Confidentiality: AI tools collect user information that cannot be deleted - and may share information with third-party vendors. Consider this privacy concern as you use these tools.
Bias: AI can produce sexist, racist or otherwise biased results
Erroneous Information: AI can produce erroneous or misleading information - including making up citations for article and book citations - and even people - that do not exist(!) AI might not include up-to-date information.
Copyright Risks: AI may present copyright and intellectual property risks
Lack of originality: AI may produce output that is not unique.
Potential for scams and fraud
Does AI pose larger societal threats? See the Center for AI Safety (CAIS)
See more on our library guide on Fake News, Misleading News, Biased News
Carpenter, Todd A. (2023, January 11). Thoughts on AI's impact on scholarly communications? An interview with ChatGPT. Scholarly Kitchen.
Chen, Brian X. (2022, December 21). How to use ChatGPT and still be a good person. New York Times. Chen notes some of the limitations of ChatGPT including a reminder that the results may look plausible and yet be incorrect (!) Also, results may be biased based on the data, text, images given to create the AI.
Christian, Jon. (2023, February 9). Magazine publishes serious errors in first AI-generated health article. NeoScope [Sports Illustrated, Men's Journal.]
Koplin, J., & Hatherley, J. (2022, December 19). Guest post: It has become possible to use cutting-edge AI language models to generate convincing high school and undergraduate essays. Here's why that matters. Practical Ethics.
Leffer, L. (2023, January 17). CNET is reviewing the accuracy of all its AI-written articles after multiple major corrections. Big surprise: CNET's writing robot doesn't know what it's talking about. Gizmodo.
Markkula Center for Applied Ethics. Internet ethics (Includes AI)
News Literacy Project. News literacy in the age of AI
Nolan, Beatrice. (2023, January 15). This man used AI to write and illustrate a children's book in 1 weekend. He wasn't prepared for the backlash. Business Insider.
Old Dominion University Libraries. Algorithms & AI Information about issues with computer algorithms
Ruiz, PatI. (2022, May 20). Artificial intelligence in education: A reading guide focused on promoting equity and accountability in AI. CIRCLS: Center for Integrative Research in Computing and Learning Sciences.
Savage, M. (2023, January 18). Nick Cave says ChatGPT's Ai attempt to write Nick Cave lyrics 'sucks'. BBC News. (What happens when AI results just aren't aesthetically pleasing?)
Thompson, Ben. (2022, December 5). AI Homework Stratechery. Good descriptions of ChatGPT creating some misleading and incorrect information for a homework assignment.
Does it matter if the output is true? Do you have the expertise to verify that the output is accurate? Are you able and
willing to take full responsibility (legal, moral, etc.) for missed inaccuracies? Questions to consider before using ChatGPT
PROMPT given to ChatGPT:
You are teaching an undergraduate English composition course. Provide your students with a handout with the pros and cons of using ChatGPT for writing academic papers.
RESPONSE from ChatGPT: