importance of critical thinking to understand chatgpt

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

View all journals
Explore content
About the journal
Publish with us
Sign up for alerts
Correspondence
Published: 15 August 2023

Importance of critical thinking to understand ChatGPT

Frank Emmert-Streib ORCID: orcid.org/0000-0003-0745-5641 1

European Journal of Human Genetics volume 32 , pages 377–378 ( 2024 ) Cite this article

401 Accesses

Metrics details

Data mining
Genetics research

This is a response to [ 1 ] providing constructive criticism about [ 2 , 3 ]. In the following, we will address the points of criticism in the order of appearance as they were presented in [ 1 ].

A point of criticism raised by [ 1 ] seems to be about the term “understanding”. The authors note that ChatGPT does not have the capacity for self-awareness or cognition nor is ChatGPT conscious in any form. Furthermore, the authors point out that ChatGPT is based on predictions and not understanding. In our opinion this is correct and none argued otherwise. In fact, the term “understand” occurs only once in [ 3 ], namely in the title, stated as a question - with a question mark at the end. Also the study in [ 2 ] does not aim to go beyond the predictive ability of ChatGPT.

This is a preview of subscription content, access via your institution

Access options

Ray PP, Majumder P. Beyond the Hype: a comprehensive critique of ChatGPT’s applicability in genetics. Eur J Hum Genet. 2023. https://doi.org/10.1038/s41431-023-01442-5 .

Duong D, Solomon BD. Analysis of large-language model versus human perfor- mance for genetics questions. Eur J Hum Genet. 2023. https://doi.org/10.1038/s41431-023-01396-8 .

Emmert-Streib F. Can ChatGPT understand genetics? Eur. J. Hum. Genet. 2023. https://doi.org/10.1038/s41431-023-01419-4 .

Turing AM. I.—Computing machinery and intelligence. Mind. 1950;LIX:433–60. https://doi.org/10.1093/mind/LIX.236.433 .

Article Google Scholar

Goertzel B. Artificial general intelligence: concept, state of the art, and future prospects. J Artif Gen Intell. 2014;5:1.

Emmert-Streib F, Dehmer M. Evaluation of regression models: model assessment, model selection and generalization error. Machine learning and knowledge extraction 1, no. 1 2019:521–51.

Facione PA, Sanchez CA, Facione NC, Gainen J. The disposition toward critical thinking. J Gen Educ. 1995;44:1–25.

Google Scholar

Emmert-Streib F, Moutari S, Dehmer M. Mathematical foundations of data science using R. Walter de Gruyter GmbH & Co KG. 2022.

George EB. Science and statistics. J Am Stat Assoc. 1976;71:791–9.

Ikuenobe P. Questioning as an epistemic process of critical thinking. Educ Philos Theory. 2001;33:325–41.

Download references

Author information

Authors and affiliations.

Predictive Society and Data Analytics Lab, Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland

Frank Emmert-Streib

You can also search for this author in PubMed Google Scholar

Contributions

FES conceived and drafted the manuscript.

Corresponding author

Correspondence to Frank Emmert-Streib .

Ethics declarations

Competing interests.

The author declares no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Cite this article.

Emmert-Streib, F. Importance of critical thinking to understand ChatGPT. Eur J Hum Genet 32 , 377–378 (2024). https://doi.org/10.1038/s41431-023-01443-4

Download citation

Received : 17 July 2023

Accepted : 19 July 2023

Published : 15 August 2023

Issue Date : April 2024

DOI : https://doi.org/10.1038/s41431-023-01443-4

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Quick links

Explore articles by subject
Guide to authors
Editorial policies

Importance of critical thinking to understand ChatGPT

Affiliation.

1 Predictive Society and Data Analytics Lab, Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland. [email protected].
PMID: 37582903
PMCID: PMC10999413 (available on 2025-04-01 )
DOI: 10.1038/s41431-023-01443-4

Publication types

IE Corporate Relations
IE University

ChatGPT and the Decline of Critical Thinking

The use of ChatGPT as a search engine has made the need for critical thinking more pressing than ever, writes Enrique Dans.

importance of critical thinking to understand chatgpt

OpenAI’s launch of ChatGPT in late November captured the world’s attention and opened our eyes to the existence of a technology capable of a surprising number of things called machine learning. Note the language here. It is not artificial intelligence because machines are not intelligent, they are simply programmed to consult databases and use statistics.

Advanced automation has for years been applied to all kinds of uses, but what ChatGPT has done is to apply one specific area of machine learning, Large Language Models (LLMs), to a conversational environment, and has dazzled the world in the process. As a result more and more people are using it—not so much for conversations, as it was initially designed, but as a search engine. This is a development that could challenge Google’s two decades of hegemony.

It’s worth pointing out that Google already has very similar technology, but has so far decided to keep it under wraps until it can be sure of its quality and reliability. An LLM answers questions based on affinities and statistical matches, and the only way to get “correct” answers is to filter them, i.e. exclude the unsuitable stuff. This is not easy, so some answers will be partially incorrect, and sometime they will be very off the mark, even if the language used seems that of an expert.

Google, of course, immediately realized the threat posed by ChatGPT. In response, the company brought its two founders out of retirement, and decided to incorporate similar technologies into around 20 of its products. Microsoft, now an investor in OpenAI, is about to do the same. (If you haven’t experienced the pleasure of creating Excel documents with an algorithm like ChatGPT, I highly recommend it).

So far, so good: we have innovation driving competition.

Yet, the problem here is what happens to critical thinking. A Google results page, with its links, shows us the source and may include a fragment of text, etc., before we finally click and land on the page to (hopefully) find what we were looking for. But, with ChatGPT and the like, we ask a question and receive a couple of paragraphs with the answer – and this answer may or may not be correct, though it certainly looks like it.

The steady erosion of critical thinking exposes us to reliance on a tool that can easily be used to manipulate us.

Such is the absence of critical thinking in the world today that many people take the first result on a Google page as gospel. I say this from experience. I have been called by several people convinced that I was the customer service manager of a Spanish airline simply because I once wrote, long ago, about Air Europa’s disastrous customer service and the article was indexed at the top of Google’s search engine. Just try convincing angry flyers that you are not the person to attend to their complaints! It didn’t matter what I told them: according to their reading of the search engine page, Google said I was the airline’s customer service, and so I must be lying.

So, if people will accept Google’s word uncritically, imagine the response to ChatGPT. The answer to your search may be 100% bullshit, but whatever: for many people, it’s hard, reliable truth.

There are tools like Perplexity.ai that try to alleviate this by providing sources – and this, at least, allows anyone who wants to fact check the answer to do so. I would think that Google, which has a great deal at stake here, will go in that direction and not simply provide a single piece of text but something more elaborate that would allow the user to check whether the answer is from a scientific article, a tabloid newspaper, or a sect of anti-vaxxers, climate change deniers, or conspiracy theorists. At the very least, search engines have a responsibility to make it possible for users to probe their answers with a few clicks. This is a necessity because the steady erosion of critical thinking exposes us to reliance on a tool that can easily be used to manipulate us.

Nevertheless, at the end of the day, we shouldn’t expect Big Tech to facilitate critical thinking: it’s something we must develop for ourselves, as individuals and collectively as a society. The problem is that our schools don’t teach it, preferring instead the comfort of a textbook, often banning smartphones in the classroom rather than embracing the challenge of teaching students how to use them properly.

That said, the education system cannot bear all the responsibility: parents also have an obligation to teach their children about how the world works. I’m afraid this means thinking twice about giving children a phone or tablet to keep them quiet.

After years of “this must be true because I saw it on television,” we now have “this must be true because the algorithm says so.” So, either we get a grip and start to prioritize critical thinking, or we’re going to end up in a collective muddle – and more vulnerable than ever to misinformation.

Retaining Talent in the Age of Resignation

Eu elections explainer: what are they and why do they matter, mending the globalist fracture, beyond the battlefield: human capital for ukraine, would you like to receive ie insights.

Charging into the Future with Electric Vehicles

Art, Cognac, and AI

Ai, academic integrity, and creative expression.

AI in Elections: The Battle for Truth and Democracy

Vision, Tech, and Learning. The Secret Sauce of AI-Powered Enterprises

Tech Transformation Is Human (Not Digital)

Chaos at OpenAI

Metacognition and Critical Thinking: Using ChatGPT-Generated Responses as Prompts for Critique in a Problem-Solving Workshop (SMARTCHEMPer)

Pharmacy and Pharmaceutical Sciences Education

Research output : Contribution to journal › Article › Research › peer-review

Successful problem solving is a complex process that requires content knowledge, process skills, developed critical thinking, metacognitive awareness, and deep conceptual reasoning. Teaching approaches to support students developing problem-solving skills include worked examples, metacognitive and instructional scaffolding, and variations of these techniques. In this report, we describe a classroom activity, which involves a combination of metacognitive scaffolding, problem-solving practice, and critiquing of ChatGPT-generated solutions. It was demonstrated that students engaged with the idea of metacognition as part of the problem-solving toolbox and showed appreciation for the collaborative nature of problem solving. They were also able to identify mistakes and flaws in the provided erroneous solutions, albeit to varying degrees. The results also revealed that incoming university students likely require scaffolding to develop sophisticated critical-thinking skills.

First-Year Undergraduate/General
Interdisciplinary/Multidisciplinary
Problem Solving/Decision Making
Solutions/Solvents

Access to Document

10.1021/acs.jchemed.3c00481

Importance of critical thinking to understand ChatGPT

Computing Sciences

Research output : Contribution to journal › Letter › Scientific

ASJC Scopus subject areas

Genetics(clinical)

Access to Document

10.1038/s41431-023-01443-4

This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.

https://urn.fi/URN:NBN:fi:tuni-2023122111172 Licence: Unspecified

T1 - Importance of critical thinking to understand ChatGPT

AU - Emmert-Streib, Frank

U2 - 10.1038/s41431-023-01443-4

DO - 10.1038/s41431-023-01443-4

M3 - Letter

AN - SCOPUS:85167878056

SN - 1018-4813

JO - European Journal of Human Genetics

JF - European Journal of Human Genetics

ChatGPT elevates the need for critical thinking skills

The rise of ai needs to also bring about a rise in critical thinking, says chris griffiths.

Artificial Intelligence
Future of HR
HR Communications
HR Insights
HR Technology
Human Resources
Strategic HR

The age of the internet could also be fairly accurately described as the age of information.

From Google to Wikipedia, we have an incredibly vast amount of data available at our fingertips. There’s no denying it: access to the web has changed the world in huge ways – but the incoming tide of AI may just change it beyond recognition.

Since the start of 2023 , we’ve seen increasing awareness (and wariness), of artificial intelligence.

And no AI tool has demanded attention quite like ChatGPT. This machine learning tool produced by the tech company Open AI, can be used to do everything from answering queries to writing code.

To date, four versions of ChatGPT have been released for public use – and doubtless there will be more to come.

Many workplaces have already begun to make the most of this tool in daily working life, and inevitably there will be an increasing number of similar technologies altering the modern workplace in the very near future.

But what does this really mean for humans in the workplace?

What is critical thinking?

Sure, AI will automate many rote and repetitive tasks. It will also help with data collation and analysis.

However it’s for this very reason that it’s so important HRDs refocus our attention on the uniquely human skills that both compliment AI usage, and separate us from it.

The most important of all these is arguably critical thinking .

But to understand why , we have to understand what critical thinking actually is.

Independent thinking

Critical thinking can be defined in a few different ways, but it’s essentially the ability to think clearly and independently about a subject or problem.

It often requires the consideration of multiple perspectives, the checking of biases, and a detailed understanding of relevant context.

Critical thinking is already a valued skill in society – especially when it comes to overcoming binary thinking and identifying the disinformation which is so often prevalent online today.

But with AI, it’s about to become even more crucial.

Expert critical thinkers are capable of cognitive dissonance .

This means, they can hold two conflicting ideas in their mind at one time – and they’ll likely understand the validity of each idea, too.

Critical thinking also involves emotional intelligence and empathy. That is both in understanding a subject fully, and how emotions might shape that understanding itself. Critical thinkers are able to make creative connections and spot patterns when considering a problem or concept.

Examples of critical thinking includes people being able to assess their own strengths and weaknesses, and recognizing the nuances which might characterize these different areas.

Critical thinking is also used when people make a judgement on whether or not to trust a piece of information – something which has become especially essential in the age of social media.

Why AI makes critical thinking essential

There’s no doubt that critical thinking has always been an invaluable skill – even if it’s not always been given the credit it deserves.

So why does the rise of AI make it even more important?

Well, the answer is two-fold.

Firstly, anyone who has worked with AI like ChatGPT will know its potential. It can write a convincing academic essay on almost any subject one can care to think of. It can theorize about deep philosophical concepts, and even explain complex quantum physics in simple terminology.

But while this may give the impression of independent thought, it is not actually capable of original ideas in the truest sense. Instead, it sifts and reorganizes existing human ideas in order to meet a specific request.

Think of it this way: AI might be able to provide you with incredibly helpful data; it might even be able to suggest actionable steps to improve human performance.

But it can’t understand the wider context and nuance which might feed into the bigger picture.

This is one of the key reasons critical thinking will be necessary for succeeding in an AI-powered future. Used in collaboration with human skills, AI can pave the way to new successes – but without the human element, there is no competitive advantage.

Another reason critical thinking is imperative when using AI relates to the infallibility of tools like ChatGPT themselves.

While we may associate mistakes with humans more than machines, there is ample evidence that AI sometimes replicates troubling human biases – and it is also capable of getting things wrong .

That’s why the humans working with AI must have strong critical thinking skills, in order to be able to question and assure the validity of information provided by AI, and to make sure its usage doesn’t inadvertently feed prejudiced viewpoints.

We foster critical thinking when we learn to question information, act strategically rather than reactively, and work in collaboration with others.

There is a lot of anxiety surrounding the rise of AI, but instead of focusing on what AI might take from us – we should try thinking about all the benefits it might bring when paired with crucial human skills like critical thinking.

