Research Article

ECNU Review of Education

2023, Vol. 6(3) 355–366
Unlocking the Power of © The Author(s) 2023
Article reuse guidelines:
ChatGPT: A Framework for sagepub.com/journals-permissions
DOI: 10.1177/20965311231168423

Applying Generative AI in journals.sagepub.com/home/roe

Education

Jiahong Su (苏嘉红)
The University of Hong Kong

Weipeng Yang (杨伟鹏)

The Education University of Hong Kong

Abstract
Purpose: Artificial intelligence (AI) chatbots, such as ChatGPT and GPT-4, developed by OpenAI,
have the potential to revolutionize education. This study explores the potential benefits and chal-
lenges of using ChatGPT in education (or “educative AI”).
Design/Approach/Methods: This paper proposes a theoretical framework called “IDEE” for
educative AI such as using ChatGPT and other generative AI in education, which includes identi-
fying the desired outcomes, determining the appropriate level of automation, ensuring ethical con-
siderations, and evaluating effectiveness.
Findings: The benefits of using ChatGPT in education or more generally, educative AI, include a
more personalized and efficient learning experience for students as well as easier and faster feed-
back for teachers. However, challenges such as the untested effectiveness of the technology, lim-
itations in the quality of data, and ethical and safety concerns must also be considered.
Originality/Value: This study explored the opportunities and challenges of using ChatGPT in
education within the proposed theoretical framework.

Corresponding author:
Jiahong Su, The University of Hong Kong, Room 219, Runme Shaw Building, Pokfulam Road, Hong Kong SAR, China.
Email: [email protected]

Creative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative
Commons Attribution-NonCommercial 4.0 License (https://creativecommons.org/licenses/by-nc/4.0/) which permits
non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as
specified on the SAGE and Open Access page (https://us.sagepub.com/en-us/nam/open-access-at-sage).
356 ECNU Review of Education 6(3)

Keywords
ChatGPT, educative AI, generative AI, GPT-4, IDEE framework

Date received: 2 March 2023; revised: 6 March 2023; accepted: 8 March 2023

Introduction
The use of artificial intelligence (AI) in education has gained significant attention in recent years,
with a growing number of educational institutions and organizations exploring the potential benefits
of AI-driven technologies (Dwivedi et al., 2021; Su & Yang, 2022). One such technology is
ChatGPT, a state-of-the-art natural language processing (NLP) model developed by OpenAI in
2019 (Lebrenz et al., 2023; Lund & Wang, 2023). ChatGPT is a form of generative AI that uses
algorithms to generate new text similar to what a human might write. It is a language model that
uses deep learning to generate human-like responses to natural language queries. ChatGPT is
designed to be used in a conversational setting, allowing users to interact with the model naturally
and intuitively. As a powerful AI application, ChatGPT can answer questions, write stories, sum-
marize documents, and compose essays. On March 14, 2023, OpenAI released GPT-4, an upgraded
version of ChatGPT.
ChatGPT has recently been used in a variety of fields, including library services (Lund &
Wang, 2023), healthcare (Aydın & Karaarslan, 2022), and education (Baidoo-Anu & Owusu
Ansah, 2023; Rudolph et al., 2023). In the field of education, ChatGPT can be used to create
virtual tutors, answer student questions, and provide personalized learning experiences. It
may also be used as a real-world AI application to empower teachers and students to
develop their AI literacy, which refers to the ability to understand, use, and critically evaluate
AI technologies and their impact on society (Ng et al., 2021; Su et al., 2022). It encompasses a
range of skills and knowledge, including the ability to comprehend AI concepts, techniques,
and algorithms as well as the ability to analyze and evaluate AI systems and their applications
(Su & Zhong, 2022; Yang, 2022). AI literacy also involves understanding the ethical, legal, and
social implications of AI, and the ability to communicate effectively about AI issues and ideas
(Su et al., 2023). As a user-friendly AI application, ChatGPT can be used as an educational tool
to foster teachers’ and students’ abilities to navigate and engage with the rapidly changing
world of AI with confidence and understanding.
Following this line of argument, this conceptual paper has the following objectives: (1) to
propose a theoretical framework for guiding the use of ChatGPT and other generative AI in
education (or “educative AI,” which refers to the use of AI in educational settings to enhance teach-
ing and learning outcomes) and (2) to illustrate ChatGPT’s potential benefits and challenges for use
Su and Yang 357

in the field of education. This study also provides recommendations for future research, policy, and
practice in the area of educative AI.

