October 14, 2024

New Study: AI Chatbots Surpass the Average Human in Creativity

These findings recommend that AI chatbots can now produce creative ideas at least as well as the typical human. The authors keep in mind that they just thought about performance in a single task associated with the evaluation of creativity. The authors propose that future research study might check out how AI can be integrated into the innovative process to improve human performance.

Mika Koivisto and Simone Grassini compared 256 human participants actions with those of 3 AI chatbots (Copy.Ai, chatgpt4, and chatgpt3) to AUTs for four items– a rope, a box, a pencil, and a candle light. The authors examined the creativity of the responses by score them on semantic range (how carefully associated the action was to the items initial use) and creativity.
A computational technique was used to measure semantic range on a scale from 0 to 2, whilst human critics, blind to the originators of the actions, subjectively ranked creativity from 1 to 5. Usually, the chatbot-generated responses scored significantly greater than the human reactions for both semantic distance (0.95 vs. 0.91) and imagination (2.91 vs. 2.47).
The human reactions had a far greater variety in both measures– the minimum scores were much lower than for the AI reactions, however the optimum ratings were usually higher. The very best human action outshined each chatbots finest reaction in seven out of 8 scoring categories.
These findings recommend that AI chatbots can now generate creative concepts at least along with the typical human. The authors keep in mind that they only thought about efficiency in a single task associated with the assessment of creativity. The authors propose that future research could check out how AI can be incorporated into the imaginative process to improve human efficiency.
Referral: “Best human beings still surpass expert system in an innovative divergent thinking task” by Mika Koivisto and Simone Grassini, 14 September 2023, Scientific Reports.DOI: 10.1038/ s41598-023-40858-3.
The research study was funded by the University of Bergen.

A recent study indicates that AI chatbots might excel over the typical human in creative thinking jobs, such as suggesting alternative usages for everyday things. However, top-performing people still surpassed the very best chatbot leads to these jobs.
A recent research study published in the journal Scientific Reports recommends that big language model (LLM) AI chatbots might excel beyond the typical human in innovative jobs, like brainstorming alternate usages for typical items– a reflection of divergent thinking. Nevertheless, people who scored the greatest in these tasks still went beyond the top-performing chatbot results.
Divergent thinking is a kind of believed procedure frequently linked with imagination, highlighting the generation of various ideas or options for a particular task.
It is frequently examined with the Alternate Uses Task (AUT), in which participants are asked to come up with as lots of alternative uses for a daily things as possible within a brief time period. The responses are scored for four various classifications: fluency, flexibility, elaboration, and originality.