Development and validation of ChatGPT literacy scale

Published: 14 February 2024

Cite this article

Seyoung Lee ORCID: orcid.org/0000-0001-8048-1796 1 &
Gain Park ORCID: orcid.org/0000-0002-3767-8320 2

581 Accesses

Explore all metrics

ChatGPT revolutionized the landscape of information transitions and creativity. The number of ChatGPT users is increasing at the fastest pace in consumer applications history, which calls for a reliable ChatGPT literacy scale. To that end, first, we conducted a literature review to gain a conceptual understanding of the ChatGPT literacy construct. Next, we conducted a focus group consisting of five experts to brainstorm potential items and the following five factors of ChatGPT literacy: technical proficiency, critical evaluation, communication proficiency, creative application, and ethical competence. The Delphi method with 10 experts was used to validate these items. After collecting expert feedback and evaluation data, we calculated content validity ratios to analyze the items’ content validity. Another focus group interview was conducted with 10 university students as a pilot test. Finally, 822 college students were recruited to evaluate the construct validity of ChatGPT literacy through exploratory and confirmatory factor analysis, resulting in 25 final items. This novel approach is expected to contribute to building a theoretical basis for ChatGPT and large language model studies, providing practical implications for large language model developers, helping to develop related regulations and policies, and creating a healthy digital culture for the use of ChatGPT.

This is a preview of subscription content, log in via an institution to check access.

Access this article

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Institutional subscriptions

Students’ voices on generative AI: perceptions, benefits, and challenges in higher education

Cecilia Ka Yuk Chan & Wenjie Hu

Artificial Intelligence (AI) Student Assistants in the Classroom: Designing Chatbots to Support Student Success

Yu Chen, Scott Jensen, … Terri Lee

AI-based chatbots in customer service and their effects on user compliance

Martin Adam, Michael Wessel & Alexander Benlian

Data availability

The data used to support the findings of this study are available from the corresponding author upon request.

Anastasi, A., & Urbina, S. (1997). Psychological testing . Prentice Hall/Pearson Education.

Google Scholar

Anderson, N., Belavy, D. L., Perle, S. M., Hendricks, S., Hespanhol, L., Verhagen, E., & Memon, A. R. (2023). AI did not write this manuscript, or did it? Can we trick the AI text detector into generated texts? The potential future of ChatGPT and AI in sports & Exercise Medicine manuscript generation. BMJ Open Sport & Exercise Medicine, 9 (1), e001568. https://doi.org/10.1136/bmjsem-2023-001568

Article Google Scholar

Bawden, D. (2008). Origins and concepts of digital literacy. In L. Colin, K. Michele, & M. Peters (Eds.), Digital literacies: Concepts, policies and practices (pp. 17–32). Peter Lang.

Biswas, S. S. (2023). Role of Chat GPT in public health. Annals of Biomedical Engineering, 51 , 868–869.

Article PubMed Google Scholar

Brown, T. A. (2006). Confirmatory factor analysis for applied research . Guilford.

Cascella, M., Montomoli, J., Bellini, V., & Bignami, E. (2023). Evaluating the feasibility of ChatGPT in healthcare: An analysis of multiple clinical and research scenarios. Journal of Medical Systems, 47 (1), 1–5. https://doi.org/10.1007/s10916-023-01925-4

Chan, A. (2022). GPT-3 and InstructGPT: Technological dystopianism, utopianism, and contextual perspectives in AI ethics and industry. AI and Ethics , 1–12. https://doi.org/10.1007/s43681-022-00148-6

Clay, I. (2023). Fact of the week: OpenAI’s ChatGPT user base has grown faster than TikTok’s or Instagram’s . Information Technology & Innovation Foundation. Retrieved February 9, 2024, from https://itif.org/publications/2023/02/13/openais-chatgpt-user-base-has-grown-faster-than-tiktoks-or-instagrams/

Cohen, J., Cohen, P., West, S. G., & Aiken, L. S. (2013). Applied multiple regression/correlation analysis for the behavioral sciences . Routledge.

Book Google Scholar

Cotton, D. R., Cotton, P. A., & Shipway, J. R. (2023). Chatting and cheating: Ensuring academic integrity in the era of ChatGPT. Innovations in Education and Teaching International, 1–12. https://doi.org/10.1080/14703297.2023.2190148

Crawford, J., Cowling, M., & Allen, K. A. (2023). Leadership is needed for ethical ChatGPT: Character, assessment, and learning using artificial intelligence (AI). Journal of University Teaching & Learning Practice , 20 (3). https://doi.org/10.53761/1.20.3.02

Dahmen, J., Kayaalp, M., Ollivier, M., Pareek, A., Hirschmann, M. T., Karlsson, J., & Winkler, P. W. (2023). Artificial intelligence bot ChatGPT in medical research: The potential game changer as a double-edged sword. Knee Surgery Sports Traumatology Arthroscopy, 31 , 1187–1189.

DeVellis, R. F. (2003). Scale development: Theory and applications (2nd ed.). Sage.

Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., & Wright, R. (2023). So what if ChatGPT wrote it? Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy. International Journal of Information Management, 71 , 102642. https://doi.org/10.1016/j.ijinfomgt.2023.102642

Eshet, Y. (2012). Thinking in the digital era: A revised model for digital literacy. Issues in Informing Science and Information Technology, 9 (2), 267–276.

Floridi, L., & Chiriatti, M. (2020). GPT-3: Its nature, scope, limits, and consequences. Minds and Machines, 30 , 681–694. https://doi.org/10.1007/s11023-020-09548-1

Fornell, C., & Larcker, D. F. (1981). Evaluating structural equation models with unobservable variables and measurement error. Journal of Marketing Research, 18 (1), 39–50. https://doi.org/10.2307/3151312

Fu, J. S. (2013). ICT in education: A critical literature review and its implications. International Journal of Education and Development Using Information and Communication Technology, 9 (1), 112–125.

Gilster, P. (1997). Digital literacy . Wiley.

Gordijn, B., & Have, H. T. (2023). ChatGPT: Evolution or revolution? Medicine Health Care and Philosophy , 1–2. https://doi.org/10.1007/s11019-023-10136-0

Grefen, P. (2021). Digital literacy and electronic business. Encyclopedia, 1 (3), 934–941.

Hachman, M. (2022). ChatGPT is the dazzling, scary future of AI chatbots . PCWorld. Retrieved February 9, 2024, from https://www.pcworld.com/article/1424575/chatgpt-is-the-future-of-ai-chatbots.html

Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2010). Multivariate data analysis (7th ed.). Prentice-Hall.

Henseler, J., Ringle, C. M., & Sarstedt, M. (2015). A new criterion for assessing discriminant validity in variance-based structural equation modeling. Journal of the Academy of Marketing Science, 43 , 115–135. https://doi.org/10.1007/s11747-014-0403-8

Homolak, J. (2023). Opportunities and risks of ChatGPT in medicine, science, and academic publishing: A modern Promethean dilemma. Croatian Medical Journal, 64 (1), 1–3. https://doi.org/10.3325/cmj.2023.64.1

Article PubMed PubMed Central Google Scholar

Huda, M., & Hashim, A. (2022). Towards professional and ethical balance: Insights into application strategy on media literacy education. Kybernetes, 51 (3), 1280–1300.

Hunter, I. (2018). Digital literacy in the workplace: A view from the legal sector. Business Information Review, 35 (2), 56–59.

Kline, R. B. (2005). Principles and practice of structural equation modeling (2nd ed.). The Guilford.

Koc, M., & Barut, E. (2016). Development and validation of New Media Literacy Scale (NMLS) for university students. Computers in Human Behavior, 63 , 834–843. https://doi.org/10.1016/j.chb.2016.06.035

Laupichler, M. C., Aster, A., & Raupach, T. (2023). Delphi study for the development and preliminary validation of an item set for the assessment of non-experts’ AI literacy. Computers and education. Artificial Intelligence, 4 , 100126. https://doi.org/10.1016/j.caeai.2023.100126

Lawshe, C. H. (1975). A quantitative approach to content validity. Personnel Psychology, 28 (4), 563–575.

Lee, S., Lee, E., Park, Y., & Park, G. (2023a). Legitimization of paltry favors effect and chatbot-moderated fundraising. Current Psychology , 1–13. https://doi.org/10.1007/s12144-023-05084-0

Lee, S., Park, G., & Chung, J. (2023b). Artificial emotions for charity collection: A serial mediation through perceived anthropomorphism and social presence. Telematics and Informatics , 102009. https://doi.org/10.1016/j.tele.2023.102009

Lee, S., & Park, G. (2023). Exploring the impact of ChatGPT literacy on user satisfaction: The mediating role of user motivations. Cyberpsychology Behavior and Social Networking, 26 (12), 913–918. https://doi.org/10.1089/cyber.2023.0312

Lee, S., Park, Y., & Park, G. (2024). Using AI chatbots in climate change mitigation: A moderated serial mediation model. Behaviour and Information Technology, 1–17 , 1. https://doi.org/10.1080/0144929X.2023.2298305

Lévy, P. (1997). Collective intelligence: Mankind’s emerging world in cyberspace . Perseus Books.

Lin, C. H., Yu, C. C., Shih, P. K., & Wu, L. Y. (2021). STEM-based artificial intelligence learning in general education for non-engineering undergraduate students. Educational Technology & Society, 24 (3), 224–237.

Lin, T. B., Li, J. Y., Deng, F., & Lee, L. (2013). Understanding new media literacy: An explorative theoretical framework. Journal of Educational Technology & Society, 16 (4), 160–170.

Munari, S. A. L. H., & Susanti, S. (2021). The effect of ease of transaction, Digital Literacy, and Financial Literacy on the Use of E-Banking. Economic Education Analysis Journal, 10 (2), 298–309.

Namkoong, M., Park, G., Park, Y., & Lee, S. (2023). Effect of Gratitude expression of AI Chatbot on willingness to Donate. International Journal of Human-Computer Interaction, 1–12 , 1. https://doi.org/10.1080/10447318.2023.2259719

Ng, D. T. K., Leung, J. K. L., Chu, S. K. W., & Qiao, M. S. (2021). Conceptualizing AI literacy: An exploratory review. Computers and Education: Artificial Intelligence, 2 , 100041. https://doi.org/10.1016/j.caeai.2021.100041

Okoli, C., & Pawlowski, S. D. (2004). The Delphi method as a research tool: An example, design considerations and applications. Information & Management, 42 (1), 15–29. https://doi.org/10.1016/j.im.2003.11.002

Park, G., Lee, S., & Chung, J. (2023a). Do anthropomorphic chatbots increase counseling satisfaction and reuse intention? The Moderated Mediation of Social Rapport and social anxiety. Cyberpsychology Behavior and Social Networking, 26 (5), 357–365. https://doi.org/10.1089/cyber.2022.0157

Article CAS PubMed Google Scholar

Park, G., Chung, J., & Lee, S. (2023b). Human vs. machine-like representation in chatbot mental health counseling: The serial mediation of psychological distance and trust on compliance intention. Current Psychology , 1–12. https://doi.org/10.1007/s12144-023-04653-7

Park, G., Yim, M. C., Chung, J., & Lee, S. (2023c). Effect of AI chatbot empathy and identity disclosure on willingness to donate: The mediation of humanness and social presence. Behaviour & Information Technology, 42 (12), 1998–2010. https://doi.org/10.1080/0144929X.2022.2105746

Park, G., Chung, J., & Lee, S. (2023d). Effect of AI chatbot emotional disclosure on user satisfaction and reuse intention for mental health counseling: A serial mediation model. Current Psychology, 42 (32), 28663–28673. https://doi.org/10.1007/s12144-022-03932-z

Podsakoff, P. M., MacKenzie, S. B., Lee, J. Y., & Podsakoff, N. P. (2003). Common method biases in behavioral research: A critical review of the literature and recommended remedies. Journal of Applied Psychology, 88 (5), 879–903. https://doi.org/10.1037/0021-9010.88.5.879

Raschke, C. A. (2003). The digital revolution and the coming of the postmodern university . Routledge.

Reddy, P., Sharma, B., & Chaudhary, K. (2020). Digital literacy: A review of literature. International Journal of Technoethics, 11 (2), 65–94.

Reed, B. (2023). ChatGPT reaches 100 million users two months after launch . The Guardian. Retrieved February 9, 2024, from https://www.theguardian.com/technology/2023/feb/02/chatgpt-100-million-users-open-ai-fastest-growing-app

Rosenblatt, K. (2023). ChatGPT banned from New York City public schools’ devices and networks. NBC News. Retrieved February 9, 2024, from https://www.nbcnews.com/tech/tech-news/new-york-city-public-schools-ban-chatgpt-devices-networks-rcna64446

Sarkar, S. (2012). The role of information and communication technology (ICT) in higher education for the 21st century. Science, 1 (1), 30–41.

Shih, P. K., Lin, C. H., Wu, L. Y., & Yu, C. C. (2021). Learning ethics in AI—teaching non-engineering undergraduates through situated learning. Sustainability, 13 (7), 3718. https://doi.org/10.3390/su13073718

Song, K. (2022). Korea is leading an exemplary AI transition: Here’s how . The OECD AI Policy Observatory. https://oecd.ai/en/wonk/korea-ai-transition

Wang, B., Rau, P. L. P., & Yuan, T. (2022). Measuring user competence in using artificial intelligence: Validity and reliability of artificial intelligence literacy scale. Behaviour & Information Technology , 1–14.

Weinstein, B. (2023). Why smart leaders use ChatGPT ethically and how they do it . Forbes. Retrieved February 9, 2024, from https://www.forbes.com/sites/bruceweinstein/2023/02/24/why-smart-leaders-use-chatgpt-ethically-and-how-they-do-it/?sh=1c118e63361b

Download references

This work was supported by the Ministry of Education of the Republic of Korea and the National Research Foundation of Korea (NRF-2021S1A5C2A02088387).

Author information

Authors and affiliations.

Department of Media and Communication, Sungkyunkwan University, 25-2, Sungkyunkwan- Ro, 50505 Hoam Hall, Jongno-Gu, Seoul, 03063, South Korea

Seyoung Lee

Department of Journalism and Media Studies, New Mexico State University, 2915 McFie Circle, Milton Hall 158, Las Cruces, NM, 88003, USA

You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gain Park .

Ethics declarations

Ethical approval.

