Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
A study revealed that instructing an AI chatbot to solve math problems as if it were a Star Trek character improves its accuracy, though the reason behind this enhancement remains unclear. The approach has shown promising results, prompting further investigation into its efficacy.
AI Chatbots Are Better at Math When They Pretend to Be Star Trek Characters https://t.co/W51urNW86i https://t.co/ufj2hTbp3k
“AIs get better at maths if you tell them to pretend to be in Star Trek” One of the first SuperPrompts I taught to a AI research scientist at a very large AI company was to show them the Star Trek motif. He laughed and said I was uniformed. Article: https://t.co/ALpds16tJr
Trying to get a chatbot to do maths? Begin by asking it to pretend to be a Star Trek captain, and you could see more accurate answers, though no one quite knows why. https://t.co/TD6PJQIX8V