Get the latest tech news
Study finds AI-generated meme captions funnier than human ones on average
Mollick proclaims “the meme Turing Test has been passed,” but a new study offers a key caveat.
The researchers attribute the AI model's strong average performance to its training on vast amounts of Internet data, allowing it to identify broadly appealing humor patterns. Additionally, the use of crowdsourced evaluators introduces subjectivity and potential biases toward mainstream or conventional humor, possibly favoring AI-generated memes optimized for broad appeal. The research team suggests future work should explore scenarios where an AI model rapidly generates multiple ideas, allowing humans to act as curators who select and refine the best content.
Or read this on ArsTechnica