What is ChatGPT?
ChatGPT is a type of large language model (Thorp, 2023). Large language models are a type of
AI that use deep learning techniques to analyze and generate text (Shen et al., 2023). ChatGPT
is a type of large language model created to generate human-like text in NLP tasks (Shen et al.,
2023). It is designed to generate human-like text based on a large corpus of text data and is
trained to perform various language tasks, such as answering questions, writing stories, com-
posing code, and generating essays. The foundation of ChatGPT is GPT-3, the third model
developed for NLP projects (Entrepreneur, 2023; Thorp, 2023), which was recently upgraded
to GPT-4. We requested that ChatGPT explain itself.

I am ChatGPT, a large language model developed by OpenAI. I am designed to generate human-like

responses to a wide range of natural language input, including questions, statements, and commands.
I am trained on a vast amount of text data from the internet, including books, articles, and websites,
using a deep learning algorithm called a transformer. As a result, I can understand and respond to a
wide range of topics, including science, history, current events, and popular culture. My purpose is
to provide helpful and informative responses to users, and to assist in a variety of tasks that require
natural language processing. (ChatGPT, February 21, 2023)

We then asked, “How does ChatGPT work?” ChatGPT gave the following answer:

ChatGPT works by using a deep learning algorithm called a transformer to process natural language
inputs and generate human-like responses. Here’s a brief overview of how it works:

1. Preprocessing: Before I can start generating responses, the input text is preprocessed to make it
easier for the transformer to understand. This involves converting the text into a numerical
representation called a token, which captures the meaning of each word.
2. Encoding: Once the input text has been tokenized, it’s passed through a series of encoding layers. These
layers use attention mechanisms to help the model focus on the most relevant parts of the input text.
3. Decoding: Once the input text has been encoded, the model generates a response by decoding the encoded
text into natural language. This is done using a similar set of attention mechanisms as in the encoding step,
which helps the model choose the most relevant information to include in the response.
4. Postprocessing: Finally, the generated text is postprocessed to remove any unnecessary tokens and format-
ting, and presented to the user as a natural language response. The transformer architecture used by
ChatGPT is highly sophisticated and allows the model to generate complex and nuanced responses to
a wide range of input text. It’s trained on a massive dataset of text data from the internet, which
358 ECNU Review of Education 6(3)

enables it to understand and respond to a wide variety of topics and styles of language. (ChatGPT,
February 21, 2023)

We asked the follow-up question, “What are the limitations of ChatGPT?” ChatGPT provided
the following answer:

As an AI language model, ChatGPT has several limitations, including:

1. Lack of Common Sense: While ChatGPT has access to a vast amount of data, it lacks common sense
and may sometimes generate responses that are technically correct, but do not make sense in the real
world.
2. Limited Understanding of Context: ChatGPT’s understanding of context is limited, and it may some-
times struggle to understand the broader meaning of conversations. It may also fail to pick up on
nuances or subtext in a conversation.
3. Biased Data: ChatGPT is only as unbiased as the data it is trained on, and if the data contains biases or
inaccuracies, it may replicate those biases in its responses.
4. Inability to Perform Physical Tasks: ChatGPT is a language model and cannot perform physical tasks,
such as cooking or cleaning.
5. Lack of Emotional Intelligence: While ChatGPT can generate responses that appear to convey emo-
tions, it does not actually experience emotions and may struggle to understand or respond appropri-
ately to emotionally charged conversations.
6. Vulnerability to Adversarial Attacks: ChatGPT can be vulnerable to adversarial attacks, where the input
data is specifically designed to cause it to generate incorrect or harmful responses. Overall, while
ChatGPT is a powerful tool for generating human-like responses to a wide variety of inputs, it
has several limitations that must be considered when using it. (ChatGPT, February 21, 2023)

The IDEE framework for using ChatGPT in education

The following theoretical framework (Figure 1; the IDEE Framework) can be used as a guide while
utilizing ChatGPT and other generative AI in education:

1. Identify the Desired Outcomes: Before using ChatGPT or other generative AI in

education (or “educative AI”), it is important to identify the objectives of the application.
This ensures that the use of technology aligns with desired outcomes.
2. Determine the Appropriate Level of Automation: Depending on the objectives, it may be
appropriate to fully automate the teaching or learning experience using educative AI or
to use it as a supplement to traditional teaching methods.
3. Ensure Ethical Considerations: The ethical implications of using educative AI must be care-
fully considered, including potential biases, and their impact on teachers and students.
Su and Yang 359

Figure 1. Theoretical framework for using generative AI in education.

