Skip to content

ChatGPT and the Future of Learning

An Educator's Viewpoint

Feb 27, 2023

Launched November 30, 2022, as a free application on the OpenAI website, ChatGPT quickly took the world by storm. It is an Artificial Intelligence (AI) language modeling tool that stands to disrupt education in some very real ways. According to Reuters, ChatGPT is “trained using a machine learning technique called Reinforcement Learning from Human Feedback (RLHF), and can simulate dialogue, answer follow-up questions, admit mistakes, challenge incorrect premises, and reject inappropriate requests.” It can also come to incorrect conclusions and in its early debut had problems generating correct answers to math equations worded in a narrative. But overall, the narrative it does produce is stunning. ChatGPT is one of many AI tools on the horizon. What does this mean to educators? Dr. Kim Round, Associate Dean and the team leader behind WGU’s new M.S. in Learning Experience Design and Educational Technology joins our Learning Community editor for a Q&A to look at how ChatGPT might be used to help teaching and learning, and where it may present risks and challenges.

(Editor) As someone whose career has been deeply integrated with education technology, what was your first reaction to reading that ChatGPT was available to the public?

(Dr. Kim Round) Curiosity. With any innovation, I’m always curious and excited to learn about how it might best enhance the human experience. I’m also a pragmatist. Technology, by itself, is neither good nor bad. It’s the application of that technology that drives the benefits/risks. So, with ChatGPT, my first thought was how might this elevate critical thinking in the learning process. Would AI chat help students overcome the lower-level mechanics of learning to become better researchers, curators, and decision-makers? Under the right set of circumstances, I’m excited about its potential. We need to approach it with cautious optimism, understand its benefits and limitations, and determine how we can leverage it to design learning experiences. Across the board, we need to protect user privacy and information. How machines collect, curate, and learn their way into data can pose some ethical concerns.

(Editor) As a former engineer, what’s your confidence level and/or concerns with ‘engineering prompts’ like those used to model and train ChatGPT?

(Dr. Round) With an engineering background, my thoughts always go toward defining operating parameters. Essentially, under what conditions, can technology bring the most benefit? How does it fail?  We’re seeing inaccurate information generated from ChatGPT when the prompt is too broad. For example, the prompt “Write a five-paragraph synopsis of the TV show, ‘The West Wing’…” does not yield reliable results. In fact, I asked ChatGPT why John Spencer, a central actor in the show, was not included in the cast list. ChatGPT thanked me for pointing that out, apologized, and supplied additional information about John’s contributions. Keeping that in mind, other researchers have noted better accuracy in ChatGPT results when a user starts with a summary that provides context. Therefore, the usefulness and accuracy of the tool are highly dependent on the human partner’s ability to speak to the machine. This will be a skill I anticipate we’ll all need to develop, like how we learned to use search engine queries.

How different is this machine learning model from the introduction years prior of Wikipedia, or Google’s search capabilities – which initially also had educators up in arms?

I see it as very similar. The Web spurred the need for new competencies around digital literacy, a skill set where users needed to critically evaluate the accuracy of the artifacts identified through search results. This skill set is taught in many college and university first-year programs, if not earlier. In addition, effective learning design can push learners to make meaning from the information they uncover via the Web, as opposed to reciting facts. So, these types of assignments move the learner from the “Remember” level (the lowest level) in Bloom’s Taxonomy through Understand, Apply and Evaluate levels – empowering learners to construct new knowledge. AI tools, like ChatGPT, are meeting the same initial consternation by educators. However, as we learn our way into the potential and risks, learning innovation will accelerate as it did with the Web.  

The initial debut of ChatGPT was met with concern from schools, colleges, and universities about potential cheating and plagiarism. Were those concerns legitimate?

Well, the machine is learning as humans are learning about the machine. So, that reality has presented a challenge, and it will take time for institutions to develop learning experiences that can encompass the benefits of ChatGPT (or other AI tools). However, early adopters are identifying exciting strategies. For example, AI doesn’t necessarily relate an essay topic to a larger context or tell a story that resonates with an audience. 

Assignments could be built in a way that ChatGPT generates a description, the learner validates that the description is correct, leveraging critical thinking and research skill sets, and then uses that description to write the context and how it might relate to their intended audience. In this way, learners build new skills in data literacy, information curation, critical thinking, and research while operating at a higher level of Bloom’s Taxonomy. While these are benefits, AI will require institutions to consider their policies, assignments, and instructional approaches.

