In a new study designed to test the co-creative capabilities ... An additional 150 memes were generated by GPT-4o for comparison. A second group of 98 people then rated the memes on how funny, ...

The researchers sourced slightly fewer than 100 people using Prolific, a platform where participants are paid to take studies. They were presented with one of six images popular in memes ...

In a study, memes created by OpenAI's GPT-4o model were, on average, rated funnier, more creative and more shareable than those created by humans.

In a new study designed to test the co-creative ... A second group of 98 people then rated the memes on how funny, creative and shareable they were. The memes were randomized so raters didn ...