Kicking the Educational Tires of ChatGPT

I love to read magazines. When I want to find out the latest chit-chat on a subject of interest to me, I go browse and buy. I usually purchase when I’m at an airport or at Barnes and Noble. I’ve recently taken to explore the latest on AI in education, yet the online headlines keep moving the AI end zone with ever-increasing morsels of contradictory predictions.

I happen to be at Barnes and Noble earlier this month and had a wild-hair to purchase all of the magazines that featured AI. I wanted to find something positive about AI in classroom situations where fear mongers wouldn’t have the upper-hand on the tone of the articles. The May/June 2023 MIT Technology Review was among my pulled collection. The cover promised teachers who believed that AI could improve education.

Enter Will Douglas Heaven, senior editor for AI at MIT Technology Review and author of “The Education of ChatGPT.” Heaven quotes many teachers and educators who have found ways to utilize ChatGPT for student learning and even suggests that “banning them [chatbots] is futile, possibly even counterproductive.”

Heaven follows up this statement with a quote from Richard Culatta, CEO of the International Society for Technology in Education (ISTE) and a former colleague of mine from the early 2000s. “We need to be asking what we need to do to prepare young people—learners—for a future world that’s not far into the future.”

Bingo! Culatta hit the educational AI nail on the head for me. With all the doom and gloom swinging around about AI, there seems to be more sour soothsayers talking about the end of education than prescient prophets like Culatta who sense a beginning of “new” education that must innovatively prepare learners with knowledge and skill sets to navigate within the digital acceleration.

Granted, there is much to be done to figure out this future, but I’m with Heaven on this one to the positives of AI and with Culatta on prepping learners for the inevitable. Heaven ends with another quote from Culatta: “We have to withhold some of our quick judgment. That’s not helpful right now. We need to get comfortable kicking the tires on this thing.”

Excuse me for a moment. I’m pausing to go kick some tires.

Blueprint for an AI Bill of Rights to Fill Possible Policy Gaps

Screenshot from the fact sheet of the Office of Science and Technology Policy.

Last October, the Biden-Harris administration released a Blueprint for an AI Bill of Rights in anticipation of the need to protect the civil rights of Americans against big technology intrusions. Although there are already many protections in place, the Blueprint was developed to “inform policy-making to fill those gaps” where there aren’t any clear or designated policies. It provides five basic protections:


  • Safe and Effective Systems: You should be protected from unsafe or ineffective systems.
  • Algorithmic Discrimination Protections: You should not face discrimination by algorithms and systems should be used and designed in an equitable way.
  • Data Privacy: You should be protected from abusive data practices via built-in protections and you should have agency over how data about you is used.
  • Notice and Explanation: You should know that an automated system is being used and understand how and why it contributes to outcomes that impact you.
  • Alternative Options: You should be able to opt out, where appropriate, and have access to a person who can quickly consider and remedy problems you encounter.

At that same time, the White House also announced actions to be taken within the government in support of the Blueprint that would immediately assist citizens across vocations in education, health care, technology and so forth. This is what the White House has in store in education for 2023:


Protecting students and supporting educators:

  • To guide schools in the use of AI, the Department of Education will release recommendations on the use of AI for teaching and learning by early 2023. These recommendations will: give educators, parents and caregivers, students, and communities tools to leverage AI to advance universal design for learning; define specifications for the safety, fairness, and efficacy of AI models used within education; and introduce guidelines and guardrails that build on existing education data privacy regulations as well as introduce new policies to support schools in protecting students when using AI.

I look forward to reading what the Department of Education will release this year.

Sam Altman’s AI conversation and ChatGPT’s answer to my question

I’ve started doing some research on Artificial Intelligence. I’m mainly interested in its application to support learning for the millions of potential “students” who find themselves outside of a formal educational system either because of lack of opportunity or poverty. The idea would be that personalized learning scaffolding could be built through AI to fit the educational trajectory that a student needs to take. My desire to start down that AI road began before OpenAI’s Chat GPT came to the forefront.

