SciTechDaily reports that, according to a new study funded by the University of Bergen, humans are, on average, outperformed by AI when it comes to creativity. At first glance, this seems like bad news for creatives, but that might not necessarily be true. The same study found that AI could not out-perform the highest-scoring human creatives, meaning that AI’s creative capabilities fall short against those of the most creative humans.

The creativity was assessed in the following way:

Mika Koivisto and Simone Grassini compared 256 human participants’ responses with those of three AI chatbots’ (ChatGPT3, ChatGPT4, and Copy.Ai) to AUTs for four objects — a rope, a box, a pencil, and a candle. The authors assessed the originality of the responses by rating them on semantic distance (how closely related the response was to the object’s original use) and creativity.

The responses were anonymously assessed by human evaluators for creativity, and semantic distance was quantified by a computational method.

On average, the chatbot-generated responses scored significantly higher than the human responses for both semantic distance (0.95 vs. 0.91) and creativity (2.91 vs. 2.47).

It’s interesting to note that the human responses were rated over a much wider range, with minimum scores far lower than AI’s minimum ratings. Humans’ highest ratings, however, were generally higher.

Further research will be needed to assess the full implications of these findings, especially since the researchers acknowledge that this was a limited study, noting that they ‘only considered performance in a single task associated with the assessment of creativity.’

At Novagram, we think it’s fair to say that our high-performing creativity has been well demonstrated. We feel confident that we’d come out on top in a creativity battle against AI!