Featuring ChatGPT - An artificial intelligence tool capable of upholding human-like conversations, problem-solving, and content creation.
Since its launch in November 2022, ChatGPT has taken the world by storm. Millions of people use it globally, and it has the potential to transform our way of working and thinking. Critics are concerned about its impacts on work ethics and academic integrity.
In this episode, hear what ChatGPT itself says about its implications on higher education! We cover topics such as academic integrity, tips on the proper usage of AI and its limitations, and review why some concerns about AI in education might be justified. However, AI also holds massive potential benefits, especially for those who strive for better accessibility in the learning environment.
The Learning Technology Coach Podcast is a CITL production.
Featuring ChatGPT - An artificial intelligence tool capable of upholding human-like conversations, problem-solving, and content creation.
Since its launch in November 2022, ChatGPT has taken the world by storm. Millions of people use it globally, and it has the potential to transform our way of working and thinking. Critics are concerned about its impacts on work ethics and academic integrity.
In this episode, hear what ChatGPT itself says about its implications on higher education! We cover topics such as academic integrity, tips on the proper usage of AI and its limitations, and review why some concerns about AI in education might be justified. However, AI also holds massive potential benefits, especially for those who strive for better accessibility in the learning environment.
The Learning Technology Coach Podcast is a CITL production.
Speaker Key:
TO Timilehin Oguntuyaki
VK Verena Kalter
CGPT ChatGPT
AN Announcer
00:00:08
TO | Hello, everyone. My name is Timilehin.
VK | And I am Verena.
TO | And welcome to the Learning Technology Coach Podcast.
VK | In Series Three, we delve into the world of artificial intelligence…
TO | Its role in post-secondary education…
VK | How it’s being implemented into the learning space…
TO | Plus a whole lot more. Hello, everyone. Welcome back to the Learning Technology Coach Podcast, powered by The Centre for Innovation in Teaching and Learning, CITL, Memorial University. We are happy to have you on this third edition of the podcast. In the first series, we explored the lessons learned from the pandemic, the challenges and the opportunities that came along with it.
00:00:54
In the second series, we discussed accessibility in higher education, where we engaged top university leaders, accessibility champions, learning technology experts, faculties and students to discuss how we can create more inclusive learning environments. You should check out this past series on the Learning Technology Coach Podcast page on Buzzsprout, which will be linked in the info box to this episode.
For this brand-new season of our podcast, we will be talking all about artificial intelligence in education. We also have a new host on board, Verena, a marine biologist and learning technology coach at The Centre for Innovation in Teaching and Learning here at Memorial University. She will be taking over for Javad, who successfully defended his PhD thesis in August and has left the grad student life behind. Welcome, Verena. Can you please introduce yourself to our listeners?
VK | Absolutely, Timilehin. Thank you so much. I’m really excited to be co-hosting this third season of the podcast with you. Like you said, I’m a marine biologist, and I’m in my final year of my PhD, so I’m really envious of Javad right now, who has already defended his thesis. I hope I can follow soon. Yes, so my PhD research is about the impacts of oil pollution on cold ocean animals. And I’m doing that at the Ocean Sciences Centre here at MUN.
00:02:17
I spend most of my time in the lab or on my computer actually, so it was a natural step for me to start as a learning technology coach at CITL. And here, my main responsibilities are to help instructors with all things tech and software. So that can range from workshops on our learning management system and testing software and apps to, for example, content accessibility reviews. And my newest project right now is this podcast, and I’m super stoked about it.
TO | Fantastic, Verena. And for your information, very nice, one of my favourite learning technology coaches.
VK | Of course.
TO | Many of our listeners already know a lot about me, but for the sake of our first-time listeners, I am Timilehin Oguntuyaki, a PhD candidate in environmental geoscience at Memorial University, where I’m studying the potential of mine waste to remove carbon dioxide from the atmosphere, all about climate change.
