An artificial intelligence chatbot, ChatGPT, according to recent research from the University of Montana, match the top 1% of human thinkers on levels of creativity.
The AI application, created using GPT-4, performed exceptionally well in both fluency and originality on the widely used Torrance Tests of Creative Thinking.
They solicited replies from 24 University of Montana students for the study. The results were contrasted with those of 2,700 students who took the TTCT nationwide. Scholastic Testing Service, which had no idea that AI was engaged, graded all entries. Following that, the results were contrasted with those of 2,700 college students nationwide who took the TTCT in 2016.
According to the study, the AI responses were just as creative as other participants. According to the report, ChatGPT outperformed most students nationwide.
“For ChatGPT and GPT-4, we showed for the first time that it performs in the top 1% for originality,” said Dr Erik Guzik, an assistant clinical professor at UM’s College of Business who directed the study. That was new.”
The researchers patiently awaited the data and refrained from drawing any hasty judgements.
One verbal and one figurative assessment are both included in the TTCT. Both gauge divergent thinking, or the method of thinking that leads to original ideas, according to CNBC.
“But we shared strong evidence that AI seems to be developing creative ability on par with or even exceeding human ability,” Dr Guzik admitted.
“We had all been exploring with ChatGPT, and we noticed it had been doing some interesting things that we didn’t expect,” Dr Guzik said. “Some of the responses were novel and surprising. That’s when we decided to put it to the test to see how creative it really is.”
