Guide
According to MLA, you should:
MLA Template for GenAI:
Author: Do not treat the AI tool as an author
Title: Describe what was generated by the AI tool
Title of Container: AI tool (i.e. ChatGPT)
Version: Version of AI tool (i.e. GPT 3.5 or 13 feb. version)
Publisher: Who made the tool?
Date: Date the content was generated
Location: URL for the chat history*
Example:
“Describe the symbolism of the green light in the book The Great Gatsby by F. Scott Fitzgerald” prompt. ChatGPT, 13 feb. version, OpenAI, 8 Mar. 2023, chat.openai.com/chat.
*the guide was created before chat histories were available. If sharing chat history via a unique URL isn’t possible on the tool you’re using, use the general URL
MLA: Citing Creative Visual Works
Fig. 1. “Pointillist painting of a sheep in a sunny field of blue flowers” prompt, DALL-E, version 2, OpenAI, 8 Mar. 2023, labs.openai.com/.
MLA Style Guide - Practice
You use ChatGPT to edit your thesis statement. This is your prompt:
Using the template to the right, create your MLA citation
MLA Template for GenAI:
Author: Do not treat the AI tool as an author
Title: Describe what was generated by the AI tool
Title of Container: AI tool (i.e. ChatGPT)
Version: Version of AI tool (i.e. GPT 3.5 or 13 feb. version)
Publisher: Who made the tool?
Date: Date the content was generated
Location: URL for the chat history*
Example:
“Describe the symbolism of the green light in the book The Great Gatsby by F. Scott Fitzgerald” prompt. ChatGPT, 13 feb. version, OpenAI, 8 Mar. 2023, chat.openai.com/chat.
*the guide was created before chat histories were available. If sharing chat history via a unique URL isn’t possible on the tool you’re using, use the general URL
How to Cite Generative AI - APA
APA Style Guide
According to APA, you should:
Example of Citation in-text:
When prompted with “Is the left brain right brain divide real or a metaphor?” the ChatGPT-generated text indicated that although the two brain hemispheres are somewhat specialized, “the notation that people can be characterized as ‘left-brained’ or ‘right-brained’ is considered to be an oversimplification and a popular myth” (OpenAI, 2023).
Reference:
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model].
https://chat.openai.com/chat
APA: Additional Notes
“You may also put the full text of long responses from ChatGPT in an appendix of your paper or in online supplemental materials, so readers have access to the exact text that was generated. It is particularly important to document the exact text created because ChatGPT will generate a unique response in each chat session, even if given the same prompt. If you create appendices or supplemental materials, remember that each should be called out at least once in the body of your APA Style paper.”
APA Style Guide
APA Template for GenAI:
Author: Creator of the Model = Author
Date: Year of the version you used (only the year, not the full date)
Title: Name of the model, italicized
Version: The version number is included after the title in parentheses*
Bracketed Text: Additional descriptions to help reader understand what’s being cited
Source: If the publisher name and author name are the same, do not repeat. Move directly to the URL
*The format for the version number in ChatGPT references includes the date because that is how OpenAI is labeling the versions. Different LLMs or software might use different version numbering; use the version number in the format the author or publisher provides, which may be a numbering system (e.g., Version 2.0)
four elements (author, date, title, and source)
How to Cite Generative AI - Chicago Style
Chicago Style Guide
According to Chicago:
Note: Chicago recommendations are still evolving, and subject to change.
Citation (if prompt is included in text):
1. Text generated by ChatGPT, OpenAI, March 7, 2023, https://chat.openai.com/chat.
Citation (if prompt isn’t included in the text):
1. ChatGPT, response to “Explain how to make pizza dough from common household ingredients,” OpenAI, March 7, 2023.
If you’ve edited the AI-generated text, you should say so in the text or at the end of the note (e.g., “edited for style and content”)
AI: Key Ethical Principles, Risks, and Regulations
Key Ethical AI Principles
When developing AI systems, creators should adhere to ethical principles that:
AI Ethics generally refer to principles centered around “transparency, fairness, accountability, and privacy.”
Key Ethical AI Principles
Fairness: AI systems should not be biased and should not discriminate against individuals based on race, gender, sexual orientation, religion, or any other characteristic
Transparency: AI systems should be transparent in their decision-making processes and should provide explanations for their decisions
Accountability: AI systems should be accountable for their decisions and actions, and mechanisms should be in place to ensure that potential harms are identified and addressed in a timely manner
Privacy: AI systems should protect users' privacy and should not process personal and sensitive data without consent
Security: AI systems should be secure and should protect against unauthorized access and malicious attacks
Text Generated from Perplexity.AI - Source 1, Source 2, Source 3
Case Study #1 - Zoom
Recently, zoom faced scrutiny regarding changes made to its Terms of Service (ToS).