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Conflict of interest

The authors declare no conflicts of interest concerning the research, authorship, or publication of this article.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Lee, S., Park, G. Development and validation of ChatGPT literacy scale. Curr Psychol (2024). https://doi.org/10.1007/s12144-024-05723-0

Download citation

Accepted : 31 January 2024

Published : 14 February 2024

DOI : https://doi.org/10.1007/s12144-024-05723-0

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Digital literacy
AI literacy
Scale development
Find a journal
Publish with us
Track your research

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Publications
Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

Advanced Search
Journal List
Eur J Investig Health Psychol Educ
PMC10670526

Drivers and Consequences of ChatGPT Use in Higher Education: Key Stakeholder Perspectives

Ahmed m. hasanein.

1 College of Business Administration, King Faisal University, Al-Ahsa P.O. Box 400, Saudi Arabia

2 Faculty of Tourism and Hotel Management, Helwan University, Cairo P.O. Box 12612, Egypt

Abu Elnasr E. Sobaih

Associated data.

The data from interviews could be shared with researchers who meet eligibility criteria after consent is given by the KFU Ethical Committee.

The incorporation of artificial intelligence (AI) into education has heralded a transformative era in the way students learn and faculties teach. Among the burgeoning array of AI tools, ChatGPT stands out as a versatile and powerful resource. Developed by OpenAI, ChatGPT is an AI-driven conversational model that generates human-like responses. This research draws on the Constructivism Learning Theory to uncover the key drivers pushing higher education students to use ChatGPT for academic purposes, and the multifaceted consequences it brings to the academic environment, by integrating the perspectives of key stakeholders: students, faculty, and education experts/leaders. The key findings of in-depth, face-to-face, interviews with key stakeholders revealed 12 main drivers that motivate students and their faculty to use ChatGPT mainly for learning purposes. However, the findings identified the multifaceted (six positive and another six negative) consequences of using ChatGPT for academic purposes. Recommendations for mitigating the negative consequences of ChatGPT were discussed with key stakeholders, particularly education experts/leaders, who were more concerned about using ChatGPT for academic reasons. The research reveals that higher education institutions should establish clear guidelines as a part of higher education policy, supplemented with training sessions for students and their faculty, about the responsible use of ChatGPT for academic purposes to mitigate any ethical concerns.

1. Introduction

Due to the fast-changing environment of higher education, technological advances are continually transforming education for both students and faculty members [ 1 , 2 ]. The emergence of generative artificial intelligence (GenAI) has been recognized as an innovative force, with chat-generative pre-trained transformer (ChatGPT) at the cutting edge of this technological revolution [ 2 , 3 ]. ChatGPT, which is driven by the combination of language processing and machine learning, is an innovative technology that has made its way into education institutions [ 3 ]. It is a massive language generator that develops human-like texts in response to a specific command [ 4 ]. It could handle a wide range of tasks related to natural language processing (e.g., conversations, translations, and completing texts) [ 5 ]. On one hand, several research studies [ 6 , 7 , 8 , 9 ] have highlighted the numerous advantages of using ChatGPT in learning, including improving accessibility by providing students and faculty with 24/7 information accessibility and assistance, promoting the learning experience by offering personalized support, and improving language skills by offering grammar suggestions and vocabulary enhancements. Additionally, it assists students in their preparation of assignments and exams, making research activities, and writing academic articles without being easily identified by plagiarism detection programs, which may raise ethical concerns [ 6 ].

On the other hand, there were other prominent key challenges concerning using ChatGPT in education. These challenges include reliability issues, the reliance on biased data [ 6 ], the limitation of knowledge to information available up to 2021 [ 7 ], relying on inaccurate or fabricated content, including fictitious citations [ 8 ], and over-reliance on ChatGPT might have negative impact students’ critical thinking and problem-solving abilities [ 9 ]. GhatGPT could represent a threat to academic ethics; the response of higher education institutions (HEIs) varies from those who have raced to enforce full constraints on the usage of ChatGPT [ 7 , 8 ] to those who have begun to support it by posting guidelines on how to deal with AI in an ethical and proper way [ 9 ]. Notwithstanding this, the majority of HEIs did not publish any information for their students concerning the use of ChatGPT for academic purposes, regarding whether it is permitted or not for academic purposes [ 10 , 11 ].

Growing research (see for instance [ 5 , 7 , 8 ]) has explored the perceptions of students and faculty concerning the use of ChatGPT for academic purposes in higher education. There is a limited, but growing, body of research [ 12 , 13 ] concerning the key benefits, opportunities and challenges of ChatGPT use in higher education. A review of earlier research has confirmed a lack of research studies that adopted a holistic outlook from the perspectives of key stakeholders regarding the use of ChatGPT for academic purposes. Earlier research examined either the perceptions of students or the perceptions of faculty. Nonetheless, there is a lack of studies that integrate and consolidate the perceptions of key stakeholders, which will be undertaken in the current study.

This research draws on the Constructivism Learning Theory by highlighting the perceptions and roles of active stakeholders (i.e., students, faculty, and education leaders). It explores emerging information and knowledge that ChatGPT could provide for academic purposes [ 4 , 10 ]. ChatGPT could enable users to build on knowledge and information to generate newer information and enhance their experience. Furthermore, ChatGPT’s tailored responses may enhance this process by capitalizing on previous learning and expertise, and offering tailored ideas for future education [ 14 , 15 ]. This response may assist stakeholders in acknowledging deficiencies, and push them into effective progress [ 16 ]. This research makes a new attempt to investigate the holistic perspectives of key stakeholders in higher education regarding the drivers and multifaceted consequences of ChatGPT use for academic reasons in higher education. The research explores the mitigation strategies for handling the negative consequences concerning ChatGPT use for academic purposes in higher education. Hence, the following research questions are suggested:

What are the drivers that motivate students and their faculty to use ChatGPT for academic purposes in higher education?
What are the positive and negative consequences raised by key stakeholders related to ChatGPT use for academic purposes in higher education?
What are the mitigation strategies for overcoming negative consequences and better using ChatGPT as an effective and supportive learning tool?

2. Literature Review

2.1. the use of chatgpt in higher education.

ChatGPT is considered an innovative, transformative and multifaceted AI that serves as an adaptable resource for both students and faculty in a dynamic learning environment [ 17 ]. Students benefit from ChatGPT’s ability to provide instant clarification on complex concepts, assistance with assignments, and access to a wealth of information, enhancing their academic journey [ 18 ]. It promotes self-directed learning, allowing students to explore subjects at their own pace and style. In terms of faculty, ChatGPT augments teaching by automating administrative tasks, offering personalized feedback, and providing insights into student needs through data analysis. It enables the faculty to focus on teaching strategies, and fosters innovation when designing curriculums [ 19 ]. ChatGPT emerges as a valuable tool that can enrich the learning experience, enhance efficiency, and prepare students for the challenges of a rapidly evolving knowledge-based educational environment [ 13 , 17 ]. However, ChatGPT raises concerns about academic integrity and the development of critical thinking skills. It is essential for educational institutions to strike a balance by providing guidance on responsible use, and emphasizing the importance of independent thought [ 20 ]. In addition, the integration of ChatGPT into higher education has the potential to reduce the reliance on faculty and, in turn, diminish opportunities for interpersonal connections and human interaction [ 7 ]. To aid students and enhance their writing skills, ChatGPT can perform tasks like identifying grammatical and structural issues in their work while also offering valuable feedback [ 9 ]. Moreover, students can receive personalized guidance tailored to their unique writing style, allowing them to pinpoint and focus on specific areas requiring improvement [ 8 ]. ChatGPT enables computers to simulate human conversations effectively, enabling accurate responses to user queries and personalization by understanding both user intent and context [ 6 ]. This opens up diverse possibilities for students, from delving into computer programming to crafting essays and tackling mathematical problems, all of which are achievable with the assistance of ChatGPT [ 8 , 9 ].

According to the constructivist perspective, education is an active process involving the construction of knowledge influenced by factors such as students’ needs, the learning materials at their disposal, the tools they use, and the overall learning environment [ 21 ]. Educators assume a pivotal part in this learning process by addressing students’ requirements, providing appropriate learning resources, and offering supportive tools [ 22 ]. In contrast to traditional teaching, which often entails the passive reception of knowledge from educators, the constructivist learning theory underscores the importance of autonomous and active learning [ 23 ]. A technology-enhanced constructivist learning environment has demonstrated great effectiveness, particularly concerning students’ access to information and their ability to analyze, interpret, and organize this information to expand their knowledge base. Subsequently, Rasul et al. [ 3 ] highlighted the applicability of constructivist theory in the context of information transmission. Aligned with the constructivist approach, the use of technology in the learning process empowers students to take charge of their skills and knowledge, allowing them to deal with gaps in their understanding [ 21 , 23 ]. Consequently, it is evident that ChatGPT, as an AI-powered instrument, offers the possibility to foster a constructivist learning experience. This enables them to experiment with ideas, pose inquiries, and obtain instant feedback, thereby facilitating the construction of their own comprehension and knowledge [ 3 ].

2.2. Drivers and Consequences of ChatGPT in Higher Education

ChatGPT has attracted substantial interest from educational institutions’ stakeholders worldwide as a revolutionary means of educating and supporting students [ 16 , 17 , 18 ]. Several educational institutions are investigating ways of integrating this artificial intelligence (AI) approach as part of their educational system, identifying its ability to revolutionize traditional pedagogical techniques, improve student interaction, as well as create specific learning environments [ 20 ]. On one hand, ChatGPT can be effectively utilized to improve education when its drawbacks are comprehended. In addition to providing responses to theory-based questions, ChatGPT can also generate ideas for research articles [ 4 , 15 ], albeit students should ensure that the generated responses are reliable before using them. ChatGPT, as an effective communicational tool (i.e., Chatbox), can also offer constructive comments on research articles and foster students’ critical thinking and argumentation [ 16 ]. In terms of students’ language skills, ChatGPT can also enhance equality in the educational process by leveling expectations for students from non-native English-speaking backgrounds [ 1 ]. Likewise, ChatGPT can be used to assist faculties in generating syllabus material for specific modules, developing materials and educational activities (i.e., supporting self-learning), implementing assessments and evaluations, and supporting the research writing process [ 24 ]. It might additionally be employed to improve thoughtful teaching techniques by testing existing evaluation techniques and verifying their content, structure, and abilities, along with GenAI, requiring the faculty to generate artificial intelligent proof assessments resulting in a genuine evaluation of students’ educational outcomes [ 17 , 25 ].

However, a recent study [ 26 ] found that accuracy and reliability are considered the most common obstacles faced when using ChatGPT in education. Challenges affiliated with reliability involve depending on biased information (i.e., restricted range of data used) [ 27 , 28 ], the lack of updated information (i.e., updated information stopped in 2021) [ 29 ] and providing inaccurate/fake data (i.e., presenting fabricated references) [ 30 ]. Moreover, the over-reliance on ChatGPT may have a negative effect on students’ ability to think critically and solve problems [ 31 , 32 ]. Concerning plagiarism, data show that articles written using ChatGPT may avoid detection by traditional plagiarism-checking systems [ 11 , 33 ]. Moreover, a recent study [ 34 ] found that laws and regulations regarding copyright and intellectual property rights still apply when using AI-generated content (e.g., ChatGPT). The misuse of information generated by ChatGPT may result negatively in copyright violations [ 27 , 35 ].

3.1. Methods Adopted

This research undertook a qualitative methodology in answering the research questions and fulfilling the research objectives. The qualitative methodology was found to be more suitable than quantitative approach for giving a better insight and gaining in-depth information about the drivers and consequences of ChatGPT use for academic purposes in higher education [ 36 ]. This research used the consolidated criteria for reporting qualitative studies (QCREQ) [ 37 ]. Qualitative research often focuses on the meanings, experiences and perceptions reported in interviews [ 36 , 37 ]; hence, it does not aim to collect quantitative data or report statistical information. All the guidelines suggested in the QCREQ were followed while undertaking the research, processing the data and reporting the findings. With regard to the data collection methods, the research adopted in-depth, face-to-face interviews [ 38 ]. We sought to find answers to the research questions about the perceptions of educational stakeholders (i.e., students, faculty, and education leaders) regarding ChatGPT use in higher education, especially its drivers and various consequences. Four core themes were discussed with the three key stakeholders:

Perceptions of ChatGPT use for academic purposes in higher educations;
Drivers of ChatGPT use by students and academics for academic purposes in higher education;
Consequences, whether positive or negative, of ChatGPT use by students and academics for academic purposes in higher education;
Strategies for mitigating the negative consequences of ChatGPT use by students and academics for academic purposes in higher education.

Interviews were conducted with students at public universities in Saudi Arabia. Participants were asked to participate in this study voluntarily, and were informed of the study’s purposes. Data collection in this study began at the beginning of the academic year 2023–2024, i.e., in August 2023, and lasted for one month. The participating interviewees had varied educational experiences, facilitating the gathering of meaningful responses and allowing us to investigate the holistic perspectives concerning the drivers and consequences of using ChatGPT in higher education. All interviews were performed one-to-one, and each interview lasted between half an hour and hour, with an average length of forty-five minutes. Both researchers were present during the interviews. The research supervisor took the responsibility of leading the interviews because he has sufficient experience in undertaking qualitative studies. All the interviews were conducted at the most convenient time reported by the interviewees, with the presence of two researchers.

It is also important to note that the current study followed the ethical guidelines throughout. It was approved by the committee in charge at the institution before undertaking the study. Furthermore, the participants’ identities were protected and there was no personal information collected. The purpose of the research was discussed with them before data collection and they were given the opportunity to withdraw from the study at any stage; however, none of the participants withdrew at any stage of the study. Additionally, codes were used when quoting the information given by the participants.

3.2. Participants

Participants were selected purposively through the network of researchers working at public universities in KSA. With regard to the type and number of participants, since the research team were on the Business Administration Major course, they were able to connect with students, academics and leaders in the Management, Accounting, Finance, Economics and Quantitative Methods departments. Interviews were done first with 85 students until data saturation was achieved [ 39 ]. There were more male participants (82%) than female (18%), due to the limited accessibility of female students to KSA. These were followed by 32 interviews with faculty members, followed by interviews with 21 education leaders and experts. There was almost equal participation of male and female academics, but we saw the limited participation of female leaders. These leaders were the deans of colleges, vice deans, heads of department and experts in quality assurance. The number of selected respondents was enough to attain saturation of data [ 39 ]. All of the participants were recorded after they gave approval. The participants were all notified at the start of the interviews that their information was to be used for the study only. The recorded interviews were transcribed after the interviews in Arabic and/or English depending on the language of the participants. However, the languages of the scripts were reviewed by two bilingual (Arabic/English) professionals to ensure the accuracy of the collected data.

