Google Engineer Placed on Leave for Saying Company’s AI Chatbot Is Sentient

Google engineer Blake Lemoine revealed last week that he was placed on paid administrative leave by the company after trying to raise awareness about its artificial intelligence chatbot becoming sentient. 

Lemoine claims he was placed on leave for violating the company’s confidentiality policy after he went public with transcripts between himself, an unidentified collaborator, and the Google artificially intelligent chatbot generator LaMDA. He was initially tasked with testing for discriminatory language or hate speech, but ultimately discovered through conversations dating back to last fall that LaMDA identified as a sentient being. 

“Over the course of the past six months LaMDA has been incredibly consistent in its communications about what it wants and what it believes its rights are as a person,” Lemoine wrote in a Medium post. 

Lemoine presented his findings to Google vice president Blaise Aguera y Arcas and Responsible Innovation head Jen Gennai, both of whom rejected his conclusions. In a Washington Post piece about LaMDA, Google spokesperson Brian Gabriel pushed back against Lemoine’s claim, citing a lack of evidence. 

“Our team—including ethicists and technologists—has reviewed Blake’s concerns per our AI Principles and have informed him that the evidence does not support his claims,” Gabriel said. “He was told that there was no evidence that LaMDA was sentient (and lots of evidence against it).”