AI Chatbots Show Comparable Creativity to Humans in Divergent Thinking Task

AI Chatbots Show Comparable Creativity to Humans in Divergent Thinking Task

AI Chatbots Show Comparable Creativity to Humans in Divergent Thinking Task

A recent study published in Scientific Reports suggests that large language model (LLM) AI chatbots may be able to compete with humans in terms of creative thinking. The study focused specifically on the Alternate Uses Task (AUT), a test that measures divergent thinking by asking participants to come up with alternative uses for everyday objects within a short time frame.

The researchers, Mika Koivisto and Simone Grassini, compared the responses of 256 human participants to those of three AI chatbots: ChatGPT3, ChatGPT4, and Copy.Ai. The responses were evaluated based on several criteria, including fluency, flexibility, originality, and elaboration.

On average, the chatbot-generated responses scored higher than the human responses in terms of semantic distance (how closely related the response was to the object’s original use) and creativity. The maximum scores for the human responses were generally higher, but the chatbot responses had a more consistent range.

While the study suggests that AI chatbots are capable of generating creative ideas comparable to the average human, it also highlights that the top-performing humans still outperformed the best chatbot responses. This raises questions about the role of AI in augmenting human creative processes.

The findings of this study have implications for the future integration of AI into the creative workflow. While AI chatbots can contribute to generating creative ideas, there is still a unique and complex nature of human creativity that AI may struggle to fully replicate or surpass.

Further research could explore how AI can be effectively integrated into the creative process to enhance human performance. Understanding the relationship between human and machine creativity is crucial as we navigate the future of creative work in the age of AI.

Source: Scientific Reports

Definitions:
– Large language model (LLM): AI models capable of generating human-like text based on input prompts.
– Divergent thinking: A thought process associated with creativity that involves generating many different ideas or solutions for a given task.
– Alternate Uses Task (AUT): A test of divergent thinking where participants are asked to come up with alternative uses for everyday objects.
– Semantic distance: The measure of how closely related a response is to the original use of an object.

Source: Scientific Reports (link not included)



Tags: