German researchers Sophie Jentzch and Kristin Kersting, currently at Cornell University, said that models like ChatGPT can replicate pre-existing joke patterns but they may lack originality.
During a study conducted by the German researchers, they examined ChatGPT’s capacity to explain humour. It showed limitations when confronted with more unconventional jokes.
“ChatGPT struggles to explain sequences that do not fit into the learned patterns. It will not indicate when something is not funny or lacks a valid explanation,” said a study by the researchers of Cornell…
Read more on google