AIs are more accurate at math if you ask them to respond as if they are a Star Trek character — and we're not sure why

Researchers asking a chatbot to optimize its own prompts found it was best at solving grade-school math when acting like it was on Star Trek.

Related Keywords

California ,United States ,Staffordshire ,United Kingdom ,Teja Gollapudi ,Catherine Flick At Staffordshire University ,Vmware ,Star Trek ,Captain Picard ,Trick Battle ,New Scientist ,Large Language Models ,Starship Enterprise ,Staffordshire University ,Positive Thinking ,Pick Battle ,