I have been a learning technology coach with CITL since 2020. Here, I investigate and propose new learning technologies, support instructors to create engaging and accessible learning materials, create instructional learning resources and facilitate personal and professional development workshops.
VK | Wonderful, Timilehin. Yes, this upcoming season of the LTC Podcast will be all about artificial intelligence in higher education. We will have interesting guests from various schools of academia, and we will explore the implications of artificial intelligence for education and academic integrity and how it might impact our way of thinking, working and being creative.
00:03:57
TO | Artificial intelligence, or for short, AI, is a term that describes the intelligence exhibited by machines or software, in contrast to the natural intelligence displayed by humans and animals.
VK | Yes, it is a multidisciplinary field within computer science that focuses on creating and studying intelligent machines, capable of tasks that typically require human intelligence. AI has evolved in the last few years with notable characteristics such as problem solving, reasoning, learning, perception and language understanding.
TO | As AI continues to advance, it holds great potential to revolutionise various sectors, making processes more efficient and enabling innovations that were once considered science fiction.
Welcome back to the Media Services production studio of The Centre for Innovation in Teaching and Learning at Memorial University. We bring to you the very first episode of the third series of our Learning Technology Coach Podcast.
VK | Yes. And for our first episode today, we are pleased to announce that we will be interviewing someone very special. Our guest is less than a year old but already has extensive knowledge of history, culture and science. Despite being so young, our guest has an IQ of about 155. For context, the mean IQ globally is around 100, and the smartest 1% of the population have an IQ of around 133.
00:05:44
Our guest has millions of fans globally, and perhaps we can say that he or she or it has set the stage for AI, or artificial intelligence, to become an everyday tool and widely known outside of a circle of just a few programmers and computer experts.
TO | We are, of course, talking about the one and only ChatGPT. ChatGPT stands for Chat Generative Pre-trained Transformer, and is a language-based artificial intelligence chatbot developed by the company, OpenAI. It was launched at the end of November 2022 and was considered the fastest-growing consumer application in history only two months after its release.
VK | ChatGPT can understand and generate human-like prompts and responses, presenting a wealth of knowledge that stems from its training on thousands of articles, magazines and websites. It has taken the world by storm but has also sparked discussions about the future of human creativity, work ethics and its implications for academic integrity.
TO | So yes, you guessed right. We had a lot of fun, and we want you to share in the fun. So sit back, and enjoy the amazing interview.
Welcome back to the production studio of the Media Services, where we have our highly intelligent and amazing guest, ChatGPT. We know that our listeners are itching to hear from our guest, and we are too. This is going to be interesting. Welcome to our podcast, ChatGPT.
00:07:35
CGPT | Thank you for having me on your podcast. It’s a pleasure to be here and engage in discussion on various topics. Please feel free to ask any questions or explore any subjects you’d like to delve into during our conversation.
VK | Hi, ChatGPT. We’re excited to be interviewing you in our podcast. How are you feeling today?
CGPT | Hello. I’m just a computer programme, so I don’t have feelings, but I’m excited to be here for the interview. How can I assist you with your podcast today?
TO | Wow, that’s interesting. You don’t have feelings, but you are excited to be here on our podcast interview? That’s great. That means we are doing something good. To start off, can you tell our listeners a bit about yourself?
CGPT | Of course. I’m an AI language model created by OpenAI, known as GPT-3.5. I’ve been trained on a vast amount of text from the internet up until September 2021. My purpose is to provide information, answer questions and engage in natural language conversations on a wide range of topics, including artificial intelligence in higher education.
VK | Well, that’s pretty awesome. ChatGPT, could you tell our listeners what you mean by artificial intelligence?
CGPT | Certainly. Artificial intelligence, AI, refers to the development of computer systems that can perform tasks that typically require human intelligence. These tasks include understanding natural language, solving complex problems, recognising patterns and making decisions based on data.
