OpenAI's chatGPT, an AI-powered chatbot, passed some of the most challenging professional exams in the U.S. Even a middle school student can solve basic math, but it doesn't seem to be an area of expertise for the chatbot.
What Happened: Ethan Mollick, associate professor at the University of Pennsylvania School of Innovation and entrepreneurship, shared a couple of reports on Twitter saying that ChatGPT passed some of the most challenging American professional exams. Elon Musk Shares Thoughts On ChatGPT As AI Chatbot Becomes Latest Internet Sensation
Mollick was referring to the Bar Exam, the Medical Licensing Exam, the MBA-level Operating Exam and the Medical Licensing Exam. He cited the research papers saying that chatGPT is not always accurate, but neither are doctors, lawyers, and executives. Elon Musk, a founding member of OpenAI, reacted to Mollick's post by saying, Wow. Why It is Important: In the white paper regarding 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 GPT 3 at times makes surprising mistakes in relatively simple calculations at the level of 6th grade math. These mistakes can be huge in magnitude. Benzinga independently verified the same, and found that while ChatGPT could answer correctly the questions about Chemistry, 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.
Continue reading Next: ChatGPT Popularity Reports Leads To Google Declaring Code Red As Sundar Pichai Increases Involvement In AI Strategy