Think you're funny? ChatGPT might be funnier
What criteria did Science X use to review the article?
Science X reviewed the article based on several criteria, including fact-checking, peer-reviewed publication, trusted source, and proofreading. The editorial process ensured the content's credibility by verifying the information, checking for proper citation and references, and ensuring the article adhered to editorial guidelines and standards.
How did participants rate ChatGPT jokes compared to human jokes?
In a study comparing jokes by people and ChatGPT, nearly 70% of participants rated ChatGPT-generated jokes as funnier than those crafted by humans6. A little over 25% of participants rated the human-crafted responses as funnier, and only about 5% rated jokes from both sources as equally funny.
What tasks were given to generate jokes in the first study?
In the first study, both ChatGPT and human participants were given three tasks to generate jokes. They had to create humorous new phrases for common acronyms, generate funny answers to fill-in-the-blank phrases, and come up with a "roast joke" based on an awkward fictional scenario. This resulted in over 945 jokes written by 105 writers and 180 jokes generated by ChatGPT.