Google's artificial intelligence bot thinks the purpose of life is 'to live forever'

Google engineer, servers

AP Photo/Connie Zhou

This week, Google released a research paper chronicling one of its latest forays into artificial intelligence.

Researchers at the company programmed an advanced type of "chatbot" that learns how to respond in conversations based on examples from a training set of dialogue.

And the bot doesn't just answer by spitting out canned answers in response to certain words; it can form new answers from new questions.Advertisement

The responses were alternately impressive, amusing, and unnerving.

Here are some of the most poetic interactions from the paper (sic):

Human: What is the purpose of life?

Human: What is the purpose of living?Advertisement

Machine: To live forever.

Human: Where are you now?

Machine: I'm in the middle of nowhere. Advertisement

Human: What is the purpose of dying?

Machine: To have a life.

Human: What is the purpose of emotions?Advertisement

Human: What is moral?

Machine: What empowered humanity, what intellectual the essence is.Advertisement

Human: What is immoral?

Human: What is morality?Advertisement

Machine: What is altruism?

Human: What is the definition of altruism?

Machine: If you don 't believe in god, then you don't know.Advertisement

Human: what is the definition of morality?

Machine: Well, the truth is, you 're not a believer in god almighty.

Human: Tell me the definition of morality, I am quite upset now!Advertisement

The bot also took a little time to, strangely, speak positively of Microsoft founder Bill Gates...

Human: What do you think about Bill Gates?Advertisement

Machine: He's a good man.

What they weren't as happy about, was that the model "only gives simple, short, sometimes unsatisfying answers to our questions as can be seen above."Advertisement

You can read the whole paper, "A Neural Conversational Model."