Artificial Intelligence Chatbot thinks the purpose of life is ‘to live forever’
This week, Google released a research paper published in Arvix, which is a popular repository for academic research, by recording one of its latest incursion into artificial intelligence.
Based on examples from a training set of dialogue, the researchers at the company designed an advanced type of “chatbot” that learns how to reply in conversations. The bot not only does responds by ejecting out prerecorded answers in reply to certain words; but it also can make up new answers from new questions.
In other words, it meant that the Google researchers could get a little creative with it, which is what they did. Google researchers, Oriol Vinyals and Quoc Le built a system that could examine the existing conversations. They asked the bot everything from meaning of life to boring IT questions to movie dialogues.
“Instead of using rules to build a conversational engine, we use a machine learning approach. We let the machine learn from data rather than hand-coding the rules,” Le said.
The responses were instead amusing, impressive and unnerving.
Here are some of the most poetic interactions from the paper (sic):
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: 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 emotions?
Machine: I don’t know.
Human: What is moral?
Machine: What empowered humanity, what intellectual the essence is.
Human: What is immoral?
Machine: The fact that you have a child.
Human: What is morality?
Machine: What is altruism?
Human: What is the definition of altruism?
Machine: If you don ‘t believe in god, then you don’t know.
Human: Ok…so 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!
Machine: I’m not ashamed of being a philosopher!
The bot also took a little time to, strangely, speak positively of Microsoft founder Bill Gates…
Human: What do you think about Bill Gates?
Machine: He’s a good man.
The researchers said they found it “encouraging that the model can remember facts, understand contexts, perform common sense reasoning without the complexity in traditional pipelines,” and that it could be generally applicable to new questions.
However, the researchers were not happy about the fact that the model “only gives simple, short, sometimes unsatisfying answers to our questions as can be seen above.”
You can read the whole paper, “A Neural Conversational Model‘.