Is banning ChatGPT as some schools are doing a viable response? Will that get them a win in the long run?

I can understand how some institutions may feel caught off-guard and need time to pivot. So, pressing a short pause button to better understand the technology, especially in K-12 schools, is a strategy some institutions have employed. We need to be vigilant in protecting our children until we know what all the hazards are. However, banning ChatGPT, in the long run, will become a frustrating experience for faculty, administrators, and students, as well as a missed opportunity. The tool is part of the future of education, as it will be part of the future of work. Learners will be experiencing these AI-empowered experiences outside of school, and it has great potential to augment learning. So, I think it’s imperative that schools and higher education institutions get their arms around these technologies as they emerge.

Some professors are integrating ChatGPT into their assignments in more of a personal tutor capacity much like some allow/encourage students to use Grammarly. What do you think of this from your learner-centered view of the universe?

I think it’s great. I’m all about removing unnecessary friction from the learning experience, so learners can focus on the bigger lifts needed to scaffold their knowledge. From a learner empathy perspective, we’re providing a student with a just-in-time coach under the right circumstances. ChatGPT can provide personalized feedback, particularly helping learners with developing writing skills. In addition, ChatGPT can be queried for step-by-step explanations and examples.

Essentially, ChatGPT has the potential to provide personalized tutoring to help learners elevate their critical thinking, as opposed to becoming mired in the mechanics of learning. However, we need to encourage learners to practice digital literacy – to always validate the information they receive in the process.

A recent article by Stephen Marche in the Atlantic declares in the headline that “The College Essay is Dead” and that “Nobody is prepared for how AI will transform academia.” While the latter subhead may ring true as we all explore AI's potential, do you think the college essay is dead, or is the model just being rewritten?

I love how Harvard’s Dr. Chris Dede (Co-PI of the National AI Institute for Adult Learning and Online Education) talks about this in his “Silver Linings for Learning” podcast which I recently had the pleasure of being his guest on. We won’t necessarily be writing in 140-character-sound-bytes. However, we generally do not often write long essays outside of K-12 and higher education. In the workplace, we’re asked to practice brevity and synthesize our thoughts. I don’t think the college essay is dead, but the point of that type of assignment is to develop critical thinking and research skills in a particular area. So, I do think the way we construct college essays is changing and the final deliverable may not be the essay itself – it may be a peer review or a critical analysis of how ChatGPT approached the topic. Learners will need to expand their skill sets beyond being critical consumers of information to become effective curators of knowledge. (Link to the Atantic article here.)

In EdTech Digest CEO of Cengage Jim Chilton urges educators to take a beat and think of ways to integrate ChatGPT into their curriculum. What are your thoughts on that?

I think it’s wise. We shouldn’t let a tool drive the design of the learning experience. We need to be thoughtful about its application. However, we also need to account for the availability of the tool when constructing those experiences.  We’re discovering many thoughtful ways to incorporate AI tools that elevate learning. Each educator needs to consider their learning objectives first and then determine which tools, if any, can facilitate the learner journey. Sometimes the best tool for the job is a pencil.

Chilton brings up a valid point – one especially relevant to WGU’s access and equity-driven mission – that students are still struggling in this country to get good Internet access. Does this stand to deepen the digital divide?

Yes, and that’s a concern beyond AI. This is why initiatives that broaden access to laptops and free Internet are so important across all education sectors. However, the tools alone will not help learners reach the potential of AI-driven learning experiences. It is the thoughtful design of the learning experience, which is enhanced by the application of AI tools that will help close the divide as well. 

Once learners have access to these tools, as AI matures, they may encounter a more level playing field through personalization and adaptive learning environments. The machine could be trained in presenting experiences that empower a wide variety of neurodiverse, DE&I (Diversity, Equity, and Inclusion), and SEL (Social Emotional Learning) approaches, all of which could promote a more equitable learning opportunity. (Link to the EdTech Digest article here.)

If ChatGPT can pass an SAT test and an MBA exam, how might professors think differently about creating authentic learning environments where AI can’t replicate the student response?

