Two separate research papers have disclosed that ChatGPT has the ability to pass the United States Medical Licensing Exam and earn an MBA from an Ivy League business school.
One study was led by Christian Terwiesch, a professor at the University of Pennsylvania’s Wharton School, and a group of medical researchers mostly affiliated with Ansible Health. The team discovered that the artificial intelligence-driven chatbot GPT-3 could pass the school’s Master of Business Administration (MBA) program’s final exam.
The ChatGPT bot, according to the report, does an “amazing job at basic operations management and process analysis questions, including those based on case studies,” with excellent explanation. The bot was also said to be adept at “altering its responses in response to human hints.” ChatGPT’s response style, according to educators, makes it difficult to distinguish it from human responses. Terwiesch and his colleagues discovered, however, that the chatbot had difficulty performing even basic mathematics.
The other was ChatGPT passing the US Medical Licensing Examination (USMLE), which is taken by medical students who want to become doctors. It passed the three levels of medical professionals and provided insights and explanations for how it arrived at its conclusions.
One of the papers, which was published in December and is available for reading on medRxivopens, demonstrated that ChatGPT could achieve more than 50% accuracy across all exams. The paper, however, has not yet been peer-reviewed.
The sources for this piece include an article in TheRegister.