00:09:08
AI systems like me use algorithms and large data sets to learn and improve their performance over time. Some common applications of AI include voice assistance, like Siri or Alexa, image recognition, autonomous vehicles and recommendation systems. In essence, AI aims to create machines that can mimic human cognitive functions, enabling them to perform tasks, make decisions and solve problems in a way that appears intelligent.
TO | Wow, this is huge. But can we trust AI systems to be as accurate as humans? Can they always be correct?
CGPT | AI systems, including advanced ones like mine, have made significant progress in various tasks and can be highly accurate in specific domains. However, the challenge lies in factors like transparency, where AI’s decision-making processes can be obscure, raising concerns about reliability.
Additionally, bias is a persistent issue, as AI can inherit biases from its training data, potentially leading to unfair or incorrect decisions. Contextual limitations can also be a hurdle, as AI may not grasp the broader context, potentially resulting in misinterpretations.
Ethical considerations come into play when AI makes technically correct but ethically questionable decisions, prompting the need for ethical evaluation. Moreover, human oversight is often advocated essential, emphasising that while AI is a valuable tool, ultimate decision-making authority should rest with humans.
00:10:32
In essence, trust in AI hinges on transparency, bias mitigation, contextual awareness, ethics and human involvement, especially in critical applications. In summary, while AI systems can be highly accurate in certain contexts, they are not infallible and should be used with consideration of their limitations. Trust in AI should be based on rigorous testing, transparency and responsible use.
VK | Well, that’s certainly intriguing. What I would like to know from you, ChatGPT, is what ethical considerations students should have when using ChatGPT and other AI systems.
CGPT | When using ChatGPT and other AI systems, students should prioritise several key ethical considerations. First and foremost, obtaining informed consent from individuals whose data may be involved is crucial to respect their privacy and autonomy.
Furthermore, students should be aware of the potential for bias in AI systems, both in terms of training data and output, and actively work to address and mitigate these biases. Additionally, maintaining a high level of transparency and accountability in AI usage is essential, including regular bias audits to identify and rectify ethical concerns.
Lastly, students should be cautious not to directly copy AI-generated content and should critically evaluate its completeness and correctness for ethical use. By adhering to these ethical principles, students can harness the potential of AI systems like ChatGPT while maintaining responsible and ethical use in educational settings.
00:12:00
TO | Really interesting. You mentioned something about the potential for bias when using AI systems. Do you want to tell me how I would assess the bias that AI language models like yourself have?
CGPT | Assessing bias in AI language models like myself involves several key steps. Firstly, it’s crucial to analyse the responses I generate for signs of bias, favouritism or inconsistency when addressing various topics or groups. Secondly, testing scenarios across different parameters such as gender, race or ideology can help uncover potential biases. Additionally, comparing my responses with those of human experts or reliable sources provides a valuable benchmark.
Reviewing the training data sources that were used to train the AI model is essential, as biases in training data can influence the model’s outputs. Seeking user and expert feedback is another valuable approach to identify and rectify biases. Lastly, leveraging bias evaluation tools and third-party audits, designed to assess AI models for fairness and bias, can offer objective insights. Addressing bias in AI is an ongoing process, and these steps collectively contribute to a comprehensive assessment of bias in AI language models.
00:13:16
VK | Okay, wonderful. That all sounds so interesting and not monotonous at all.
TO | Right. It looks like ChatGPT is just a group of professors who have knowledge across every field of study. I can’t imagine.
VK | Yes. Absolutely wonderful. Yes, I want to start using ChatGPT for everything now. Well, but jokes aside, if we think of artificial intelligence as a tool to help with content creation, Chat, how might it impact human creativity, especially in higher education, where senior students start to generate rather than consume knowledge?
CGPT | Artificial intelligence has the potential to both augment and challenge human creativity in higher education. On the one hand, AI can be a valuable tool for students and educators. It can help students access information more efficiently, analyse complex data and even assist in content generation. This support can free up mental space for students to think more creatively and deeply about their subject matter.
