If ChatGPT had been human, it would have received a rating between B and B –…Theartificial intelligence developed by Open AI has demonstrated the ability to write compelling answers to a prestigious exam (MBA conclusion) offered by the Wharton business school.
“ Not only are the answers correct, but the explanations are excellent. “, we can read research work which exposes this new test conducted with ChatGPT conversational AI. The goal was to require the RN to pass a standard exam that concludes an MBA (Master of Business Administration), the highest-level international education in business management.
The test turned out to be quite conclusive: OpenAI’s GPT3 chat has shown a remarkable ability to automate some of the skills of high-paying workers in general and workers in positions requiring an MBA in particular, including analysts, managers, and consultants. “, explains Christian Terwiesch, a professor at Wharton.
Business school students, however, have some consolation. ChatGPT definitely got a pass grade, but it didn’t shine either. Christian Terwiesch says the AI would narrowly succeed, getting a B or a B-. Furthermore, this grade could only be obtained after some adjustments in the answers: the professor wanted to observe how the AI could improve when it was given clues in the face of an incorrect answer. ” ChatGPT3 is remarkably good at modifying its responses after signals given by humans “, points out. ” In other words, in cases where it initially failed to match the problem with the correct solution, GPT3 Chat was able to correct itself after receiving an appropriate suggestion from a human expert. “.
“Massive” math errors.
It should also be noted that the performance of ChatGPT is rather uneven depending on the domains covered by the proposed questions. ” As others have argued before me, Chat GPT3 sometimes makes startling mistakes in relatively simple 6th grade math level calculations. These errors can be huge “says Christian Terwiesch. We were really talking yesterday in an article a test carried out on ChatGPT and Claude, a similar AI, by a specialized company. Similarly, the AIs had some difficulty tackling some math problems.
In terms of analytics, ChatGPT also hit its limits during this review: “ The current version of Chat GPT cannot handle more advanced process analysis questions, even if based on fairly standard templates. This includes process flows with multiple products and problems with stochastic effects such as demand variability “, the professor details. On the other hand, ” Chat GPT3 does an amazing job on basic operations management and process analysis questions, including those based on case studies “. However, this performance is enough to raise some perplexities… Both in terms of cheating and future competition on the labor market: a debate that is on many lips these days, including in the arts.