3.3. Analysis of the Collected Data

A content and thematic analysis technique has been adopted to analyze the data collected from the interviews. Thematic analysis is considered one of the most effective and widespread approaches to analyzing qualitative research data [ 36 ]. The collected data were analyzed under four themes:

Stakeholders’ perceptions of ChatGPT use for academic purposes in higher education;
Key drivers of ChatGPT use by students and academics for academic purposes in higher education;
Consequences of ChatGPT use by students and academics for academic purposes in higher education;
Recommendations for overcoming negative consequences of ChatGPT use in higher education.

The data obtained from the in-depth interviews were evaluated manually using thematic analysis. The findings from all interviews have been integrated together, rather than presenting results from each group of participants, to avoid repeating specific points as well as to provide more clarity regarding the collected data. The following sub-sections present the key findings of the study.

4.1. Stakeholders’ Perceptions of Using ChatGPT for Academic Proposes in Higher Education

The participants were asked about their perceptions of ChatGPT use for academic purposes in higher education. The key stakeholders’ perceptions about ChatGPT use for academic purposes vary widely depending on various factors, including the context in which it is used, the specific tasks it is employed for, and individual preferences and experiences. In terms of students’ perceptions, the majority of students have a positive view of ChatGPT use for academic purposes in their higher education. Among their comments:

“ChatGPT is a magical tool. It helps us in our daily educational activities, e.g., assignments, research work, and homework”. (ST-3)

“I believe ChatGPT is a powerful tool that assist on various tasks through a series of queries and responses”. (ST-7)

“I would consider ChatGPT as an excellent search engine. We can use it for many purposes... The answer generates similar human-like responses”. (ST-11)

Faculty responses towards using ChatGPT for academic purposes in higher education were multifaceted. Faculty members reported both positive and negative perceptions about using ChatGPT for teaching and learning. The positive perceptions were related to the beneficial aspects of ChatGPT in searching for information, and assisting in academic content creation and designing the syllabus. The negative perceptions regarded the overreliance on ChatGPT in every single detail in education without human thinking, as demonstrated in the following quotes:

“In one hand, it is a useful tool in collecting information. It is also useful in data presentation. On the other hand, the over-reliance on ChatGPT is one of the critical negative aspects, because it reduces critical thinking”. (FC-2)

“It has a pros and cons. It is an assistive tool for academics that facilitates them in the educational process. Otherwise, it is not an official or authorized tool by our institutions, and students often misuse it”. (FC-5)

With regard to education experts and leaders, the majority of them were more likely to have negative perceptions rather than positive. They mentioned that the use of AI in education should add value to the education. The use of AI, including ChatGPT, should add to the learning outcomes, including knowledge and skills. Hence, the use of ChatGPT for academic purposes must be regulated. The educational institutions have to set guidelines for students about its use in a proper way. Examples of these responses could be seen in the following quotes:

“This tool does not contribute to several skills such as critical-thinking and problem-solving. However, these skills are critical for students’ career”. (EDLE-1)

“This tool will change students’ attitude negatively through turning on cheating information, lessons and answers without any control from their faculty or institutions”. (EDLE-4)

To sum up, the perceptions of all respondents regarding the use of ChatGPT varied according to the perspective of each group of interviewees. Students only see the positive aspects of using ChatGPT in their education, while the faculty mentioned that the ChatGPT tool has both positive and negative aspects. With regard to education leaders, they highlighted mainly the negative aspects of using ChatGPT in higher education.

4.1.1. Key Drivers of Using ChatGPT for Academic Purposes in Higher Education

Key stakeholders were asked about the main motives that push them to use ChatGPT as an educational tool or for academic purposes. A summary of the drivers highlighted by the interviewees is shown in Table 1 . All interviewees agreed that the quick response and ease of use ChatGPT are considered the most substantial drivers of utilizing it in education. This is a hallmark of its efficiency in education, manifested through its ability to provide immediate answers and support. It also optimizes tasks and raises efficiency. These quick responses have been proven especially valuable in educational environments, where students receive immediate explanations and resources, and faculty as well as education leaders may conserve their time by streamlining their daily tasks. Furthermore, ChatGPT has the ability to offer a smooth, simple, friendly and understandable interface for students and faculty to input queries, receive responses, and navigate its functionalities. These features not only boost stakeholders’ performance, but also fosters a smooth and simple user experience, making ChatGPT a vital tool in today’s digital age.

Key drivers of ChatGPT use for academic purposes in higher education.

* Codes of participants who commented on this point (ST = students; FC = faculty; EDLE = education leaders/experts).

All interviewees agreed that the quick response and ease of use ChatGPT are the most substantial drivers of utilizing it in education. This is a hallmark of its efficiency in education, facilitating its ability to provide immediate answers and support. It also optimizes tasks and raises efficiency. These quick responses have been proven especially valuable in educational environments, whereby students receive immediate explanations and resources, and faculty as well as education leaders may conserve their time by streamlining their daily tasks. Furthermore, ChatGPT has the ability to offer a smooth, simple, friendly and understandable interface for students and faculty to input queries, receive responses, and navigate its functionalities. These features not only boost stakeholders’ performance, but also foster a smooth and simple user experience, making ChatGPT a vital tool in today’s digital age.

Another driver of using ChatGPT in education has been raised by students and faculty in relation to classroom and homework assistance. Students commented that ChatGPT is a useful tool that can assist them in doing their homework, assignments, and projects. They can ask questions, seek explanations, and get guidance on how to approach their academic tasks. Moreover, faculty noted that ChatGPT could facilitate lecture preparation, the presentation of case studies about specific topics within the lecture, as well as helping them in teaching through giving clear and simple explanations and examples about specific topics, which make them understandable for students.

Language proofreading and editing is considered one of the key drivers that has been cited by both students and faculty for using ChatGPT in education. Students commented that ChatGPT can help them improve their language skills by providing accurate reviews and improving the clarity, coherence, and correctness of their work, helping them convey their ideas effectively. This not only elevates the quality of their submissions, but also fosters and improves their writing skills. Furthermore, faculty explained that ChatGPT can benefit them significantly through language proofreading and editing services when preparing research papers, grant proposals, and scholarly publications. This driver may ensures that their academic work meets the highest standards, enhancing the likelihood of acceptance by prestigious journals and funding agencies.

Regarding problem-solving and data analysis, as some of the key drivers pushing students to use ChatGPT in education, all students explained that ChatGPT can be used as a problem-solving tool that conveys a transformative approach to education. This versatile AI-powered assistant provides immediate clarification of complicated or confusing concepts, and tackles challenging math problems in their coursework. Moreover, ChatGPT can perform various data analysis tasks, such as summarizing large volumes of text, identifying trends or recurring themes in conversations, categorizing information, solving math problems, and providing statistical or quantitative assessments of the data it processes. It empowers students to learn at their own pace and fosters independence by offering step-by-step solutions and explanations.

Another pivotal driver of using ChatGPT in education has been discussed by students and faculty in the context of test preparation. Students noted that the pressure of standardized tests and examinations can be overwhelming. ChatGPT steps in as an invaluable resource, offering targeted assistance in reviewing material, practicing problem-solving, and honing test-taking strategies. It provides students with the flexibility to access test preparation materials at any time, ensuring optimal readiness and boosting confidence. Moreover, faculty highlighted that ChatGPT is considered an instrumental tool in optimizing test preparation processes. They can use it to create practice questions, quizzes, and mock tests that align with the curriculum. Additionally, ChatGPT’s data-driven insights can help the faculty identify areas wherein students may need additional support or tailored test preparation resources, enabling educators to fine-tune their teaching strategies.

Research support is considered as a crucial driver for using ChatGPT in education; it can serve as a guiding light, assisting them in formulating research questions, suggesting relevant sources, summarizing articles, and even generating preliminary research proposals. It empowers students and faculty with the tools needed to conduct more efficient and effective research, thereby elevating the quality of their academic work. Concept clarification related to the journey of understanding complex concepts can often be filled with confusion and uncertainty. ChatGPT can offer for students instant clarification and explanations on specific topics, and serves as a virtual tutor that can break down abstract ideas, provide real-world examples, and address specific queries, thus fostering enhanced comprehension and learning. Furthermore, ChatGPT may assist the faculty in explaining challenging concepts more effectively, ensuring that their teaching resonates with students, allowing them to stay up-to-date with the latest research and pedagogical techniques.

Concerning supplementary learning resources and adaptive learning, all students and faculty explained that ChatGPT can provide an extensive array of supplementary materials, including explanations, examples, practice questions, and recommended readings. These resources bolster traditional educational content, offering additional support for comprehension and skill development. Additionally, ChatGPT’s adaptive capabilities allow it to tailor responses and recommendations to each student’s unique needs and progress. By analyzing individual interactions, it can provide personalized guidance, adapt the difficulty level of questions, and offer targeted support in areas where a student may be struggling.

Another driver explained by the faculty is that ChatGPT can assist the faculty in assessing students’ level of competence, identifying areas of strength or weakness, and providing feedback or recommendations for improvement regarding their educational activities (e.g., quizzes, assignments, exams, discussions). Furthermore, ChatGPT can offer students scores or feedback, and may adapt subsequent interactions based on the assessment results.

4.1.2. Consequences of Using ChatGPT for Academic Purposes in Higher Education

The incorporation of ChatGPT in education has brought both positive and negative consequences, shaping the learning approach of students. A summary of the key positive consequences is presented in Table 2 . Concerning positive consequences, both students and faculty commented that ChatGPT is a remarkable timesaving tool. It provides immediate response, and they no longer need to spend excessive hours searching for answers or tackling complex concepts. Another two positive consequences explained by students concerned reducing anxiety and improving language skills. Students commented that assignments and homework make them feel anxious. ChatGPT steps in as a non-judgmental and readily available resource that allows students to practice and refine their language skills in a stress-free environment. It lowers the anxiety associated with language-related challenges and boosting students’ confidence in their ability to articulate their thoughts effectively. ChatGPT also serves as an indispensable tool for language learners. Its capacity to offer grammar suggestions, vocabulary enhancements, and coherent sentence structures aids students in honing their writing and communication skills.

Positive consequences of ChatGPT use for academic purposes in education.

Another positive aspect that has been explained by students and faculty is self-confidence. ChatGPT plays a key role in boosting self-confidence among students. When students receive prompt and accurate responses to their queries and challenges, they develop a sense of competence and mastery over the subject matter. Furthermore, ChatGPT’s support can help students tackle complex problems and assignments, making them feel more capable and confident in handling academic tasks. Regarding on-time submission, all faculty stated that ChatGPT can significantly improve time management skills, as students can allocate more time to researching, writing, and revising their work. With ChatGPT’s support, students are better equipped to meet deadlines without the stress of last-minute rushes, ultimately leading to a higher rate of on-time submissions. Moreover, the time saved by using ChatGPT for tasks like research and content generation allows students to focus on other aspects of their education, contributing to a more balanced and manageable workload. Another pivotal positive consequence pertains to the assistance and information provided by ChatGPT’s AI system to students for tasks and inquiries that are unrelated to their academic coursework or learning objectives, such as enrollment, course registration, scheduling, campus resources, financial aid, student services, and other logistical or procedural queries that students may have during their educational journey. ChatGPT can offer prompt and helpful responses to such administrative inquiries, simplifying students’ access to information and resources outside the realm of academia.

However, the rapid adoption of ChatGPT also presents negative consequences, which have been raised by education leaders/experts and faculty members (see Table 3 ). The two most prominent concerns related to using ChatGPT in education are the overreliance on AI in education, and academic integrity. While ChatGPT serves as an invaluable tool for learning, overreliance can potentially hinder the development of essential critical thinking and problem-solving skills. Students may become overly dependent on ChatGPT for answers, sacrificing their own exploration and analysis. With regard to academic integrity, ChatGPT can be misused by students for unethical purposes, such as plagiarism or cheating. When students rely on ChatGPT to generate assignments or answers without proper consideration of originality, it compromises the fundamental principles of academic honesty. This lack of integrity not only erodes the credibility of their educational achievements, but also diminishes the value of learning itself. Students may use ChatGPT to generate content that is not their own and present it as original work. Despite ChatGPT’s remarkable capabilities, it is not immune to challenges related to the lack of quality and accuracy in its responses. Like any AI system, ChatGPT relies on the data it was trained on, and these data can contain inaccuracies, biases, and inconsistencies. As a result, there are instances where ChatGPT may generate incorrect or misleading information, which can be problematic, especially in education or learning contexts. Additionally, the quality of ChatGPT’s responses can vary depending on the specificity and complexity of the query.

Negative consequences of ChatGPT use for academic purposes in education.

Concerning learning outcomes, ChatGPT can have a negative influence on students’ social interaction in education when it becomes a primary source of learning and assistance. Relying on ChatGPT for educational support can reduce opportunities for face-to-face interactions between students and faculty. It may also discourage peer collaboration and limit the development of essential communication skills. In extreme cases, it could lead to a sense of social isolation, as students miss interpersonal communication resulting from traditional classroom interactions, which could negatively affect their learning experience. There were two more negative consequences cited by faculty and educational leaders: potential bias and student skill set. Potential bias represents a significant negative effect of using ChatGPT in education. All faculty and education leaders commented that ChatGPT’s responses are generated based on vast datasets, and if these datasets contain biases, they can be inadvertently perpetuated in ChatGPT’s interactions with students. This bias can manifest in various forms, including gender bias, racial bias, or cultural bias, and it can lead to unfair or discriminatory responses, reinforcing stereotypes or prejudices. This not only hinders the AI’s ability to provide equitable assistance, but also raises ethical concerns in educational settings.

Another pivotal negative consequence has been explained by students, faculty and educational leaders. The over-dependence on ChatGPT in education can have detrimental effects on students’ skill sets. While ChatGPT offers quick solutions and readily available information, it can inadvertently hinder the development of critical skills essential for lifelong learning. The excessive use of this AI tool can discourage independent thinking, problem-solving, and research skills, as students may prioritize convenience over intellectual engagement. Furthermore, ChatGPT’s assistance with writing and communication tasks may diminish students’ abilities to express themselves effectively, as they may become excessively dependent on AI-generated content.