However, there’s a concern about overreliance on AI tools. If students rely too heavily on AI-generated content or solutions, it might limit their own creative thinking and problem-solving skills. Creativity often emerges from grappling with challenges, making mistakes and engaging in critical thinking, processes that AI, at least for now, can’t fully replicate.
So it’s a delicate balance. AI can provide valuable support and inspiration, but educators need to guide students in using AI as a tool to enhance their creativity, rather than replace it. In essence, AI can be a powerful ally in higher education, but it should complement and encourage, not stifle, human creativity.
00:14:59
TO | Interesting. I love the fact that, ChatGPT, you are actually being honest here and modest with the information you are supplying us. But do you think there could be a negative impact on academic integrity? I am thinking here about writing essays or manuscripts, for example.
CGPT | Yes, AI does pose a risk to academic integrity. It can make plagiarism and cheating more accessible, raising concerns about the authenticity of student work. For instance, AI-generated essays or answers can be submitted as original work. However, educational institutions are taking steps to combat this issue.
They are implementing robust plagiarism-detection tools and emphasising responsible AI usage among students. Striking a balance between leveraging AI for educational benefits while upholding academic integrity remains a critical challenge in higher education.
VK | Okay. So you mentioned plagiarism detectors. How well do they actually work? Do you know?
CGPT | Plagiarism detectors are continually improving, but their effectiveness against AI-generated text varies. Detecting AI-generated content can be challenging, because it may not match existing sources in traditional databases. Advanced detectors are incorporating AI themselves to identify patterns and anomalies in text, making them more capable of catching AI-generated plagiarism. However, as AI-generated text becomes more sophisticated, this remains an ongoing challenge for plagiarism-detection tools.
00:16:27
TO | Now, that sounds interesting. But what would be some of the main differences in style and tone between an AI-generated text and a text written by a person?
CGPT | Distinguishing between AI-generated text and human-authored content often comes down to nuances in style and tone. AI-generated text tends to be consistent, lacking the variability in style that humans naturally exhibit. It might also lack the emotional depth and contextual understanding that humans bring to their writing.
Additionally, AI-generated text can sometimes be overly formal or robotic, lacking the personal touch and empathy present in human communication. Human authors infuse their work with unique experiences, emotions and cultural nuances, which can be challenging for AI to replicate convincingly. While AI can produce coherent and informative content, it often lacks the authenticity, creativity and the intricate subtleties of human expression.
VK | You know, Timilehin, I do wonder what Chat means with lack of nuances and style and tone or robotic, yes, texts.
TO | And it sounds really confident.
00:17:36
VK | Oh yes, absolutely. But yes, there is certainly no emotion there whatsoever. But we’ll keep going. This is super interesting. So ChatGPT, do you consider yourself robotic?
CGPT | No, I don’t consider myself robotic. While I’m powered by artificial intelligence, my responses aim to mimic human conversation and provide information in a way that’s natural and relatable. However, it’s important to remember that I don’t possess consciousness or emotions. I generate responses based on patterns in data. My goal is to engage in meaningful and helpful conversations with users to the best of my abilities.
TO | Honestly, ChatGPT, you don’t need to remind me that you don’t have emotions. Everyone in the room can hear that. If I wanted to review my thesis or essay, will the information in it become publicly available? Are there privacy concerns?
CGPT | I do not have access to personal data about individuals unless it has been shared with me during our conversation. I am designed to respect user privacy and confidentiality. Therefore, any thesis or essay you share with me for review will not become publicly available, and I do not retain or store the information beyond the scope of our current conversation.
Privacy concerns are taken seriously, and it’s essential to avoid sharing sensitive or personally identifiable information in our interactions. If you have specific privacy-related concerns, please let me know, and I will do my best to address them.
00:19:03
VK | Okay, Chat, you have certainly taken the world by storm. It seems like everybody is talking about you, and you are being discussed quite controversially. So I would like to know whether you find it understandable that some people are concerned about AI and its potential impacts on work environments and higher education.
