Generative AI: MARCs of Intelligence
Is an AI “smart” if it passes certain tests? How much does it “know”? Can it really “think”? Answering these questions has led to a proliferation of benchmarks measuring different capacities, which are difficult to accurately compare.
Hear Professor Bert Baumgaertner speak about abstractions and reasoning corpus (ARC) 2 p.m. tomorrow, Oct. 7, on the Library first floor. Learn about the distinctions between knowledge and intelligence benchmarks using ARC and a home-grown version including metaphors (MARC) as examples.