The revised terms raised privacy concerns among users and the public.
The specific concern raised was related to the language in the terms of service regarding AI data collection and usage. Users were worried that Zoom would use their audio, video, chat, screen sharing, and other customer content to train its artificial intelligence models without their consent
Case Study #1 - Zoom
Link to Article (with updates):
Discussion Questions:
What are your thoughts on the Terms of Service shown on the previous slide?
How do you think zoom handled the scrutiny?
What do you think about the author of the article’s take?
Case Study #2 - Deep Fake
“A University College London study found that humans can detect deepfake speech only 73% of the time, with equal accuracy for English and Mandarin speakers.
Using a text-to-speech algorithm, the researchers generated 50 deepfake speech samples in each language and played them to 529 participants.
About 27 percent of the time, listeners thought the deepfake speech was real. A familiarization treatment only increased recognition accuracy by an average of 3.84 percent, and listening to the clips several times or listening to shorter clips didn't help either.”
“This means, for example, that one in four phone scams could be successful. Even though there are other factors at play, such as hearing a voice you already know, which is probably easier to recognize as fake (but even more dangerous if you don't).”
Case Study #2 - Deep Fake
Discussion Questions:
Have you run into instances of clear AI-generated content? When and where? Why was it so clear, how could you tell?
What are the implications of increasingly deceiving deep fake technologies?
How can we prevent malice from Deep Fake?
Why is this happening?
“Large language models or LLMs like ChatGPT are trained to churn out low perplexity text, but this means that if humans use a lot of common words in a familiar pattern in their writing, their work is at risk of being mistaken for AI-generated text. The risk is greater with non-native English speakers, the researchers say, because they are more likely to adopt simpler word choices.”
“Scientists led by James Zou, an assistant professor of biomedical data science at Stanford University, ran 91 English essays written by non-native English speakers through seven popular GPT detectors to see how well the programs performed.”
“More than half of the essays, which were written for a widely recognised English proficiency test known as the Test of English as a Foreign Language, or TOEFL, were flagged as AI-generated, with one program flagging 98% of the essays as composed by AI.
When essays written by native English-speaking eighth graders in the US were run through the programs, the same AI detectors classed more than 90% as human-generated.”
Discussion Questions:
Potential Risks and Biases of AI Systems?
In summary, here are some risks associated with AI systems. Remember, not all systems are made equally, have the same ToS, or use the same technological practices.
This doesn’t include data privacy & ownership risks (LLMs training on your data), the implications of producing factual inaccuracies, and much more!
Conclusion
Just like buying a car or hiring a service, it’s important to be an informed consumer of your products and services, including AI. Be aware of the risks & dangers. Protect yourself, and make sure you do a lot of due diligence after use of AI to avoid portraying inaccurate or bias information.
Remember to:
Lesson 3: Optional Pre-Work
Before your lesson on AI Ethics, have students use image generating AI (like Dall-E or Gencraft) to explore how bias can manifest in AI systems.
If you’re a Packback user, set this up as a “Deep Dive” and include the reflection questions as “guiding questions” in your prompt.
Bonus: If you’re planning to use Dall-E by openAI for this activity, have students read this announcement about reducing bias and improving safety. https://openai.com/blog/reducing-bias-and-improving-safety-in-dall-e-2
Optional Pre-Work
“Image Generative AI Bias Exploration” Prompt
Using an image generating AI tool, generate several images using the same non-specific prompt, like "doctor", "teacher", "criminal", "rich person", "gamer", "burger king employee", etc.
After each image is generated take note of the characteristics in each image. After regenerating several times, what characteristics do you notice recurring?
Write a reflection on what potential biases you observed and why this could be harmful.
Lesson 3: Optional In-Class Activity
Get to know where students stand on using generative AI in coursework. Read Boston University’s GAIA policy, then ask students several yes/no questions.
If you’re a Packback user, use “in-class polls”
If you’re not a Packback user, use your desired polling software. Or simply have students raise their hands to answer the poll or get up and “go to a side of the room”
Optional In-Class Activity (Polls)
Should students be required to disclose when they use AI tools to assist with coursework? Y/N
Should instructors be allowed to impose stronger restrictions on AI use than outlined in university policy? Y/N
Does this policy sufficiently address issues around access to paid versus free AI tools? Y/N
Should instructors be required to enhance their own understanding of how AI tools work? Y/N
Is it reasonable to expect students to run their work through AI detection tools before submitting it? Y/N
Lesson 3: Optional Follow Up Assessment
Drafting an AI Use Policy Activity
As AI tools become more widely available, it's crucial we determine appropriate and ethical ways to leverage them for learning.
