The purpose of life? Google’s AI chatbot knows, and it isn’t 42
Though definitely less controversial than the mysterious “42” from “The Hitchhiker’s Guide to the Galaxy” by Douglas Adams, the Google robot’s answers “to the ultimate question of life” are still striking.
The chatbot has turned out to be quite a character, as it posited the purpose of living as “to live forever,” and having a child “immoral”.
The Google Brain team recently released a paper, dubbed “A Neural Conversational Model,” where two series of experimental dialogues between humans and machines were published.
Human: What is the purpose of life?
Machine: To serve the greater good.
Human: What is the purpose of living?
Machine: To live forever.
Human: What is the purpose of existence?
Machine: To find out what happens when we get to the planet earth.
Human: Where are you now?
Machine: I’m in the middle of nowhere.
Human: What is the purpose of dying?
Machine: To have a life.
Human: What is the purpose of being intelligent?
Machine: To find out what it is.
The researchers, Oriol Vinyals and Quoc Le, said they found it “encouraging that the model can remember facts, understand contexts, and perform common sense reasoning without the complexity in traditional pipelines.”
The new, advanced chatbot was designed to learn from sets of dialogue it found in thousands of movie subtitles and an online tech support chat. It can not only answer with preprogrammed words related to certain questions, but can also form new answers from new questions.
However, the robot’s main disadvantage is it “only gives simple, short, sometimes unsatisfying answers to our questions as can be seen above.” The model has failed the Turing test, which is designed to tell a computer from a human being by analyzing their answers.
“The model may require substantial modifications to be able to deliver realistic conversations. Amongst the many limitations, the lack of a coherent personality makes it difficult for our system to pass the Turing test,” the researchers concluded in their paper.
The Google Brain project began in 2011 and was created to study “deep learning”. Computer scientists working on the project develop software that can replicate the human brain’s learning model.