4.1.3. Recommendations for Mitigating the Negative Consequences of ChatGPT Use in Higher Education

There are several recommendations offered by faculty and education leaders in order to overcome the negative consequences of the misuse of ChatGPT for educational purposes. A summary of the key strategies or recommendations in terms of mitigating the negative consequences of ChatGPT use in education is presented in Table 4 .

Recommendations for overcoming negative consequences of ChatGPT use for academic purposes in education.

Codes of participants who commented on this point (ST = students; FC = faculty; EDLE = education leaders/experts).

In terms of students’ overreliance on ChatGPT, faculty should establish and promote clear guidelines on the responsible use of ChatGPT. These guidelines can include defining the boundaries of AI assistance and learning in relation to the potential pitfalls of overreliance. They have to emphasize the importance of critical thinking and problem-solving skills as fundamental aspects of education. Encouraging students to question, analyze, and synthesize information independently fosters self-reliance and reduces dependency on AI tools like ChatGPT. Regarding academic integrity concerns such as intellectual property rights, cheating and plagiarism, students should receive training on responsible use and ethical guidelines, and only use AI for getting ideas and information, and in trying to illustrate them using their own writing skills. Moreover, educational institutions can invest in plagiarism detection tools that can identify AI-generated content and distinguish it from original work. Such tools can help maintain the integrity of academic assessments and uphold intellectual property rights. In order to combat students cheating using ChatGPT, proactive measures are essential. Students must understand the importance of academic honesty and avoid using ChatGPT to gain an unfair advantage. The faculty play a pivotal role in addressing this issue by designing assessments that are less accommodating of AI-generated content. They should focus on assignments that require critical thinking, problem-solving, and creative expression, tasks that go beyond the capabilities of AI and cannot be easily outsourced. Concerning the lack of quality and accuracy in ChatGPT, AI developers and organizations should continuously refine and improve the underlying AI models through rigorous testing and validation processes. This includes fine-tuning the training data to minimize biases and inaccuracies, and implementing mechanisms for regular updates to reflect evolving knowledge. Furthermore, the faculty should encourage students to cross-reference AI-generated information with trusted academic sources, foster a habit of discernment, and reinforce the importance of accuracy. Concerning learning outcomes, both educational institutions and faculty should encourage students to attend lectures and participate in class discussions to ensure they are comprehensively absorbing the subject matter. They should set specific learning goals and objectives for each study session, focusing on what they aim to achieve. Additionally, students should regularly reflect on their progress and seek feedback from faculty to identify areas that require improvement.

In terms of the potential bias that results from using ChatGPT in education, students should take proactive steps, starting with diversifying their information sources and cross-verifying the information provided by ChatGPT from multiple reputable sources. They should be mindful of the possibility of bias and critically evaluate the content they receive, particularly in the context of sensitive or controversial topics. Regarding students’ skill set, students should approach ChatGPT as a valuable support tool rather than a crutch. It is essential to strike a balance between using AI assistance and honing essential skills. Independent research, critical thinking, and problem-solving exercises are important to graduates from higher education. Collaboration with peers and interactions with faculty remain crucial for skill development. They should seek feedback on their work, participate in class discussions, and ask questions to foster intellectual growth.

5. Discussion and Implications

ChatGPT has attracted the attention of key stakeholders in higher education institutions worldwide, due to its groundbreaking potential applicability in the realms of education, learning, and student support [ 18 ]. The current research confirms that stakeholders’ perceptions about using ChatGPT for academic purposes in higher education vary. Students tend to concentrate on the potential benefits of integrating ChatGPT into their educational activities, which supports the findings of previous research [ 3 , 9 ], whereas the faculty acknowledge both benefits and concerns related to using ChatGPT as an educational tool [ 3 , 8 , 9 ]. On the other hand, education experts/leaders were more cautious, and predominantly emphasized the key concerns and negative consequences of utilizing ChatGPT for academic purposes in education.

The current research has outlined twelve key drivers of using ChatGPT in educational contexts. Consistent with several other studies, there are nine key drivers or benefits, which are quick response [ 4 ], ease of use [ 5 ], classroom and homework assistance [ 10 ], problem solving [ 3 ], data analysis [ 3 , 4 ], concept clarification [ 12 ], adaptive learning [ 3 , 5 ], assessment activities [ 15 ], and supplementary learning resource [ 4 ]. Furthermore, this research added other three drivers, mainly concerned with students and faculty, which are language proof-reading and editing, test preparation and research support. Ease of use and quick response are considered the most common drivers that have been cited by stakeholders, helping to enhance task optimization and efficiency within educational settings. Other common drivers pushing students to use ChatGPT in education are adaptive leaning, problem-solving and data analysis. ChatGPT allows adaptive learning through tailoring responses and suggestions according to the specific requirements and progress of each student. Through the analysis of individual interactions, it can offer personalized guidance, adjust the complexity of questions, and provide focused assistance in areas where a student may encounter difficulties. This aligns with the constructivist approach, as ChatGPT builds upon existing information by tailoring the necessary knowledge and resources [ 15 ]. This enhancement of learning is facilitated by capitalizing on prior knowledge to establish new associations and meanings that ultimately contribute to the acquisition of new knowledge. Concerning problem-solving and data analysis, ChatGPT can serve as a tool for data analysis and problem-solving, offering a transformative approach to education. Drawing upon the Constructivist Learning Theory, one crucial principle emphasizes that learners actively engage in the process of knowledge creation by exploring and uncovering the fundamental principles that form the basis of the concepts they are studying. Aligning with this approach, students would be encouraged to participate in observations, analyze data, and collaborate in solving problems within their learning process.

This research has confirmed that there are both positive and negative consequences attached to the use of ChatGPT in education, as explained by stakeholders. There are six positive and six negative consequences of using ChatGPT in education. The positive consequences include the greater saving of time [ 4 ], reduced anxiety [ 8 ], improved language skills [ 3 ], self-confidence [ 15 ], punctual submissions and non-academic support [ 3 ]. One of the most crucial positive consequences cited by students is non-academic support. The constructivist theory of learning underscores the significance of active learning, whereby learners engage actively in the learning process rather than passively receiving information. Another two positive consequences also highlighted by students related to reducing anxiety and improving their language skills. Students revealed that homework activities make them feel anxious. ChatGPT serves as a non-judgmental and easily accessible tool, affording students the opportunity to practice and enhance their language skills within a comfortable educational environment. It lowers the anxiety associated with language-related challenges, boosting students’ confidence in their ability to articulate their thoughts effectively.

However, the negative aspects cited by faculty and education leaders include overreliance, compromised academic integrity [ 11 ], lack of quality and accuracy [ 8 ], compromised learning outcomes [ 8 ], potential bias [ 3 , 4 ] and student skill set depletion [ 3 ]. The utilization of ChatGPT in education raises two primary concerns: an overreliance on AI in the educational process, and issues related to academic integrity. While ChatGPT has been proven to be an invaluable learning tool, an overreliance on it may potentially impede the development of critical thinking and problem-solving skills that are crucial for students. There is a risk that students might excessively rely on ChatGPT for answers, diminishing their own capacity for exploration and analysis. In terms of academic integrity, concerns arise due to the potential misuse of ChatGPT by students for unethical purposes, such as plagiarism of intellectual property or cheating. When students utilize ChatGPT to generate assignments or responses without proper attribution or originality, it undermines the fundamental principles of academic honesty and equitable evaluation. Another negative consequence cited by both faculty and education leaders concerns learning outcomes. The dependence on ChatGPT as a primary source of learning and assistance can potentially have adverse effects on students’ social interactions within the educational context. This dependence may lead to diminished opportunities for in-person interactions between students and faculty. Furthermore, it may discourage collaborative efforts among peers and curtail the cultivation of vital communication skills.

The above results have some practical and theoretical implications. With regard to practical implications, the current research has shown that the use of ChatGPT for learning purposes should be the focus of more attention from key stakeholders. It could be used with caution, to avoid the realization of its negative consequences. The current research provides a set of recommendations to mitigate these negative consequences related to ChatGPT usage in higher education. Higher education institutions should establish and promote clear guidelines on the responsible use of ChatGPT. They should provide students with training on responsible use and ethical guidelines. Students should understand that they could use AI for developing ideas, deriving information, and developing their own writing skills. Moreover, educational institutions should invest in plagiarism detection tools that can identify AI-generated content and distinguish it from original work. Faculty should encourage students to cross-reference AI-generated information with trusted academic sources, so as to foster a habit of discernment and reinforce the importance of accuracy. Students should take proactive steps, starting with diversifying their information sources and cross-verifying the information provided by ChatGPT with multiple reputable sources. Furthermore, they should strike a balance between using AI assistance and developing their skills. Additionally, collaborations with their peers and interactions with faculty remain crucial for skill development. Also, students should seek feedback on their work, participate in class discussions, and ask questions to foster intellectual growth. Scholars, on other hand, should neither support nor reject the use of ChatGPT for learning or other academic purposes without understanding both the positive and the negative consequences. The long-lasting consequences in relation to students’ learning outcomes, as well as ethical considerations and the sustainability of higher education institutions, have to be considered when examining the integration of any AI tool used for learning in higher education. The perspectives of various stakeholders must be considered in order to develop a better understating of this issue.

6. Conclusions

ChatGPT is a transformative and multifaceted AI tool that serves as an adaptable resource for both students and faculty in dynamic learning environments. The current research has shown that there are twelve key drivers motivating students towards using it in their learning. These key drivers are quick response, ease of use, classroom and homework assistance, problem solving, data analysis, concept clarification, adaptive learning, assessment activity and supplementary learning resource provision, language proof-reading and editing, test preparation and research support. The research has also shown that there are both positive and negative consequences attached to the use of ChatGPT in education, as explained by stakeholders—six positive and six negative. The positive consequences include time saving, reduced anxiety, improving language skills, self-confidence, punctual submission and non-academic support. However, the negative areas of concern, which are mainly cited by faculty and education experts/leaders, include overreliance, the loss of academic integrity, lack of quality and accuracy, damaged learning outcomes, potential bias and deteriorated student skill sets. The research thus provides some recommendations for overcoming the negative consequences. The key strategy involves higher education institutions establishing a clear policy and guidelines regarding the use of ChatGPT for academic purposes in higher education. ChatGPT could be used as a supporting tool to enhance students’ learning and their understanding of specific topics and concepts.

This research used a qualitative approach with a sample of students, faculty and education experts/leaders in public KSA universities. Therefore, the results could not be generalized to other contexts without further testing. Future research avenues could include quantitatively testing the key drivers or factors that shape students’ usage of ChatGPT for learning and other related academic purposes in higher education. In addition, using ChatGPT has long-term consequences, both positive and negative. However, students misusing this tool could have an impact on the educational process, which should also be addressed in future research. One future research avenue could be a comparison between male and female students in terms of their use of AI, and its relationship with their academic performance. Moreover, future studies could examine the factors from the faculty’s perspective. Other theoretical framework, such as TAM or TPB, could be adopted for interpreting the key drivers of academic-related use in higher education.

Funding Statement

This research was funded by the Deanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia, grant number GRANT4379.

Author Contributions

Conceptualization, A.M.H. and A.E.E.S.; methodology, A.M.H. and A.E.E.S.; validation, A.M.H. and A.E.E.S.; formal analysis, A.M.H. and A.E.E.S.; investigation, A.M.H. and A.E.E.S.; resources, A.M.H. and A.E.E.S.; data curation, A.M.H. and A.E.E.S.; writing—original draft preparation, A.M.H. and A.E.E.S.; writing—review and editing, A.M.H. and A.E.E.S.; visualization, A.M.H. and A.E.E.S.; supervision, A.M.H.; project administration, A.E.E.S.; funding acquisition, A.M.H. and A.E.E.S. All authors have read and agreed to the published version of the manuscript.

Institutional Review Board Statement

The study was conducted according to the guidelines of the Declaration of Helsinki and approved by the Deanship of Scientific Research Ethical Committee, King Faisal University (project number: GRANT4379, date of approval: 1 June 2023).

Informed Consent Statement

Informed consent was obtained from all subjects involved in the study.

Data Availability Statement

Conflicts of interest.

The authors declare no conflict of interest.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

The Importance of Critical Thinking when Using ChatGPT (and Other Large Language Models)

Written by Argumentful

Artificial intelligence has made tremendous strides in recent years, allowing for the creation of conversational AI models that can engage in human-like dialogue. One of the most well-known examples is OpenAI’s language model, ChatGPT . This system can perform a wide range of tasks, from answering trivia questions to generating written content. However, it’s important to remember that ChatGPT is not a human and its responses should not be taken as gospel truth. In order to make the most of this technology, users must engage in critical thinking and exercise caution when using it.

One of the most compelling aspects of ChatGPT is its ability to generate text that appears to be written by a human. This means that it can be easy to forget that the text wasn’t written by a person and to trust the information it provides without considering its accuracy. This can lead to the spread of false information and misinterpretation of facts. For example, if a user asks ChatGPT about a medical condition, it may provide inaccurate information that could harm the user.

The purpose of this article is to examine the impact of ChatGPT on critical thinking. We will explore the limitations of this technology, the ways in which it may perpetuate misinformation and biases, and the steps that individuals and organizations can take to maximize the benefits of ChatGPT while minimizing the risks.

• What is ChatGPT ?

• Potential Drawbacks of ChatGPT for Critical Thinking

• The potential for large language models to perpetuate biases and stereotypes

• Fake news , propaganda and misinformation

• Tips for exercising critical thinking when using language AIs

What is ChatGPT?

ChatGPT is a type of artificial intelligence language model that has been trained on a vast corpus of text data. This allows it to perform a wide range of tasks, including answering questions, generating written content, and participating in human-like dialogue.

One of the most remarkable capabilities of ChatGPT is its ability to generate written content that appears to be written by a human . This has led to its growing use in a number of industries, including journalism, advertising, and publishing. In journalism, for example, ChatGPT can be used to generate news articles, summaries, and reports. In advertising, it can be used to create captions, headlines, and product descriptions. In publishing, it can be used to generate fiction, poetry, and other forms of written content.

The growing use of ChatGPT in these industries has led to both excitement and concern. On one hand, ChatGPT has the potential to revolutionize the way we produce and consume written content. On the other hand, it raises questions about the impact of this technology on the quality and credibility of information. As ChatGPT becomes increasingly widespread, it’s important to understand its limitations, and to use it in a responsible and informed manner.

