IJSSER

Title: A Comparison of the Relative Effectiveness of AI vs Humans in Debugging Computer Code
Authors: Yuvan Ganne and John Leddo
\|\| \|\|
Yuvan Ganne and John Leddo MyEdMaster LLC Virginia, USA
MLA 8 Ganne, Yuvan, and John Leddo. "A Comparison of the Relative Effectiveness of AI vs Humans in Debugging Computer Code." Int. j. of Social Science and Economic Research, vol. 9, no. 12, Dec. 2024, pp. 5997-6001, doi.org/10.46609/IJSSER.2024.v09i12.022. Accessed Dec. 2024. APA 6 Ganne, Y., & Leddo, J. (2024, December). A Comparison of the Relative Effectiveness of AI vs Humans in Debugging Computer Code. Int. j. of Social Science and Economic Research, 9(12), 5997-6001. Retrieved from https://doi.org/10.46609/IJSSER.2024.v09i12.022 Chicago Ganne, Yuvan, and John Leddo. "A Comparison of the Relative Effectiveness of AI vs Humans in Debugging Computer Code." Int. j. of Social Science and Economic Research 9, no. 12 (December 2024), 5997-6001. Accessed December, 2024. https://doi.org/10.46609/IJSSER.2024.v09i12.022.
References [1] . Agbolade Omowole. (2021, July 19). Research shows AI is often biased. Here’s how to make algorithms work for all of us. World Economic Forum. https://www.weforum.org/stories/2021/07/ai-machine-learning-bias-discrimination/ [2] . Henderson, S. (2022, March 16). There’s More to AI Bias than Biased Data, NIST Report Highlights. NIST; NIST. https://www.nist.gov/news-events/news/2022/03/theres-more-ai-bias-biased-data-nist-report-highlights [3] . How AI Bias Is Impacting Healthcare. (2024). Informationweek.com. https://www.informationweek.com/machine-learning-ai/how-ai-bias-is-impacting-healthcare# [4] . IBM Data and AI Team. (2023, October 16). AI Bias Examples \| IBM. Ibm.com; IBM. https://www.ibm.com/think/topics/shedding-light-on-ai-bias-with-real-world-examples [5] . Moschella, D. (2022, April 25). AI Bias Is Correctable. Human Bias? Not So Much. Itif.org. https://itif.org/publications/2022/04/25/ai-bias-correctable-human-bias-not-so-much/ [6] . Norori, N., Hu, Q., Aellen, F. M., Faraci, F. D., & Tzovara, A. (2021). Addressing bias in big data and AI for health care: A call for open science. Patterns, 2(10), 100347. https://doi.org/10.1016/j.patter.2021.100347 [7] . Schwartz, R., Vassilev, A., Greene, K., Perine, L., Burt, A., & Hall, P. (2022). Towards a Standard for Identifying and Managing Bias in Artificial Intelligence. Towards a Standard for Identifying and Managing Bias in Artificial Intelligence, 1270(1270). https://doi.org/10.6028/nist.sp.1270 [8] . Tyson, A., Pasquini, G., Spencer, A., & Funk, C. (2023, February 22). 60% of Americans Would Be Uncomfortable With Provider Relying on AI in Their Own Health Care. Pew Research Center Scienociety. https://www.pewresearch.org/science/2023/02/22/60-of-americans-would-be-uncomfortable-with-provider-relying-on-ai-in-their-own-health-care [9] . What do we do about the biases in AI? \| McKinsey. (n.d.). Www.mckinsey.com. [10] . https://www.mckinsey.com/mgi/overview/in-the-news/what-do-we-do-about-the-biases-in-ai\
ABSTRACT: Current research and educational assessment have concluded that the majority of AI programs have AI bias, which causes their data to be skewed (Schwartz et al., 2022). Because of this trend that can affect almost all AI programs, it is hard to know how large of a problem AI bias can be and how much it can affect data representation. This paper explores whether AI bias exists in finding errors in computer code. We conducted an experiment in which we took 2 AI code debuggers and 2 human programmers. Next, we tested the AI code debuggers against 24 different pieces of code with various errors, using the human programmers as a control comparison. The results of the experiment showed that the AI’s accuracy of error was around 95% while the humans were around 89%. These results showed that, in regard to the AI programs used for error detection in coding, AI bias is not a frequent problem that can impact data heavily.

IJSSER is Member of