Note. Permission is granted to incorporate the diagram into a work, subject to certain conditions.
Firstly, neither the publisher nor the user may assert any copyright claims over the image. Secondly, the
language below must be used to label or cite the image. Revised version of the IDEE Theoretical Framework
for Using Generative AI in Education. © Jiahong Su & Weipeng Yang, 2023. Reproduced with permission. Su
and Yang (2023). Unlocking the power of ChatGPT: A framework for applying Generative AI in
education. ECNU Review of Education.

4. Evaluate the Effectiveness: It is important to evaluate the effectiveness of educative AI in

achieving the desired outcomes.

An inspiring example of the use of ChatGPT in education is the development of virtual tutors
for language learning. Using ChatGPT, a virtual tutor can provide personalized feedback and
conversation practices for language learners. The virtual tutor can also adapt to the learners’
360 ECNU Review of Education 6(3)

level and pace, thereby providing a highly customized learning experience. This can be espe-
cially helpful for learners who do not have access to in-person language tutors or prefer to
learn on their schedule.
In one of our current research projects, we are trying to use ChatGPT to help coaches provide
responsive and timely feedback to early childhood teachers. Below, we detail how the framework
can be applied to the example of using ChatGPT to facilitate coaches in providing responsive and
fast feedback to early childhood teachers:

1. Identify the Desired Outcomes: The objective, in this case, is to provide early childhood tea-
chers with targeted and timely feedback on their teaching practices to improve the quality of
early childhood education.
2. Determine the Appropriate Level of Automation: ChatGPT can be used to automatically
generate feedback based on observations made by the coach during classroom observations.
This feedback can be customized to the specific needs and challenges of each teacher, pro-
viding a highly tailored and efficient coaching experience.
3. Ensure Ethical Considerations: It is important to ensure that the feedback generated by
ChatGPT is free from bias and is based on objective observations. Additionally, the use
of ChatGPT should not replace the important role of human coaches in providing support
and guidance to early childhood teachers.
4. Evaluate the Effectiveness: The effectiveness of using ChatGPT to facilitate coaching can be
evaluated by analyzing the impact of feedback on the teaching practices and outcomes of
early childhood teachers. This can be achieved through teacher evaluations, feedback
surveys, and other assessment tools.

To facilitate the coaching of early childhood teachers, ChatGPT can be applied in the develop-
ment of a virtual coach that can provide immediate feedback to teachers during classroom observa-
tions. For example, if a virtual coach observes that a teacher does not use enough open-ended
questions to promote critical thinking, it can provide feedback on the importance of using open-
ended questions and suggest specific examples that the teacher can use in future lessons. This
can help early childhood teachers improve their teaching practices and ultimately enhance the learn-
ing outcomes of young children.

Key issues of using ChatGPT in education

In this section, we highlight several potential benefits, limitations, challenges, future research direc-
tions, and suggestions associated with the use of ChatGPT in education, which can be generalized to
other educative AI.
Su and Yang 361

Potential benefits
The use of ChatGPT in education could provide several benefits. First, it can provide a more per-
sonalized learning experience for students. ChatGPT can encourage teachers to reflect on educa-
tional content and trust between teachers and students. By using ChatGPT to create personalized
recommendations and virtual tutors, students can receive more targeted instruction tailored to
their individual needs. For instance, if students need assistance with a math problem, the
ChatGPT can offer detailed instructions on how to solve the issue.
Second, ChatGPT can make it easier for teachers to answer students’ questions. By using ChatGPT to
generate answers to students’ questions, teachers could save time and energy, which could be better spent
on other tasks. For example, do students ask teachers about game-based learning? ChatGPTcan answer this
question: “Game-based learning is an educational approach that uses games and game mechanics to
enhance learning outcomes. It involves the use of digital or nondigital games as part of the learning
process to help learners develop their knowledge, skills, and attitudes. In game-based learning, the
game serves as a tool for engaging learners and provides a fun, immersive, and interactive learning experi-
ence. The game can be used to teach a wide range of subjects, from mathematics and science to social
studies and languages. Game-based learning is an effective way to promote active learning, increase
motivation and engagement, and improve knowledge retention. It is often used in both formal and informal
learning settings such as schools, museums, and training programs.” (ChatGPT, February 21, 2023)
Third, ChatGPT can provide a more engaging learning experience for students. ChatGPT can
improve teaching models, assessment systems, and education ecology by empowering the
teacher-student-technology triad structure. By using ChatGPT to create virtual tutors and persona-
lized recommendations, students can have a more interactive and enjoyable learning experience.
Fourth, ChatGPT can provide useful suggestions for teachers. ChatGPT can accelerate the trans-
formation of AI by assisting and coordinating virtual and physical relationships within the current
institutional system for deep involvement in various directions, expanding the broad network, and
forming a new ecology of education. For example, we asked ChatGPT about “how to teach young
children about AI.” ChatGPT provided the following answer:

