Humor is emerging as a revealing lens for understanding bias within artificial intelligence systems. A new study published in Scientific Reports found that when tools like ChatGPT and DALL-E were prompted to make images “funnier,” the resulting shifts in representation highlighted underlying patterns of bias. Stereotypical portrayals of age, body weight, and visual impairments became more prominent, while depictions of racial and gender minorities decreased.
Generative artificial…
Article Source
https://www.psypost.org/scientists-just-found-a-novel-way-to-uncover-ai-biases-and-the-results-are-unexpected/