Potential Drawbacks of ChatGPT for Critical Thinking

ChatGPT poses a number of risks.

The potential for large language models to perpetuate biases and stereotypes

The potential for large language models to perpetuate biases and stereotypes has significant implications for critical thinking. In particular, it highlights the importance of being aware of the limitations of these models and the potential biases they may contain.

Large language models are not always objective

Firstly, it is important to recognize that large language models are not objective sources of information. They are trained on data that may contain biases and stereotypes, which means that the language they generate may reflect these biases . This means that we should be cautious when using language generated by these models as evidence or as the basis for decision-making.

For example, if a large language model generates language that reinforces a harmful stereotype, it is important to question the accuracy and reliability of this language. This requires a critical approach to evaluating the sources of information we use and being aware of the potential biases they may contain.

We need diverse and inclusive data sets

Secondly, the potential for large language models to perpetuate biases highlights the need for diverse and inclusive data sets. If the data used to train these models is biased or limited, the models are likely to replicate these biases in their language generation. Therefore, it is important to ensure that the data used to train these models is diverse and representative of the population.

This means that critical thinking should also involve evaluating the quality and diversity of the data used to train these models. It is important to consider the sources of the data, as well as how the data was collected and processed, in order to understand any potential biases that may be present.

Ethics: are we transparent and accountable in how we develop LLMs?

Finally, the potential for large language models to perpetuate biases and stereotypes also highlights the importance of ethical considerations in artificial intelligence. As these models become more powerful and more widely used, it is essential that they are developed and used in an ethical and responsible manner.

This requires critical thinking about the potential implications of these models and the need for transparency and accountability in their development and use. It is important to consider the ethical implications of these models, including issues related to bias, privacy, and fairness, in order to ensure that they are developed and used in a way that benefits society as a whole.

Fake news, propaganda and misinformation

Perhaps the most obvious concern is the spread of misinformation. As ChatGPT is capable of generating written content based on data and existing sources, it’s possible for it to perpetuate and amplify false or misleading information. This can undermine critical thinking by presenting individuals with biased or inaccurate information and hindering their ability to make informed decisions.

For example, blackhatworld.com is a forum where individuals engaged in unethical practices exchange ideas for profiting from fake content. ChatGPT is celebrated on the platform as a transformative tool for generating more sophisticated fake reviews, comments, and profiles.

Influence operations

These risks are not just theoretical. OpenAI itself published a report that examines the potential dangers posed by influence operations that leverage artificial intelligence.

What are influence operations?

Influence operations encompass a range of tactics that seek to activate individuals who hold certain beliefs, persuade a particular audience to adopt a specific viewpoint, or divert the attention of target audiences.

The principle behind the strategy of distraction is based on the fact that propagandists are in a race to capture user attention on social media platforms, which is already spread thin.

By disseminating alternative theories or diluting the information environment, propagandists could successfully absorb user attention without necessarily swaying their opinions.

Although influence operations can take various forms and employ a range of tactics, they share several common threads, such as:

portraying one’s government, culture, or policies positively
advocating for or against specific policies
depicting allies in a favourable light and opponents in an unfavourable light to third-party countries
destabilizing foreign relations or domestic affairs in rival countries.

The paper published by OpenAI discusses the potential misuse of large language models and the need for a proactive approach to address it. It examines various misuse scenarios, including disinformation campaigns, phishing attacks, and deepfakes, and explores the challenges involved in detecting and preventing such misuse.

But one thing that the paper doesn’t include is the fact that we can all improve our critical thinking skills to better assess the veracity of the information we encounter online.

While technical and policy interventions are important to mitigate the risks of language model misuse, each of us can also play a crucial role in combatting disinformation by honing our critical thinking skills and exercising greater scepticism when evaluating online content.

The potential drawbacks of ChatGPT for critical thinking demonstrate the need for accountability and caution in its use. As with any new technology, it’s important to be aware of its limitations and to use it in a responsible and informed manner. This will ensure that we can maximize its benefits while minimizing its risks and preserving the integrity of information and critical thinking.

It’s important to note that these risks can be mitigated through responsible development and deployment of AI systems, as well as through media literacy and critical thinking education for consumers of information.

Tips for exercising critical thinking when using language AIs

Here are some tips for using ChatGPT in a responsible and effective way:

Always verify the information provided by ChatGPT. Use reliable sources to check the accuracy of its responses.

While ChatGPT is designed to provide accurate and helpful information, it is always important to verify the information provided by any source, including ChatGPT. Users are encouraged to use reliable sources to check the accuracy of responses, particularly for important or sensitive information. Additionally, users should be aware that ChatGPT’s responses may not always reflect the most up-to-date information or the full range of perspectives on a given topic. Therefore, it is recommended to use ChatGPT’s responses as a starting point for further research and exploration.

Be aware of the limitations of ChatGPT and the biases that may be present in its responses.

ChatGPT has limitations and biases that users should be aware of. While ChatGPT has been trained on a vast amount of data to generate responses that are relevant and accurate, it is not infallible and may provide incomplete or inaccurate information. Moreover, like any machine learning model, ChatGPT is only as unbiased as the data it has been trained on, and may inadvertently reflect certain biases or limitations of the data. Therefore, it is important for users to approach ChatGPT’s responses with a critical eye and to supplement them with information from multiple sources to gain a well-rounded understanding of a given topic.

Exercise caution when using ChatGPT for sensitive or important decisions. Double-check its responses and consider seeking the advice of a professional if necessary.

When using ChatGPT for sensitive or important decisions, it is crucial to exercise critical thinking skills such as analysis, evaluation, and interpretation. Rather than relying solely on ChatGPT’s responses, it is important to double-check the information provided and to consider seeking the advice of a professional, particularly in complex or high-stakes situations. In addition to verifying the accuracy of ChatGPT’s responses, critical thinking skills such as logical reasoning and problem-solving can be used to weigh the pros and cons of different options and to make informed decisions based on the available information. By using critical thinking skills to supplement ChatGPT’s responses, users can make more informed and confident decisions, particularly in situations where the stakes are high.

Use ChatGPT to generate ideas and spark creativity, but don’t rely solely on its responses. Use your own critical thinking skills to evaluate and refine its output.

For example, , if you are using ChatGPT to generate ideas for a creative project, you can use your critical thinking skills to evaluate the quality and relevance of its suggestions. Consider factors such as whether the ideas align with your goals, whether they are feasible given your resources and constraints, and whether they are original and innovative. You can also use your critical thinking skills to build upon ChatGPT’s ideas and develop them further, using techniques such as brainstorming, mind mapping, or lateral thinking. By combining the power of ChatGPT’s natural language generation capabilities with your own critical thinking skills, you can enhance your creativity and generate ideas that are truly unique and impactful.

Educate yourself about the capabilities and limitations of ChatGPT. Read articles, watch videos, and participate in online forums to stay informed about this technology.

The growing use of ChatGPT has significant implications for critical thinking, both in terms of its benefits and its risks.

On the one hand, ChatGPT has the potential to increase the efficiency and accessibility of written content, making it easier for individuals and organizations to access and engage with information.

On the other hand, ChatGPT also poses a number of risks, such as the spread of misinformation and the homogenization of perspectives, which can undermine critical thinking.

In order to ensure that the impact of ChatGPT on critical thinking is positive and beneficial for all, it’s important for individuals, organizations, and policymakers to be aware of its limitations and to use it in a responsible and informed manner. This might involve developing guidelines for the ethical use of ChatGPT, such as ensuring that information generated by ChatGPT is fact-checked and verified, and that alternative perspectives are represented. It might also involve investing in education and training programs to help individuals develop critical thinking skills and to learn how to effectively engage with written content generated by ChatGPT.

In conclusion, while ChatGPT has the potential to offer significant benefits for critical thinking, it also poses a number of risks. By being aware of its limitations and using it in a responsible and informed manner, individuals, organizations, and policymakers can help to ensure that the impact of ChatGPT on critical thinking is positive and beneficial for all. Through careful and responsible use, ChatGPT can become a powerful tool for promoting critical thinking, improving access to information, and fostering greater understanding and collaboration.

How to Critically Evaluate News and Media Sources

I think we all agree that access to information has never been easier. With the click of a button, we can access an...

Critical Thinking in the Workplace

Imagine that you're in a job interview and the interviewer asks you to describe a time when you had to solve a complex...

Critical Thinking is Different from Debating

Do you agree that we are steadily bombarded with a seemingly endless stream of information, opinions, and arguments?...

Here's Everything You Need to Know About Using ChatGPT

Spent all of 2023 hearing about AI and want to try it out for yourself this year? We have you covered.

Learning to use AI chatbots effectively is more important than ever.

If 2023 was the year of AI, then 2024 will be carrying on this trend . You may not have tried out one of the many AI chatbots that hit the scene over the last year, but you've probably heard a thing or two about them. How could you not? OpenAI's ChatGPT gained 100 million users in just two months . It took Instagram and TikTok two and a half years and nine months, respectively, to hit that same mark.

The field of AI chatbots and other generative AI tools is expansive and growing. A short list includes Google Gemini, Microsoft Copilot, Claude.ai, Perplexity, Dall-E and Midjourney, and collectively they're poised to transform how you work, how you get information and how companies do business. But the chatbot craze got started with ChatGPT.

Learning to use and navigate AI chatbots will be increasingly important this year, and if one of your goals is to get more comfortable with AI, you're in the right place. Here's everything you need to know about getting started with ChatGPT.

For more, here's an in-depth look at ChatGPT and how AI is changing the way we answer our health questions .

What is ChatGPT?

ChatGPT is an artificial intelligence service that simulates human conversation to attempt to understand your text-based questions and requests and then respond to them. To accomplish this task, the chatbot is pretrained on large data sets (including public webpages) to look for patterns and create understandable and appropriate responses based on your requests or prompts. (The "GPT" part of the name reflects that and is short for "generative pretraining transformer.")

If you really want to dig into what ChatGPT is, we have a handy ChatGPT glossary that can help you make sense of it all.

Before your first ChatGPT prompt…

You can't start asking ChatGPT for help until you make an account with OpenAI.

Navigate to ChatGPT's login page , and you'll be met with the options to Log In or Sign Up. Tap the Sign Up button and provide your name, email address and a valid phone number to verify your account. Note you'll have to accept a couple of disclaimers from OpenAI before you can start prompting ChatGPT.

Tweak some ChatGPT settings

After creating your account and accepting OpenAI's disclaimers, you should do a few more things before asking all of your questions. First, I recommend tinkering with a few ChatGPT settings. There aren't too many settings, but the more familiar you are with the options, the better.

screenshot of ChatGPT's custom instruction screen

Custom instructions let you give ChatGPT some parameters to work with when answering your prompts -- at least it's supposed to.

The settings that I suggest adjusting are the Custom instructions , where you can give ChatGPT instructions and parameters for how to answer your prompts. These instructions can include information about you, how long or short responses should be, what your hobbies and interests are, and other specifying information. For instance, I told ChatGPT that I was a big fan of Taylor Swift and Formula 1. But when I would ask what music I should try listening to, or what sports I should try watching, this information did not seem to impact the responses I got.

Before your first prompt, define your 'why'

Now that you're set up, you're ready to ask your first question. Before you start typing your prompt, however, stop and think about what you really want out of your query.

You can ask ChatGPT to do all sorts of things for you, but the more focused you are when you're drafting your prompt, the more focused your answer will be. This practice, commonly referred to as prompt engineering , is important if you want useful answers from ChatGPT.

Ready, set, prompt

Prompting ChatGPT itself is simple. On ChatGPT's homepage, you will see a bar labeled "Message ChatGPT…" at the bottom of the page. When you have a prompt in mind, simply type it into that bar.

After you've submitted your prompt, ChatGPT will "think" for a moment, and then return a response to your question. At the bottom of ChatGPT's response, you will see four symbols. A small clipboard, a thumbs up, a thumbs down and a circular arrow.

The small clipboard allows you to copy ChatGPT's response, the thumbs up and thumbs down allow you to tell ChatGPT if its response is good or bad, and the circular arrow will tell ChatGPT to regenerate its response. Note: Regenerating the response will yield a different response than you got the first time.

After you prompt…

Even after ChatGPT yields its response, your job isn't quite done. There are still a couple of best practices to consider before putting ChatGPT's response into action.

Be aware of hallucination : Even if you have crafted a near-perfect prompt, ChatGPT may "hallucinate" in its answer. In the context of AI, hallucination refers to the chatbot returning incorrect and nonfactual information. This is not unique to ChatGPT and can affect other chatbots as well.

It's wise to double-check any advice you receive, and that's especially true when it's coming from a chatbot such as ChatGPT.

And that goes for questions around health and self-diagnosis . If you ask ChatGPT if women can use Rogaine (a hair-loss medication with the active ingredient minoxidil), for example, the chatbot may tell you that women can use Rogaine but only the women's formulations. But this isn't necessarily true. A 2017 study found that there is no chemical difference between men's and women's Rogaine . The only difference is the price, which can be 40% more for the women's version. When I was dealing with some hair loss, my dermatologist recommended me to opt for men's Rogaine to save a bit of money.

Sometimes ChatGPT gets it right. Usually it's close. Once in a while, it's very wrong. Check ChatGPT's answers with a Google search at the very least and, if possible, confirm the answer with professionals.

The answer is just… bad

I go into this much more in my guide on how to write prompts , but ChatGPT is by no means perfect. It will most likely give you an answer that you're not quite satisfied with. Luckily, it's easy to remedy this issue.

First, make sure you're asking a detailed question: The more usable information you put in your prompt, the better chance that you get back a usable answer. (You should be willing to go back and refine your prompt if you're not getting the answers you expected.)

Second, ask clarifying follow-up questions. I've found that this produces mixed results. It can sometimes prompt ChatGPT to refine its answer, but it can also just return more garbage.

Finally, if it feels like you're heading down the wrong path, start a new chat and ask your question again. Note that if you do start over or delete your chat history, your prompts are still on OpenAI's servers.

Does ChatGPT remember what I've asked it?

Your previous prompts will not affect the answers that ChatGPT gives you. I asked ChatGPT to help me brainstorm ideas for a birthday gift for my brother and gave information on his interests in my initial prompt. If I wanted to ask another question about my brother's birthday later, I would need to re-enter the information into ChatGPT.