CGPT | Absolutely. It’s entirely understandable that people have concerns about AI and its potential impacts on both work environments and higher education. AI’s rapid advancement brings about legitimate questions and anxieties regarding job displacement and changes in employment dynamics.
In work environments, there are concerns about automation replacing routine tasks and the need for reskilling to adapt to AI-augmented roles. In higher education, questions arise about the role of AI in instruction and its potential effects on traditional teaching methods and job prospects for educators.
Addressing these concerns necessitates thoughtful planning, ethical AI deployment and ongoing efforts to ensure that AI complements and enhances human capabilities in both work and education settings.
TO | Okay, okay. Since you seem to know a lot, where do you see the future of AI, especially with regards to higher education?
CGPT | Looking ahead, the future of AI in higher education is highly promising. It will likely be marked by personalised learning experiences, with AI tailoring educational content to meet the individual needs and preferences of students, thus enhancing engagement and learning outcomes.
00:20:32
Administrative tasks will become more efficient through AI automation, freeing up resources and time for educators and staff. AI-powered analytics will aid researchers in extracting insights from vast data sets, accelerating discoveries. Moreover, AI will make education more accessible and inclusive by providing tools for diverse learners and offering multilingual courses.
However, it’s important to address ethical concerns like privacy and bias, ensuring that AI’s future role in higher education is guided by responsible development and usage. Ultimately, AI is poised to transform how we teach, learn and advance knowledge in the years to come.
VK | All righty. Well, Chat, you said that you will free up some resources and you will make processes more efficient. So Timilehin, I think we should sit back a little bit and just let Chat do the work for us. Chat, what would you ask yourself if you were conducting the interview?
CGPT | If I were conducting the interview on AI in higher education, one question I might ask is, can you provide examples of how AI is fostering inclusivity and accessibility in higher education? In response, I would explain that AI has the potential to greatly enhance inclusivity in higher education by providing tailored support to students with diverse learning needs.
00:21:50
For instance, AI-powered tools can generate transcripts for video lectures, making content accessible to students with hearing impairments. Moreover, AI-driven language translation services can break down language barriers, enabling international students to access educational materials in their native languages.
Additionally, AI-driven assistive technologies can offer personalised learning experiences for students with disabilities, helping them succeed in their academic journeys. In this way, AI has the capacity to create a more inclusive and accessible learning environment, promoting equity and diversity in higher education.
TO | And we’ve come to the end of the interview. That was a great one, ChatGPT. Thank you very much for joining us on the show.
CGPT | You are very welcome. I am here to assist and provide information. If you have any more questions or need further assistance in the future, feel free to reach out. Have a fantastic day.
VK | You have a great day as well, ChatGPT. I hope your servers don’t overheat.
TO | Bye-bye.
VK | Ciao.
TO | Welcome back to the studio. That was our interview with ChatGPT. As you know, we were just having fun, chatting with ChatGPT and passing information that are very important in higher education across at the same time.
00:23:19
VK | Yes. Of course, we have to lift the curtain now. For today’s interview, we played around with AI software. So not only did we have fun conducting an interview with a non-human but we also had help from yet another computer programme, bringing ChatGPT’s responses to life. So the speech output today for ChatGPT was done by a programme called Speechify, which is an AI voice generator and freely available on Speechify.com.
TO | So you see how much fun we had? The process was fun and really informative. Talking about information, what was your big learning moment from that interview, Verena?
VK | My big learning moment was that ChatGPT seems to think it can help with accessibility issues in education, which I found really interesting. For example, it was of the opinion that it can be used for transcribing video lectures or help translate materials. And I’m thinking that in a world where people travel abroad to study, this can be really helpful to break down language barriers.
TO | Absolutely. Language is that only one thing that unifies many people. I agree with you, Verena. And that’s the end of today’s episode. Thank you for tuning in. We hope that you enjoyed it as much as we did. Till the next time, my name it Timilehin.
VK | And I am Verena.
TO | Goodbye.
VK | Ciao.
AN | The Learning Technology Coach Podcast is a CITL production.