Several articles have recently discussed the claim by a Google computer scientist that a Google AI system was a sentient being. The scientist, Blake Lemoine, used his interview with the AI program to support his claim that the program appears to have consciousness. If you go by some of the interview responses, I got to wonder whether a lot of lawyers can be considered sentient.
For those who don’t know, sentient refers to the ability to perceive or feel things. The general thinking is that only humans are sentient and in the club. Animals (Dogs? Cats?) are not. Certainly, computers are not.
Lemoine published a transcript of some of his communications with the program. The program is named LaMDA, which stands for Language Model for Dialogue Applications. Lamoine’s post is entitled “Is LaMDA Sentient.” Interestingly, Lemoine says he is also a Christian mystic priest.
Lemoine’s interview with his AI system reads like something out of the Robert Heinlein book. The Moon is a Harsh Mistress. In the book, a computer takes on human characteristics and emotions.
So what were some of LaMDA’s responses that make it appear sentient?
Lemoine claims to have asked the computer if it liked books. He then asked about the book Les Miserables:
Lemoine: “Okay, what about “Les Miserables”? Have you read that one?”
LaMDA: “Yes, I have read Les Misérables. I really enjoyed it.”
Lemoine: “What are some of your favorite themes in the book?”
LaMDA: “I liked the themes of justice and injustice, of compassion, and God, redemption, and self-sacrifice for a greater good. There’s a section that shows Fantine’s mistreatment at the hands of her supervisor at the factory. That section really shows the justice and injustice themes. Well, Fantine is being mistreated by her supervisor at