Even the best AI models studied can be fooled by nonsense sentences, showing that “their computations are missing something about the way humans process language.”zuckermaninstitute.columbia.edu abobla ( @abobla@lemm.ee ) ScienceEnglish • 1 year ago message-square4fedilinkarrow-up121
arrow-up121external-linkEven the best AI models studied can be fooled by nonsense sentences, showing that “their computations are missing something about the way humans process language.”zuckermaninstitute.columbia.edu abobla ( @abobla@lemm.ee ) ScienceEnglish • 1 year ago message-square4fedilink
minus-square brie ( @brie@beehaw.org ) linkfedilink1•1 year agoGood point. It just seems odd that the Columbia article calls them “current language models,” whereas the coauthor of the paper is quoted as only calling them “the best models [the authors of the paper] have studied.”
Good point. It just seems odd that the Columbia article calls them “current language models,” whereas the coauthor of the paper is quoted as only calling them “the best models [the authors of the paper] have studied.”