In a new paper, cognitive science researchers from the University of California San Diego found that more than half the time, people mistook writings from GPT-4 as having been written by a human.
Beyond the 54 percent who mistook GPT-4 for a human, exactly 50 percent of the subjects confused GPT-3.5, the latest LLM’s direct predecessor, for a person as well.
They conclude that the Large language model (LLM) passes the Turing test which is a simple method to determine if a machine can demonstrate human intelligence.
However, we have to wait for the paper to be peer-reviewed until any final conclusions can be made.
MORE