“Teaching young children about AI can be a fun and interesting way to introduce them to the world of
technology and innovation. Here are some ideas for teaching young children about AI:

1. Start With the Basics: Begin by explaining what AI is and how it works. You can use simple examples
to illustrate the concept, such as a talking toy or a smart home device.
2. Use Age-appropriate Language: When teaching young children about AI, it is important to use lan-
guage and concepts that they can understand. Avoid using technical jargon and focus on simple expla-
nations that relate to their everyday experiences.
362 ECNU Review of Education 6(3)

3. Demonstrate AI in Action: Show children examples of AI in action, such as virtual assistants or chat-
bots. You can also let them interact with simple AI-powered toys or games to help them understand
how it works.
4. Explain the Benefits of AI: Talk to children about the many ways that AI can be used to help people,
such as by improving healthcare or making our lives easier and more convenient.
5. Discuss the Ethical Implications of AI: It is important to teach children about the ethical considerations
of AI, such as the need to ensure that it is used in a responsible and fair way.
6. Encourage Curiosity: Encourage children to ask questions and explore AI on their own. Provide them
with resources, such as books or online tools, to help them learn more about this exciting and rapidly
evolving field.
By introducing young children to the concepts and applications of AI in a fun and engaging way, you
can help inspire their curiosity and interest in this important field of technology. (ChatGPT, February
21, 2023)

Fifth, the ChatGPT could provide useful suggestions for writing an essay. ChatGPT can assist stu-
dents in writing essays by recommending topics, outlining structures, providing ideas, and improving
their academic writing. For example, a student can ask for help in writing an essay on early childhood
education and ChatGPT can provide suggestions for statements and potential topics for body para-
graphs. On this basis, students can combine their thoughts and viewpoints to complete their essays.
However, students’ critical thinking is required to ensure the accuracy of writing.

Potential limitations
The use of ChatGPT in education has some limitations. First, ChatGPT is still an emerging technol-
ogy and its effectiveness has not been fully tested. While the studies mentioned above suggest that
the ChatGPT could be a useful tool for education, more research is needed to determine its effect-
iveness in different contexts.
Second, ChatGPT can be limited by data quality. If the data used to train the model is of low
quality, the responses of the model may not be accurate or reliable. ChatGPT may have negative
effects and implies the need to adjust educational goals, methods, and ethics education.
Third, ChatGPT can be limited by the complexity of the tasks it is asked to perform. Although
ChatGPT can generate human-like responses to simple queries, it may struggle with more
complex tasks.

Challenges
Cost. An important aspect to consider is the cost of implementing the ChatGPT in education. This
technology requires significant investment in terms of both hardware and software as well as
ongoing maintenance and support. This may present a challenge for some educational institutions,
Su and Yang 363

particularly those in lower-income areas, and it is important to find ways to make the technology
more accessible and affordable.

Ethical and safety issues. The use of the ChatGPT in education also raises ethical and safety
issues. First, there is the potential for technology to be used to manipulate or deceive students.
If the model is not properly monitored and regulated, it can be used to provide inaccurate infor-
mation or lead students down the wrong path. Second, there is the potential for technology to be
used to invade students’ privacy. If the model is not properly secured, it can be used to collect
sensitive information from students without their prior knowledge or consent. Third, there is the
potential for technology to be used to discriminate against certain students. If the model is
not trained on data that are representative of all students, it can be used to provide unequal
access to education.