As OpenAI came into my purview, I listened to an interview of Sam Altman, the CEO of OpenAI, to see if I could pick up any clues as to what might be coming down the AI pipe. Altman said that AI is the biggest technological platform of our generation—a legitimate revolution. He said that with AI, the marginal costs of intelligence and energy are trending towards zero. AI will impact ALL computing and will quicken iteration cycles. He said we will see an explosion of new companies that will use the large language model as a service.

The main societal issue at the beginning of the AI revolution will be disruption of economic activity. He suggested that we will need to have a new social contract on how we think about fairly distributing wealth, who will get access to AGI systems, and how governance will work. I think the AI disruption will also affect how we think about education, how it is distributed, what even is the nature of education. What will it be that we need to learn? Who will determine what we need to learn?

In the spirit of OpenAI, I decided to ask ChatGPT “What are the best ways in which AI can support learning?” I was surprised at its ability to immediately inform me of five different ways articulated in succinct terms. Here is what it gave back.

AI can support learning in several ways, including:

  1. Personalized Learning: AI can personalize learning experiences for individual students, using algorithms to adapt to their needs and progress. This can help students learn at their own pace, with content and activities that are tailored to their specific learning style and level.
  2. Intelligent Tutoring Systems: Intelligent tutoring systems can provide real-time feedback to students, helping them understand and learn from mistakes, and improve their skills. These systems can also track student progress and suggest activities or resources to help them improve.
  3. Automated Grading: AI-powered tools can help automate grading and provide more consistent and objective evaluations of student work. This can save teachers time and provide students with faster feedback on their progress.
  4. Adaptive Testing: Adaptive testing systems can use AI algorithms to dynamically adjust the difficulty level of questions based on the student’s performance. This can help identify knowledge gaps and provide more accurate assessments of student learning.
  5. Content Creation: AI can also be used to create educational content, such as videos or interactive simulations, that is tailored to specific learning objectives and student needs.

By incorporating AI into the learning process, students can benefit from more personalized and adaptive learning experiences, faster and more consistent feedback, and access to high-quality educational resources.

The Process by Which I Came to AI and Started Down a Path of Study

Before I started the IP&T 520 class this Spring Term (2021), I didn’t even have the idea of Artificial Intelligence (AI) in my head as a way to help with lifelong education. I just knew that there were some instructional design theories still undiscovered—according to Elder L. Tom Perry (1996)—and I wanted to find out what they were. As I stated in my Letter of Intent for my application to the IP&T program: As I’ve thought more about the quote from Elder Perry, I imagine that these “new” designs and learning theories will probably be centered around the personal learning environments of the individual and the integration of these personal learnings into a community of learners. 

About 15 years ago I took a class from Dr. Andrew Gibbons at BYU and became interested in design layers and design languages. I knew when I came back for a PhD that I wanted to look more into these areas as possible ways to help structure learning. I also came to this 520 class with Mary Parker Follett’s (1918, 1924),  observations about teaching and learning, and the teacher/student relation. I knew that I wanted to incorporate her ideas into anything that I would develop as a theory of design, and/or that the design theories I was looking for would possess a semblance of her ideas. 

As I mentioned in my 520 journal, my idea for AI in education and to find out if/how it is used, came about not from reading about it for education. I wanted a way for me to use AI to act as a memory storage and retrieval unit with some design layers mixed in to keep everything straight—and I wanted my “Aha!” learning moments to be preserved. I wanted AI technology to hold onto things that I had learned previously and preserve the emotional reactions from the moment when the learning had occurred. In tandem with the functions of this tool, I wanted AI to bring to mind—such as a periodical reminder through Siri or Alexa— things I had committed to memory over time so I could hang on to the learnings. 

When we were assigned in class to officially Tell Heather What You Will Do for Your Final Project I came up with the following: I want to write a literature review discussing AI as a curation tool for niche/personalized education and/or the roles of AI in Education, and develop ideas about design layers that may be involved in using such a tool.