I think it’s where effective learning experiences need to evolve anyway. We help humans construct knowledge by scaffolding new learnings onto their prior experiences. Building learning experiences and assessments that allow students to find personalized meaning through context-driven project-based work can accelerate learning. The rinse and repeat of “sit and get” and recall for the test will become less effective. The use of an AI partner can help the learner operate at a higher level of critical thinking when presented with a well-designed learning experience. However, the AI tool cannot personalize or draw broader conclusions to a context. I’d point back to Chris Dede again as he affirms, “We need to prepare people for things that AI cannot do…We need to teach students, ‘don’t let other people do your thinking for you.’”

In this next section we are providing you a glimpse into Dr. Round's session with ChatGPT where her prompts ultimately led to ChatGPT telling her it would need a human.

Dr. Round's prompts are in all capitals. ChatGPT's response (verbatim) is in italics.

(Round) CAN AI TEACH A CLASS? (ChatGPT) It is possible for AI to be used to teach a class, but it would require a significant amount of programming and training. AI systems can be designed to provide instruction on a wide range of topics, but they would not be able to answer questions or engage in meaningful discussions with students in the same way that a human teacher could. Additionally, AI systems are not capable of understanding or responding to the emotional needs of students, which is an important part of teaching. As a result, while AI could be used as a tool to supplement human instruction, it would not be able to fully replace a human teacher.

 

(Round) CAN AI DESIGN A CLASS? (ChatGPT) In theory, AI could be used to design a class by analyzing a set of learning objectives and creating a lesson plan that is tailored to achieving those objectives. This would involve using algorithms to organize and sequence the material in a way that is effective for learning, and potentially even incorporating elements of gamification or other techniques to make the class more engaging for students. However, it is important to note that AI systems are not capable of understanding or accounting for the complex needs and preferences of individual students, and as a result, a class designed by AI would not be able to provide the same level of personalized instruction that a human teacher could.

 

(Round) CAN AI ASSIST A LEARNING EXPERIENCE DESIGNER? (ChatGPT) AI could potentially be used to assist with Learning Experience Design (LXD) in a number of ways. For example, AI could be used to analyze large amounts of data about student learning and behavior in order to identify patterns and trends that can inform the design of effective learning experiences. AI could also be used to generate personalized learning plans for individual students, based on their unique needs and abilities. Additionally, AI could be used to create interactive learning environments that adapt to the needs and preferences of individual students in real-time. However, it is important to note that AI would not be able to replace the creative and human elements of LXD and would only be able to assist with certain aspects of the design process.

ChatGPT went on to explain to Dr. Round that while artificial intelligence and machine learning systems have come a long way in recent years, there are still certain aspects of the learning process where human interaction and intervention are necessary. Dr. Round will speak more about this in future articles, but these areas included: Setting Goals, Motivation and Engagement, Social and Emotional Learning, and Creativity and Critical Thinking. For these things, even ChatGPT recognizes it needs a human.

 

 

As the leader at WGU bringing to market a master’s degree in Learner Experience Design (MSLxDET) across K-12, higher education, and corporate training how does this change your game plan if at all?

In the MSLxDET program, we understood the technology landscape would be constantly changing, so we designed the program to accommodate and embrace this reality. Number one, we do reinforce the tenet that technology choice should always follow the design. So, in the ChatGPT conversations, we need to be careful that the tool isn’t leading the learning, or that we’re designing around the use of a tool. That’s still highly relevant. However, I think AI chat is a resource (i.e., the Web) that we can weave into learning experiences as it makes sense.  I’m really pleased that our program was designed to easily accommodate disruptive innovations from both a content and an assessment standpoint.  We want our graduates prepared to pivot as new technologies emerge.

As an educator, what’s your dream for the future of learning in the world of AI?

Over time, AI can provide a foundation for offering personalized learning experiences, where unnecessary friction is removed, allowing the student to focus on achieving transformational learning. Through technology (i.e., AI and analytics) learning environments adapt to each learner based on their needs. It ethically knows learners, protecting their data and assuring their privacy. It follows the learners throughout their journey and is seamless beyond courses, presenting assistance as needed. Learners will experience greatly enhanced personalized journeys powered by AI in the consumer space. They will expect this in the learning space as well. 

And, as a spouse and parent of neurodiverse magnificent men, I look forward to this reality for the future of our family and others. For my husband and sons, schooling was something to survive, as opposed to a place to thrive. All were incredibly resilient and persevered, but not without some challenging and traumatic moments. 

Recommended Articles

Take a look at other articles from WGU. Our articles feature information on a wide variety of subjects, written with the help of subject matter experts and researchers who are well-versed in their industries. This allows us to provide articles with interesting, relevant, and accurate information.