Research published in Nature today used machine learning to try to find “a name-like component” in the rumbles of elephants. The AI model identified which elephant was being addressed 27.5 percent of the time, and they could use those calls to get a reaction from that elephant.

“Our finding that elephants are not simply mimicking the sound associated with the individual they are calling was the most intriguing,” Fristrup said. “The capacity to utilize arbitrary sonic labels for other individuals suggests that other kinds of labels or descriptors may exist in elephant calls.”