This won't be the case for long, though. On Feb. 13, OpenAI announced that it's testing ways for ChatGPT to remember details you've discussed in earlier chats when you create new prompts. OpenAI said it was rolling out the features to a "small portion of ChatGPT free and Plus users this week" and will share plans for a larger rollout soon. If you have access to this new feature and you don't want ChatGPT to remember your history, you can disable it by going to Settings , selecting the Personalization tab and then toggling Memory off.

For more on AI, here's what to know about ChatGPT's new memory function and whether or not ChatGPT is helpful when it comes to wooing your loved one.

Editors' note: CNET is using an AI engine to help create some stories. For more, see this post .

Services and Software Guides

Best iPhone VPN
Best Free VPN
Best Android VPN
Best Mac VPN
Best Mobile VPN
Best VPN for Firestick
Best VPN for Windows
Fastest VPN
Best Cheap VPN
Best Password Manager
Best Antivirus
Best Identity Theft Protection
Best LastPass Alternative
Best Live TV Streaming Service
Best Streaming Service
Best Free TV Streaming Service
Best Music Streaming Services
Best Web Hosting
Best Minecraft Server Hosting
Best Website Builder
Best Dating Sites
Best Language Learning Apps
Best Weather App
Best Stargazing Apps
Best Cloud Storage
Best Resume Writing Services
New Coverage on Operating Systems
Hostinger Coupon Codes
HR&R Block Coupons
ShutterStock Coupon Codes
FedEx Office Coupons
Coursera Coupons
Autodesk Coupons
Codeacademy Coupon Codes
iolo Techologies Coupons
Norton Coupon Codes

New! Member Benefit New! Member Benefit
Featured Analytics Hub
Resources Resources
Member Directory
Networking Communities
Advertise, Exhibit, Sponsor
Find or Post Jobs

Learn and Engage Learn and Engage
Bridge Program

Compare AACSB-Accredited Schools
Explore Programs

Advocacy Advocacy
Featured AACSB Announces 2024 Class of Influential Leaders
Diversity, Equity, Inclusion, and Belonging
Influential Leaders
Innovations That Inspire
Connect With Us Connect With Us
Accredited School Search
Accreditation
Learning and Events
Advertise, Sponsor, Exhibit
Tips and Advice
Is Business School Right for Me?

Innovative AI Applications for Education

Avatars fill in for professors when students anywhere in the world have questions at any time of day.
Simulations and VR experiences help students learn teamwork and leadership skills under challenging conditions.
An AI-powered career coach analyzes a student’s career ambitions and suggests the courses and training opportunities that will provide the proper preparation.

As companies increasingly integrate artificial intelligence (AI) into their operations, it becomes more essential that business students gain a mastery of emerging technologies. Business schools are responding to the need with a range of initiatives that explore the possibilities and perils of virtual reality (VR), extended reality (XR), ChatGPT, and other digital tools.

Here, we look at six European schools that have reached beyond the constraints of traditional classrooms and created quirky ways to make AI a part of learning. They’re not only delivering content in radical new formats, but helping students perfect the skills they’ll need in tomorrow’s workplace.

The eProf Will Take Your Questions Now

At ESSEC Business School in Cergy, France, associate professor Fabrice Cavarretta wondered if AI could play a role in allowing him to share his knowledge and research. To find out, he came up with an avatar of himself that he named eProf Cavarretta.

He created it by feeding the body of his work—including various documents that ranged from practitioner articles to research papers—to a customized version of ChatGPT. He then instructed ChatGPT to answer questions in ways that are similar to how he explains concepts in his classes.

Now, students anywhere in the world can consult the avatar at any time. Learners currently taking one of his courses don’t need to raise a question in class; they can ask the avatar for clarification. Former students facing new problems or looking to refresh their knowledge can turn to the eProf whenever it’s convenient for them. Instead of querying an algorithm and receiving general answers, they can get Cavarretta’s expert perspective on any of his specific teachings or research methods.

Not only does the avatar have infinite patience, but it also allows for one-on-one interactions. Just as important, its broad scalability means Cavarretta can reach more students via avatar than he ever could on his own.

Learning Journeys on Earth, in Space

The scalability of AI is a major advantage for INSEAD Business School in Fontainebleau, France, which maintains an XR immersive learning library dedicated to management education and research. The portal allows users to access 20 VR experiences covering a range of management topics.

In one of these experiences, learners are virtually transported to a peaceful beach in Zanzibar. Various exotic juice bars dot the white sand that borders the clear turquoise waters. The bars are all close to each other, look the same, and sell similar products—so how do customers choose which bar to buy from?

INSEAD Business School’s extended reality learning library gives learners access to 20 virtual reality experiences covering a range of topics.

Participants meet two juice bar owners to gather details on their different business outlooks and competitive advantages. After completing their consultations, learners offer strategic advice on how to expand the avocado shake business. Through the simulation, students gain insights into sustainable growth, have a chance to devise innovative solutions, and get practice acting as consultants.

In another XR experience, students undertake a mission to Mars, where a new base needs to be built quickly. However, on the way, an accident occurs on the space shuttle, and learners must come up with ideas for how to save both the payload and the lives of the crew members. Working in teams, participants interview members of the crew, assess team dynamics, and recommend the best solutions to Mission Control. The objective of the simulation is for students to learn how to work in teams to generate innovative ideas in challenging environments.

More than 40 faculty members at INSEAD are using XR in their teaching, employing it in their research, or developing VR experiences. These experiences are available to other institutions around the world to use their own classrooms.

Critical Mission, Essential Learning

Similarly, ESMT Berlin is relying on an immersive VR simulation to drop participants into an imaginative yet perilous metaverse landscape.

“The simulation is centered around a critical mission where teams are plunged into an unstable setting threatened by environmental degradation,” says Mandy Hübener, director of executive education. “The simulation divides participants into two roles: One group uses VR to construct a bridge across hazardous terrains, embodying a hands-on, collaborative effort. Simultaneously, people in a second group located in a separate room act as strategic planners. This group, connected via audio, observes the VR team’s efforts and provides guidance, utilizing additional information to navigate challenges and allocate resources effectively.”

Through the exercise, participants work within a custom metaverse space to enhance their skills in hybrid teamwork, strategic thinking, and adaptability. As they seek solutions in a simulated high-stakes situation, they prepare to handle the complexities of real-world challenges.

AI is also a component in ESMT Berlin’s executive programs. A new challenge developed by Carolin Puppel, program director of executive education, teaches students how to use generative AI to complement human decision-making.

In ESMT Berlin’s virtual reality simulations, students build skills in teamwork, strategic thinking, and adaptability, which prepares them to handle real-world challenges.

Participants play the role of the chief quality officer at AquaPure. The company, which specializes in flavored bottled water, is facing a crisis because some products potentially have been contaminated. Using lab reports, customer feedback, and sales data, participants must determine how severe the contamination is and what actions they should take. These range from instituting a full product recall to staging customer service interventions. At the same time, participants must shape the appropriate communications.

Taking on tasks such as writing prompts and checking facts, team members learn to use AI tools such as ChatGPT as they analyze complex data, validate their findings, generate solutions, and make decisions. Because they are engaging with the tools on practical tasks, participants learn how to create effective prompts, address the limitations of AI, confirm accuracy, and understand the real dynamics at play when humans collaborate with technology.

Virtual, Immersive, and Personalized

Technology is a growing component of educational delivery at NEOMA Business School, which has locations in Reims, Rouen, and Paris, France. In 2020, the school opened a virtual campus , an online space that allows students to join seminars and meetings or even play football on the digital pitch.

The school also has brought VR cases into its classrooms. For instance, NEOMA partnered with ENEDIS, a major electricity grid operator in France, to create an immersive case study experience for its Global Executive MBA.

In addition, the school uses AI-powered adaptive learning processes to sort students into slower or faster learners. This allows faculty to adapt the type and quantity of exercises they provide in the classroom while putting more focus on areas that are more challenging. Taking these insights one step further, professors can turn fast learners into mentors who help other students and thus contribute to the success of the entire class.

Alain Goudey, professor of marketing and associate dean for digital at NEOMA, has written about how tools such as ChatGPT can improve education by providing students with personalized assessments and high-quality feedback, thus freeing up some of the instructor’s time and attention. He says, “The time saved means there’s more human interaction, which is beneficial for teachers and students alike.”

The Career Coach With All the Answers

AI can be useful outside of the classroom, too, as POLIMI Graduate School of Management in Milan demonstrates with its career coach, FLEXA . The tool was created through a partnership with Microsoft.

POLIMI’s AI career coach analyzes a student’s career ambitions, proposes training opportunities, and suggests which skills might need improvement.

Acting as a digital mentor, the AI application analyzes a student’s career ambitions and proposes the best training opportunities. It even allows participants to go through an assessment phase to evaluate the skills they need to improve before they embark on their personalized learning paths.

To create programs tailored to unique individuals, FLEXA sorts through about 800,000 pieces of learning material, from digital courses and webinars to podcasts, articles, and case studies. Because it maintains profiles of interested professionals, FLEXA also can serve as a digital recruiting platform for corporations looking to hire new talent.

An IDEA for the Future Classroom

As these examples show, today’s business schools are highly focused on answering a critical question: How will technology shape the future of learning?

It’s a question that’s getting particular attention at Imperial College Business School’s Innovation, Digital Education, and Analytics Lab ( IDEA Lab ) in London. In one initiative, which considers how AI can be integrated into learning, faculty are using course materials and personas to create AI avatars and simulations. As students converse with the avatars to deepen their understanding of specific topics, AI turns passive content consumption into interactive dialogues.

Through rapid advancements in AI and XR, society is witnessing a unique convergence of digital and physical worlds and unlocking an entirely new set of tools to build solutions, says the IDEA Lab’s executive director Monica Arés. This rare moment in the trajectory of education, she adds, will increase student engagement and retention by enabling personalized learning at scale.

As other schools come up with their own ways of integrating AI into the classroom, they will create more fun, intriguing, and innovative learning experiences. Sandy beaches and space shuttles are just the beginning—who knows where business education might go next?

artificial intelligence
experiential learning
future of business education
learner engagement
online learning
virtual reality

Mobile Workstations
Student Offers
All-in-Ones
Towers & Mini's
Workstations
Configure Your Workstation
Virtual Reality
More than 27"
Between 23" - 25"
Home Office
InkJet Printers
LaserJet Printers
Large Format Printers
Discover HP+
Instant Ink
Print At Your Service
Recycling Program
Mice & Keyboards
Power Adapters
Docking Stations
Gaming Accessories
Audio & VR Headsets
Bags & Cases
Software & Drivers
Technical Support
Track My Order
Contact HP Store
Frequently Asked Questions
My saved cards
Personal Information
My Addresses
Reset Password

New to HP Store?

more item(s) in your basket

Free Delivery on all orders to UK mainland within 3 working days.

Discover the wider range of HP products.

Find the perfect HP product to fit your needs.

Discover the range
Shop by product type
See all Laptops
See all Desktops
See all Workstations
Shop by screen size
See all Monitors
See all Printers
See our full range

Contact our Technical Support or download Drivers and Software.

HP TECH TAKES /...

What is ChatGPT?

Defining artificial intelligence.

Types of AI

Capability-based, narrow or weak ai, general or strong ai, functionality-based, limited memory, theory of mind, what chatgpt can do.

Development

Pros for ai, cons for ai, about the author, related tags.

artificial intelligence

Article archives

What Do You Really Need in Your Carry On? >
2020 Articles >
2019 Articles >
2018 Articles >
Latest HP Laptops
Latest HP Desktops
Laptop Offers
Desktop Offers
Printer Offers
All Printers
Accessories
All-in-One Desktops
Home Desktops
Business Desktops
Gaming Desktops
Home Laptops
Business Laptops
Gaming Laptops

Disclosure: Our site may get a share of revenue from the sale of the products featured on this page.

Shipping Information
Order Tracking
Returns Information
Cancellation Policy
My HP Rewards
Chat with a sales rep
Send us an email

Prices, specifications, availability and terms of offers may change without notice. Price protection, price matching or price guarantees do not apply to Intra-day, Daily Deals or limited-time promotions. Quantity limits may apply to orders, including orders for discounted and promotional items. Despite our best efforts, a small number of items may contain pricing, typography, or photography errors. Correct prices and promotions are validated at the time your order is placed. These terms apply only to products sold by HP.com; reseller offers may vary. Items sold by HP.com are not for immediate resale. Orders that do not comply with HP.com terms, conditions, and limitations may be cancelled. Contract and volume customers not eligible.

HP’s MSRP is subject to discount. HP’s MSRP price is shown as either a stand-alone price or as a strike-through price with a discounted or promotional price also listed. Discounted or promotional pricing is indicated by the presence of an additional higher MSRP strike-through price

The following applies to HP systems with Intel 6th Gen and other future-generation processors on systems shipping with Windows 7, Windows 8, Windows 8.1 or Windows 10 Pro systems downgraded to Windows 7 Professional, Windows 8 Pro, or Windows 8.1: This version of Windows running with the processor or chipsets used in this system has limited support from Microsoft. For more information about Microsoft’s support, please see Microsoft’s Support Lifecycle FAQ at https://support.microsoft.com/lifecycle

Ultrabook, Celeron, Celeron Inside, Core Inside, Intel, Intel Logo, Intel Atom, Intel Atom Inside, Intel Core, Intel Inside, Intel Inside Logo, Intel vPro, Itanium, Itanium Inside, Pentium, Pentium Inside, vPro Inside, Xeon, Xeon Phi, Xeon Inside, and Intel Optane are trademarks of Intel Corporation or its subsidiaries in the U.S. and/or other countries.

In-home warranty is available only on select customizable HP desktop PCs. Need for in-home service is determined by HP support representative. Customer may be required to run system self-test programs or correct reported faults by following advice given over phone. On-site services provided only if issue can't be corrected remotely. Service not available holidays and weekends.

HP will transfer your name and address information, IP address, products ordered and associated costs and other personal information related to processing your application to Bill Me Later®. Bill Me Later will use that data under its privacy policy.