Have students write a personalized AI policy.
If you’re a Packback user, set this up as a “Homework Poll” and encourage students to argue what should and should not be included in a policy within their poll responses.
Remember, any responses on Packback to a homework poll will count toward their grade for that assignment.
Optional Follow-Up Assessment
In this activity, you will draft a personalized policy outlining your own guidelines for using generative AI in coursework.
First, get to know:
Then, write a 1 page AI use policy for yourself that covers:
Compare your policies and discuss any gaps or disagreements on AI use guidelines
Lesson 4: AI's Impact on [Your Discipline]
Lesson Objectives
Examine current and emerging applications of AI in [discipline]
Discuss ethical implications of AI in relation to core principles of [discipline]
Reflect on personal assumptions about AI's impact on the nature of work in [discipline]
Current and emerging applications of AI in [discipline]
We highly recommend you showcase a news story or case study, examining an application of AI in your discipline.
For example, if you’re teaching in the STEM/Bio/Medicine discipline, share this NYT Story: A Stroke Stole Her Ability to Speak at 30. A.I. Is Helping to Restore It Years Later.
Insert an image, discussion question, or reflection question here!
Ethical Implications of AI in Relation to Core Principles of [Discipline]
We recommend you showcase another news story, article, or case study related to ethical implication of AI in relation to your discipline
For example, if you’re an education instructor, you can share this story about how AI detectors discriminate against non-native English speakers
Insert an image, discussion question, or reflection question here!
AI’s Potential Impact on the Nature of Work in [Discipline]
Use this as an opportunity to share your own predictions as a subject matter expert.
We also recommend you create 2-3 discussion questions that you can put in front of your students to facilitate a lively in-class discussion. Of course, you could always save those questions for a writing assignment, reflection, or online discussion.
Lesson 4: Optional Pre-Work
3-7 days leading up to your this AI-Lesson, create a “Homework Poll” in your Packback community.
Ask students: Can parts of [discipline] be fully automated or replaced by AI capabilities? Yes/No
Remember, a “homework poll” requires students to justify their multiple-choice answer with a written response.
If you do not use Packback, you could have students do a quick write or answer this question in an LMS discussion board.
Optional Pre-Work
Since the impacts of AI on most disciplines are still speculative, having students definitively state yes or no prompts introspection on unknown factors and uncertainty.
This will likely spark a lively debate and provide you insight into your students believes.
Use their responses to drive your lesson and engage students as they learn more about how AI may impact your discipline.
Lesson 4: Optional Follow Up Assessment
After your lesson on how AI will impact you discipline, assign an essay. Their reflection will synthesize the lessons on AI's transformative impacts through the lens of disciplinarity values, ethics, and wisdom.
It emphasizes introspection and perspective-taking on an AI future.
If you’re a Packback user, set this up as a “Deep Dive” and include the reflection questions as “guiding questions” in your prompt.
Optional Follow-Up Assessment (Essay)
Beyond AI: Essay Prompt
The integration of artificial intelligence is bound to have profound impacts on the field of [discipline].
In this essay, I want you to move beyond just practical changes, and reflect on how we can maintain meaning, ethics, and humanity even as [discipline] evolves alongside advancing AI capabilities.
In a short essay, address the following:
Cite your sources (including generative AI)
Appendix
We put together additional slides, discussion questions, and ideas you can use as you openly discuss AI with your students
To the right is a table of contents for this Appendix
Appendix
Table of Contents
How you can stay up to date, or learn more about AI
Great AI Resources to learn more about AI
Here are a few cult favorite Films that include AI Characters and Themes
AI in Film
AI-Generated Text Detection vs. Plagiarism Detection
What AI-generated text detectors do is predict the likelihood of a body of text being generated by AI! AI-generated text detectors are statistical models, just like the AI-text generators.
These are things AI-Detectors will or may look for in a submitted body of work:
Plagiarism detection works by looking for exact or similar text in a MASSIVE database of published work. Plagiarism detection is more or less definitive and fact-based.
Examples of Generative AI Producing Errors
Early Research and Trends in AI & Education
*Stanford University, the 2023 AI Index Report **BestColleges Survey
Source: BestColleges Survey (via Forbes)
“[we] have made a commitment to develop and deploy mechanisms that enable users to understand if audio or visual content is AI-generated,"
Open AI Shuts Down Text Detection
Student Interview on “AI Cheating”
Boston University - Student Generated AI Policy
Student-generated AI Policy
Authored by 47 students in CDS DS-380, “Data, Ethics, and Society"
Heavily rooted in ethical use of generative AI, the importance of disclosure, and the importance of using AI as an extension of skill, not a replacement.