Challenging the existing assessment system. Many educators, academic institutions, and schools are
concerned about students using ChatGPT to complete their homework. Consequently, local educa-
tional authorities around the world often prohibit the use of ChatGPT in schools. For example, the
University of Hong Kong has temporarily prohibited students from utilizing ChatGPT and other
AI-based tools in their academic assignments (Yau & Chan, 2023). In the long term, ChatGPT
may lead people to believe that knowledge is no longer important.

Future research directions

First, future research should focus on developing and evaluating AI-based educational applications
and exploring the potential benefits and challenges of using this technology in different educational
contexts and settings.
Second, it is also important to conduct studies that examine the impact of ChatGPT and/or other
generative AI applications on student learning outcomes, such as academic achievement, motiv-
ation, and engagement. Furthermore, future research should continue to explore the ethical and
social implications of using AI in education, including its potential impact on human teachers
and the need for appropriate regulations and policies.
Third, further research is needed to fully understand the potential of this technology and identify
effective strategies for its use in education. It is important to stay up-to-date with the latest devel-
opments in AI.
Fourth, informed by the IDEE framework, further research is needed to determine the effective-
ness of ChatGPT in different contexts (e.g., teacher education, professional development, early
childhood education, formal schooling, lifelong learning, special education, and online learning)
and to ensure that the technology is used responsibly and ethically. In the context of early childhood
364 ECNU Review of Education 6(3)

education, for instance, ChatGPT can be used by young children who cannot read and write through
voice-activated interfaces, such as smart speakers or virtual assistants. Children can ask ChatGPT
questions or give commands through voice, and the AI model can respond with audio outputs.
Thus, children who are not yet able to read and write can still interact with and benefit from tech-
nology. However, it is important to note that the use of AI technology in young children should be
carefully monitored and guided by adults to ensure safety and well-being.

Suggestions for policy and practice

It is important to establish policies and standards for cultivating digital literacy, optimizing
the curriculum system, innovating teaching methods, and adhering to evaluation guidance.
To fully realize the potential of generative AI in education, it is important to involve educa-
tors, students, and other stakeholders in the development and implementation processes
within the proposed theoretical framework. This will help ensure that the technology is
designed and used in a way that meets the needs of all parties and supports student learning
and success.
Furthermore, the issue of data privacy and security in the use of generative AI in education is
crucial. The use of AI in education generates a large amount of data on students, including their
academic performance, learning preferences, and personal information. It is crucial to ensure that
the data are protected and used responsibly and ethically.
In addition, it is important to consider the ethical implications of using generative AI in educa-
tion. These may include issues related to fairness, bias, and accountability. For example, it is
important to ensure that generative AI is not biased toward certain groups of students and that it
provides equitable learning opportunities for all students.
Another important aspect to consider is the issue of personalization when using generative AI in
education. Personalized learning has been shown to have positive effects on student achievement
and engagement, and generative AI has the potential to provide students with highly personalized
educational experiences. However, it is important to ensure that the use of generative AI in educa-
tion does not lead to increased inequalities and that students from all backgrounds have access to
this technology and its benefits.
Finally, it is important to consider the role of human teachers in the integration of generative AI into
educational practices. Teachers play a crucial role in ensuring that students receive high-quality educa-
tion and foster positive learning experiences, and their perspectives and expertise are essential for ensur-
ing that generative AI is used effectively and responsibly in education. It is also important to consider the
potential impact of generative AI on teachers’ roles and the teaching profession. While generative AI
has the potential to facilitate and enhance teaching and learning, it is also important to consider how
it may change the role of teachers and the skills they need to be effective in the classroom.
Su and Yang 365

Conclusion
The use of ChatGPT and other generative AI in education, or “educative AI,” can provide students
with highly personalized and interactive learning experiences; however, it is important to approach
its integration into educational practices responsibly and ethically, with the support of a sound the-
oretical framework. This will ensure that educational institutions can take advantage of new
advances and keep pace with the changing landscape of education. This paper explores several
potential benefits, limitations, challenges, future research directions, and suggestions for using
ChatGPT in educational settings. This study highlights three key advantages of incorporating
ChatGPT in educational settings: a personalized learning experience for students, improved
support for teachers in answering student questions, and assistance with writing essays. Future
research in this field includes developing and evaluating AI-based educational tools, exploring
the benefits and challenges in various educational contexts, assessing the impact on student learning
outcomes, making ethical considerations, and examining their effectiveness in different situations.

