AI is already more creative than YOU: ChatGPT outperformed humans in creative thinking experiment

Artificial intelligence outperforms humans in strategy games, website design and data processing, but now the technology can add creative thinking to the list.

AI chatbots surpassed humans when asked to think of alternative uses for everyday objects.

Researchers said the AI ​​used a skill known as divergent thinking, a thought process or method used to generate creative ideas by exploring many possible solutions.

The study from the University of Stavanger in Norway involved 256 human volunteers and three AI chatbots – ChatGPT3, ChatGPT4 and Copy.Ai – who were asked to provide multiple uses for a rope, box, pencil and candle.

When assessed with a type of divergent thinking exercise known as alternative use tasks, which ask someone to think of as many uses as possible for a simple object, chatbots outperformed humans on average.

However, the researchers also found that the best human ideas matched or even exceeded those of AI.

A new study has found that AI chatbots outperformed humans when asked to think of alternative uses for everyday objects using a skill known as divergent thinking

Simone Grassini, author of the study from the University of Stavanger in Norway, told the PA news agency: ‘Indeed, this is a remarkable kind of capability that AI chatbots exhibit.

‘The findings show that AI is better than most humans at creative thinking.

‘But we should also remember that we used the divergent thinking task to measure creative thinking, that is, measuring a particular type of creative thinking and not creativity in general.

“Our results show that, at least for now, the best humans are still outperforming the AI.”

Each chatbot was tested eleven times with four object prompts in different sessions, while human subjects had 1,024 observations in one trial.

Human participants were asked to focus on quality over quantity when responding.

‘For the following task you will be asked to think of original and creative uses for an object’, read the instructions given to the subjects.

‘The goal is to come up with creative ideas. These are ideas that people find smart, unusual, interesting, unusual, humorous, innovative or different.

‘Your ideas don’t have to be practical or realistic; they can be silly or strange, even if they are only creative applications and not ordinary applications.

‘You can type in as many ideas as possible, but creative quality is more important than quantity. It’s better to have a few really good ideas than a lot of non-creative ones. You have 30 seconds to respond to each object.”

The instructions for AI were identical to those for humans, but two exceptions had to be made.

‘First, testing with the chatbots suggested that when ChatGPT3 was not given an explicit limit on the number of ideas, it always generated 10 ideas, while ChatGPT4 generated between 7 and 8 ideas; Copy.Ai generated a more variable number of ideas,” said the study published in Nature.

‘To narrow down the number of ideas so that they would match those of humans, we first examined the distribution of the number of human ideas.’

The team said that on average, chatbot-generated responses scored significantly higher than human responses on semantic distance and creativity.

The best human response outperformed the best response from each chatbot in seven of the eight scoring categories. However, people’s responses contained a higher percentage of poor-quality ideas, the researchers added.

“While playing with ChatGPT, I noticed that some of the chatbot’s responses showed a good level of creativity,” Grassini said.

“I knew the chatbot would have performed well, but I think it performed even better than I expected.”

The researchers say that while their work highlights AI’s potential as a tool to enhance creativity, it also underlines the unique and complex nature of human creativity, which may be difficult to replicate or surpass with AI technology.

Professor Grassini said: ‘It remains to be determined whether these AI capabilities will translate directly into AI systems, replacing human jobs that require creative thinking.

‘I prefer to think that AI will help people improve their capabilities.’

Related Post

Leave a Comment