Subscribe now

Technology

AIs get better at maths if you tell them to pretend to be in Star Trek

Chatbots vary their answers depending on the exact wording used to prompt them, and now it seems that asking an AI to answer as if it were a Star Trek captain boosts its mathematical ability

By Chris Stokel-Walker

29 February 2024

Star Trek is playing a role in the strange new world of large language models

Album/Alamy

Instructing an AI chatbot to answer questions as if it were in the TV show Star Trek seems to improve its mathematical ability, although no one is exactly sure why.

People who use chatbots like ChatGPT have already recognised that the quality of outputs can be improved by asking the AI to adopt a certain persona, or by bribing or threatening it. Rather…

Sign up to our weekly newsletter

Receive a weekly dose of discovery in your inbox! We'll also keep you up to date with New Scientist events and special offers.

Sign up

To continue reading, subscribe today with our introductory offers

View introductory offers

No commitment, cancel anytime*

Offer ends 2nd of July 2024.

*Cancel anytime within 14 days of payment to receive a refund on unserved issues.

Inclusive of applicable taxes (VAT)

or

Existing subscribers

Sign in to your account