Being rude to ChatGPT may boost its accuracy: Study

A study from Pennsylvania State University has revealed that ChatGPT's accuracy may improve when it's prompted rudely. Researchers tested OpenAI's GPT-4o model using over 250 unique prompts ranging from very polite to very rude and found that the AI model performed best when given blunt or impolite instructions. Even neutral prompts performed better than polite ones, the scientists found.