To Catch a Fake: Machine learning sniffs out its own machine-written propaganda
Publication/Creation DateJune 2 2019
DescriptionResearchers at Allen Institute and the Paul Allen School of Computer Science and Engineering at the University of Washington have tuned the "GPT-2" neural network to create "Grover," a program that both creates convincing fake articles but also is able to detect those fakes, pointing to a way to combat propaganda.
Date archivedJune 11 2019
Last editedMay 22 2020