Contributorship
Jiahong Su was responsible for conceptualization, methodology, as well as writing the original draft and
reviewing and editing the manuscript. Weipeng Yang contributed to the conceptualization, writing the original
draft, and reviewing and editing the manuscript.

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publica-
tion of this article.

Funding
The authors received no financial support for the research, authorship, and/or publication of this article.

ORCID iDs
Jiahong Su https://orcid.org/0000-0002-9681-7677
Weipeng Yang https://orcid.org/0000-0002-8057-2863

References
Aydın, Ö., & Karaarslan, E. (2022). OpenAI ChatGPT generated literature review: Digital twin in healthcare.
Available at SSRN 4308687.
Baidoo-Anu, D., & Owusu Ansah, L. (2023). Education in the era of generative artificial intelligence (AI):
Understanding the potential benefits of ChatGPT in promoting teaching and learning. Available at SSRN
4337484.
366 ECNU Review of Education 6(3)

Dwivedi, Y. K., Hughes, L., Ismagilova, E., Aarts, G., Coombs, C., Crick, T., & Williams, M. D. (2021).
Artificial intelligence (AI): Multidisciplinary perspectives on emerging challenges, opportunities, and
agenda for research, practice, and policy. International Journal of Information Management, 57,
101994. https://doi.org/10.1016/j.ijinfomgt.2019.08.002
Entrepreneur. (2023). ChatGPT: What is it and how does it work? https://www.entrepreneur.com/science-
technology/chatgpt-what-is-it-and-how-does-it-work/445014
Liebrenz, M., Schleifer, R., Buadze, A., Bhugra, D., & Smith, A. (2023). Generating scholarly content with
ChatGPT: Ethical challenges for medical publishing. The Lancet Digital Health, 1–2. https://doi.org/
10.1016/S2589-7500(23)00019-5
Lund, B. D., & Wang, T. (2023). Chatting about ChatGPT: How may AI and GPT impact academia and librar-
ies? Library Hi Tech News.
Ng, D. T. K., Leung, J. K. L., Chu, S. K. W., & Qiao, M. S. (2021). Conceptualizing AI literacy: An explora-
tory review. Computers and Education: Artificial Intelligence, 2, 100041. https://doi.org/10.1016/j.caeai.
2021.100041
Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments in higher
education? Journal of Applied Learning and Teaching, 6(1), 1–22. https://doi.org/10.37074/jalt.2023.6.1.9
Shen, Y., Heacock, L., Elias, J., Hentel, K. D., Reig, B., Shih, G., & Moy, L. (2023). ChatGPT and other
large language models are double-edged swords. Radiology, 230163. https://doi.org/10.1148/radiol.
230163
Su, J., Ng, D. T. K., & Chu, S. K. W. (2023). Artificial intelligence (AI) literacy in early childhood education:
The challenges and opportunities. Computers and Education: Artificial Intelligence, 4, 100124. https://doi.
org/10.1016/j.caeai.2023.100124
Su, J., & Yang, W. (2022). Artificial intelligence in early childhood education: A scoping review. Computers
and Education: Artificial Intelligence, 3, 100049. https://doi.org/10.1016/j.caeai.2022.100049
Su, J., & Zhong, Y. (2022). Artificial intelligence (AI) in early childhood education: Curriculum design and
future directions. Computers and Education: Artificial Intelligence, 3, 100072. https://doi.org/10.1016/j.
caeai.2022.100072
Su, J., Zhong, Y., & Ng, D. T. K. (2022). A meta-review of literature on educational approaches for teaching AI
at the K-12 levels in the Asia-Pacific region. Computers and Education: Artificial Intelligence, 3, 100065.
https://doi.org/10.1016/j.caeai.2022.100065
Thorp, H. H. (2023). ChatGPT is fun, but not an author. Science (New York, N.Y.), 379(6630), 313–313. https://
doi.org/10.1126/science.adg7879
Yang, W. (2022). Artificial intelligence education for young children: Why, what, and how in curriculum
design and implementation. Computers and Education: Artificial Intelligence, 3, 100061. https://doi.org/
10.1016/j.caeai.2022.100061
Yau, C., & Chan, K. (2023). University of Hong Kong temporarily bans students from using ChatGPT, other
AI-based tools for coursework. South China Morning Post. https://www.scmp.com/news/hong-kong/
education/article/3210650/university-hong-kong-temporarily-bans-students-using-chatgpt-other-ai-based-
tools-coursework