OpenAI‘s chatGPT — an AI-powered chatbot — passed some of the most challenging professional exams in the U.S. However, basic Math, which even a middle school student can solve, still doesn’t seem to be an area of expertise for the chatbot.
What Happened: Ethan Mollick, associate professor at Wharton School of the University of Pennsylvania, where he studies and teaches innovation and entrepreneurship, shared a couple of reports on Twitter saying, “ChatGPT clearly passes some of the most challenging American professional exams.”
See Also: Elon Musk Shares Thoughts On ChatGPT As AI Chatbot Becomes Latest Internet Sensation
Mollick was referring to the U.S. Medical Licensing Exam, MBA-level Operating exam and the Bar Exam. He cited the research papers saying “chatGPT is not always accurate,” but neither are “doctors, lawyers and executives.”
Elon Musk, also a founding member of OpenAI, reacted to Mollick’s post by saying, “Wow.”
Why It’s Important: In the white paper concerning the Wharton MBA exam, researcher Christina Terwiesch stated that while chatGPT’s answers were impressive, it made “major mistakes” in reasonably simple situations.
The paper read, “Chat GPT3 at times makes surprising mistakes in relatively simple calculations at the level of 6th-grade Math. These mistakes can be massive in magnitude.”
Benzinga independently also verified the same and found that while chatGPT could answer questions about Chemistry correctly, it couldn’t give accurate answers for subjects like Mathematics and Physics.
The question and solution was taken from BYJU's, an education technology company.
© 2024 Benzinga.com. Benzinga does not provide investment advice. All rights reserved.
Comments
Trade confidently with insights and alerts from analyst ratings, free reports and breaking news that affects the stocks you care about.
