From a young age, many children have been instructed by their parents to be polite to smart assistants. But when it comes to AI assistants like OpenAI’s ChatGPT, there might be some tangible benefits to being rude and even insulting them. “Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8 percent for Very Polite prompts to 84.8 percent for Very Rude prompts,” the paper reads. “For the longest of times, we humans have wanted conversational interfaces for interacting with machines,” coauthor and Penn State IT professor Akhil Kumar told Fortune. To Kumar and his colleague, Penn State undergraduate Om Dobariya, it’s a definitive “no.” In their paper, they stopped well short of advocating being mean to AI.