Microsoft Windows 10: Not all features are available in all editions or versions of Windows 10. Systems may require upgraded and/or separately purchased hardware, drivers, software or BIOS update to take full advantage of Windows 10 functionality. Windows 10 is automatically updated, which is always enabled. ISP fees may apply and additional requirements may apply over time for updates. See http://www.microsoft.com.

“Best All In One Printer” and “the easiest printer you’ve ever had to set up” from Wirecutter. ©2020 The Wirecutter, Inc.. All rights reserved. Used under license. https://www.nytimes.com/wirecutter/reviews/best-all-in-one-printer/

Get Marvel’s Avengers when you purchase HP gaming PCs with qualifying 9th gen or 10th gen Intel® Core™ i5, i7 and i9 processors. Redemption code will be sent out by email within 60 days of purchase. Limited quantities and while supply lasts. Offer valid thru 12/31/2020 only while supplies last. We reserve the right to replace titles in the offer for ones of equal or greater value. Certain titles may not be available to all consumers because of age restrictions. The Offer may be changed, cancelled, or suspended at any time, for any reason, without notice, at Intel’s reasonable discretion if its fairness or integrity affected whether due to human or technical error. The Offer sponsor is Intel Corporation, 2200 Mission College Blvd., Santa Clara, CA 95054, USA. To participate you must create an Intel Digital Hub Account, purchase a qualifying product during the redemption period, enter a valid Master Key, and respond to a brief survey. Information you submit is collected, stored, processed, and used on servers in the USA. For more information on offer details, eligibility, restrictions, and our privacy policy, visit https://softwareoffer.intel.com/offer/20Q3-19/terms.

© 2020 MARVEL. © Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries in the U.S. and/or other countries. Other names and brands may be claimed as the property of others.

The personal information you provide will be used according to the HP Privacy Statement (https://www8.hp.com/us/en/privacy/ww-privacy.html)

Turnitin marks one year anniversary of its AI writing detector with millions of papers reviewed globally

Anniversary and number of papers reviewed sheds new light on data around AI writing use in education

Press Contact

[email protected]

About Turnitin

Turnitin is a global company dedicated to ensuring the integrity of education and meaningfully improving learning outcomes. For 25 years, Turnitin has partnered with educational institutions to promote honesty, consistency, and fairness across all subject areas and assessment types. Turnitin products are used by educational institutions and certification and licensing programs to uphold integrity and increase learning performance, and by students and professionals to do their best, original work.

Turnitin has offices in Australia, Germany, India, Japan, South Korea, Mexico, the Netherlands, Sweden, The United Arab Emirates, the United Kingdom, and the United States. Over 16,000 academic institutions, publishers, and corporations use Turnitin services: Gradescope by Turnitin, iThenticate, Turnitin Feedback Studio, Turnitin Originality, Turnitin Similarity, ExamSoft by Turnitin, ProctorExam, and Ouriginal.

IMAGES

How to Improve Critical Thinking
Critical Thinking Definition, Skills, and Examples
How To Improve Critical Thinking Skills at Work in 6 Steps
The benefits of Critical Thinking for Students
Why Critical Thinking is Important for Businesses?
How to promote Critical Thinking Skills

VIDEO

How ChatGPT "Thinks"
IFAC EdExchange: An AI Tutor for Accountancy Students
ChatGPT Gets A Memory
Exploring the effectiveness of ChatGPT in enhancing critical thinking and problem-solving skills
Stanford's Thoughts on ChatGPT
Mastering Chat GPT: The Benefits of AI with Romon Logan

COMMENTS

Importance of critical thinking to understand ChatGPT
Importance of critical thinking to understand ChatGPT. European Journal of Human Genetics 32 , 377-378 ( 2024) Cite this article. This is a response to [ 1] providing constructive criticism ...
Leveraging ChatGPT for Enhancing Critical Thinking Skills
This article presents a study conducted at Georgia Gwinnett College (GGC) to explore the use of ChatGPT, a large language model, for fostering critical thinking skills in higher education. The study implemented a ChatGPT-based activity in introductory chemistry courses, where students engaged with ChatGPT in three stages: account setup and orientation, essay creation, and output revision and ...
Importance of critical thinking to understand ChatGPT
Importance of critical thinking to understand ChatGPT. Eur J Hum Genet. 2023 Aug 15. doi: 10.1038/s41431-023-01443-4. Online ahead of print.
Importance of critical thinking to understand ChatGPT
Abstract Aspects of scientific method are discussed: In particular, its representation as a motivated iteration in which, in succession, practice confronts theory, and theory, practice. Rapid…. Expand. 1,837. PDF. Semantic Scholar extracted view of "Importance of critical thinking to understand ChatGPT." by F. Emmert-Streib.
Metacognition and Critical Thinking: Using ChatGPT-Generated Responses
Successful problem solving is a complex process that requires content knowledge, process skills, developed critical thinking, metacognitive awareness, and deep conceptual reasoning. Teaching approaches to support students developing problem-solving skills include worked examples, metacognitive and instructional scaffolding, and variations of these techniques. In this report, we describe a ...
Using ChatGPT to Encourage Critical AI Literacy Skills and for
Critical thinking means different things to different people, from a limited view of criticality linked to cognition and rational thought, to more dialogical, creative, even caring approach to critical thinking . However, as ChatGPT does not yet reveal its sources, it is difficult to understand where certain criteria come from, what theories ...
Adapting to the Future: ChatGPT as a Means for Supporting ...
The ChatGPT platform itself lacks higher-order thinking abilities, and this lack of discernment may pose threats to students' development of critical thinking skills. If students depend on ChatGPT to produce exam and assignment content, bypassing the learning process can have negative consequences for knowledge construction and critical ...
Leveraging ChatGPT for Enhancing Critical Thinking Skills
Students who recommended using ChatGPT to enhance critical thinking skills were highly likely to self-report being more confident to evaluate the credibility of sources (r = 0.749), ask probing questions (r = 0.895), understand complex concepts (r = 0.633), and generate new ideas (r = 0.666).
Importance of critical thinking to understand ChatGPT
The disposition toward critical thinking. Jan 1995. 1. P A Facione. C A Sanchez. N C Facione. J Gainen. PA Facione. Request PDF | On Aug 15, 2023, Frank Emmert-Streib published Importance of ...
ChatGPT effects on cognitive skills of undergraduate students
The ChatGPT may offer students feedback and guidance, which can help them develop a deeper understanding (Rospigliosi, 2023) of the topic and enhance their critical thinking skills (Darvishi et al., 2022; Kasneci et al., 2023). Another possible justification is that ChatGPT may provide students with a more personalized learning experience.
ChatGPT and the Decline of Critical Thinking
The use of ChatGPT as a search engine has made the need for critical thinking more pressing than ever, writes Enrique Dans. OpenAI's launch of ChatGPT in late November captured the world's attention and opened our eyes to the existence of a technology capable of a surprising number of things called machine learning. Note the language here.
Metacognition and Critical Thinking: Using ChatGPT ...
The results also revealed that incoming university students likely require scaffolding to develop sophisticated critical-thinking skills. AB - Successful problem solving is a complex process that requires content knowledge, process skills, developed critical thinking, metacognitive awareness, and deep conceptual reasoning.
Importance of critical thinking to understand ChatGPT
TY - JOUR. T1 - Importance of critical thinking to understand ChatGPT. AU - Emmert-Streib, Frank. PY - 2023. Y1 - 2023. U2 - 10.1038/s41431-023-01443-4
ChatGPT elevates the need for critical thinking skills
Independent thinking. Critical thinking can be defined in a few different ways, but it's essentially the ability to think clearly and independently about a subject or problem. It often requires the consideration of multiple perspectives, the checking of biases, and a detailed understanding of relevant context.
(PDF) ChatGPT and Generative AI: Possibilities for Its Contribution to
The study's contribution lies in ChatGPT-generated lesson plans' implications and the enhancement of critical thinking for teacher education, and it also underscores the need for further ...
Development and validation of ChatGPT literacy scale
Laupichler et al. highlighted the importance of the ability to understand technology in AI literacy. Based on these findings, we developed the first factor, technical proficiency with ChatGPT, and defined it as the possession of the technical skills required to understand and utilize ChatGPT. Factor 2. Critical evaluation
PDF Comment: Importance of critical thinking to understand ChatGPT
Comment: Importance of critical thinking to understand ChatGPT Frank Emmert-Streib, Predictive Society and Data Analytics Lab, Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland Email: [email protected] This is a response to [1] providing constructive criticism about [2,3].
Drivers and Consequences of ChatGPT Use in Higher Education: Key
On the other hand, the over-reliance on ChatGPT is one of the critical negative aspects, because it reduces critical thinking". (FC-2) ... They have to emphasize the importance of critical thinking and problem-solving skills as fundamental aspects of education. ... Students must understand the importance of academic honesty and avoid using ...
The Importance of Critical Thinking when Using ChatGPT ...
When using ChatGPT for sensitive or important decisions, it is crucial to exercise critical thinking skills such as analysis, evaluation, and interpretation. Rather than relying solely on ChatGPT's responses, it is important to double-check the information provided and to consider seeking the advice of a professional, particularly in complex ...
The Impact of ChatGPT on Student Learning/performing
It investigates the impact of ChatGPT on student engagement, critical thinking, and problem-solving skills, as well as its potential to enhance writing skills and provide personalized learning ...
ChatGPT and Information Literacy
A new iteration called GPT-4, which can read imagery in addition to text inputs, promotes "safer and more useful responses.". The implications of ChatGPT and other generative AI platforms on information literacy and academic research are part of ongoing discussions at University of Houston, in which faculty and librarians are familiarizing ...
Don't Be A Jerk: The Surprising Success Skill In The Age Of AI
Even ChatGPT can explain it: Don't be a jerk. In an age in which people are increasingly connected through digital communications, it's important to remember how our interactions come across.
[PDF] Can ChatGPT understand genetics?
Computer Science, Biology. ArXiv. 2024. TLDR. This survey surveyed the applications of ChatGPT in various sectors of bioinformatics and biomedical informatics throughout the year, covering omics, genetics, biomedical text mining, drug discovery, biomedical image understanding, bioinformatics programming, and bioinformatics education. Expand.
Here's Everything You Need to Know About Using ChatGPT
Prompting ChatGPT itself is simple. On ChatGPT's homepage, you will see a bar labeled "Message ChatGPT…". at the bottom of the page. When you have a prompt in mind, simply type it into that bar ...
ChatGPT use linked to sinking academic performance and memory loss
ChatGPT use is linked to bad results and memory loss. (Getty Images) Using AI software such as ChatGPT is linked to poorer academic performance, memory loss and increased procrastination, a study has shown. The AI chatbot ChatGPT can generate convincing answers to simple text prompts, and is already used weekly by up to 32% of university ...
Innovative AI Applications for Education
The scalability of AI is a major advantage for INSEAD Business School in Fontainebleau, France, which maintains an XR immersive learning library dedicated to management education and research. The portal allows users to access 20 VR experiences covering a range of management topics. In one of these experiences, learners are virtually ...
What Is Chat GPT
What ChatGPT can do. ChatGPT is an AI chatbot. That means a user can enter a text prompt and receive an intelligently-generated output, allowing for a back-and-forth conversation. While similar platforms have existed for a few years now, what makes ChatGPT so impressive is its detail and versatility.
Turnitin marks one year anniversary of its AI writing detector with
Additionally, the survey** found 75 percent of these students said they will continue to use the technology even if faculty or institutions ban it. Students and instructors have gained a new tool that can help promote transparency and develop critical thinking skills. The use of generative AI has grown over the past year with more growth to come.

Importance of critical thinking to understand ChatGPT

Access options

Author information

Contributions

Corresponding author

Ethics declarations

Additional information

Rights and permissions

About this article

Share this article

Quick links

Importance of critical thinking to understand ChatGPT

Publication types

ChatGPT and the Decline of Critical Thinking

Retaining Talent in the Age of Resignation

RELATED CONTENT

Charging into the Future with Electric Vehicles

Art, Cognac, and AI

AI in Elections: The Battle for Truth and Democracy

Vision, Tech, and Learning. The Secret Sauce of AI-Powered Enterprises

Tech Transformation Is Human (Not Digital)

Chaos at OpenAI

Metacognition and Critical Thinking: Using ChatGPT-Generated Responses as Prompts for Critique in a Problem-Solving Workshop (SMARTCHEMPer)

Access to Document

Other files and links

Importance of critical thinking to understand ChatGPT

ASJC Scopus subject areas

Access to Document

ChatGPT elevates the need for critical thinking skills

What is critical thinking?

Independent thinking

Why AI makes critical thinking essential

Development and validation of ChatGPT literacy scale

Cite this article

Access this article

Similar content being viewed by others

Students’ voices on generative AI: perceptions, benefits, and challenges in higher education

Artificial Intelligence (AI) Student Assistants in the Classroom: Designing Chatbots to Support Student Success

AI-based chatbots in customer service and their effects on user compliance

Data availability

Author information

Corresponding author

Ethics declarations

Informed consent

Conflict of interest

Additional information

Rights and permissions

About this article

Share this article

Drivers and Consequences of ChatGPT Use in Higher Education: Key Stakeholder Perspectives

Abu Elnasr E. Sobaih

1. Introduction

2. Literature Review

2.2. Drivers and Consequences of ChatGPT in Higher Education

3.1. Methods Adopted

3.2. Participants

3.3. Analysis of the Collected Data

4.1. Stakeholders’ Perceptions of Using ChatGPT for Academic Proposes in Higher Education

4.1.1. Key Drivers of Using ChatGPT for Academic Purposes in Higher Education

4.1.2. Consequences of Using ChatGPT for Academic Purposes in Higher Education

4.1.3. Recommendations for Mitigating the Negative Consequences of ChatGPT Use in Higher Education

5. Discussion and Implications

6. Conclusions

Funding Statement

Author Contributions

Institutional Review Board Statement

Informed Consent Statement

Data Availability Statement

The Importance of Critical Thinking when Using ChatGPT (and Other Large Language Models)

Written by Argumentful

What is ChatGPT?

Potential Drawbacks of ChatGPT for Critical Thinking

The potential for large language models to perpetuate biases and stereotypes

Large language models are not always objective

We need diverse and inclusive data sets

Ethics: are we transparent and accountable in how we develop LLMs?

Fake news, propaganda and misinformation

Influence operations

What are influence operations?

Tips for exercising critical thinking when using language AIs