According to new research by the University of Montana, ChatGPT, an artificial intelligence chatbot can match the top 1 per cent of human thinkers on a standard test of creativity.
The AI application, developed using GPT-4, excelled in fluency and originality in the Torrance Tests of Creative Thinking, a widely recognised tool for assessing creativity.
For the research, they collected responses from 24 University of Montana students. The scores were compared with 2,700 students nationally who took the TTCT. All submissions were scored by Scholastic Testing Service, which didn't know that AI was involved. Then the scores were compared with 2,700 college students nationally who took the TTCT in 2016.
The study said that the AI responses were as creative as the responses from the most creative real people who took the test. It said that ChatGPT outperformed a majority of students nationally.
"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 carefully waited for the results and did not jump to conclusions.
"But we shared strong evidence that AI seems to be developing creative ability on par with or even exceeding human ability," Dr Guzik admitted.
The TTCT contains different assessments: one verbal and one figural. Both measure divergent thinking, or the thought process used to generate creative ideas, CNBC reported.
In the study, ChatGPT responses were in the top percentile for fluency and originality.
"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."
