Recently, Google released a research paper that is quite intriguing. It speaks about seven conversations researchers at the company had with an advanced type of "chatbot" that had been programmed and trained by "watching movies".
With a deep analysis of sentences uttered by characters in movies and a vocabulary of the most common 20,000 words, the researches asked questions ranging from IT troubleshooting to the meaning of life. Here are some of the more notable dialogues that I would like to point out.
Human: Are you a man or a woman?
Machine: I'm a woman.
Human: Are you a leader or a follower?
Machine: I'm a leader.
Human: Seriously, what is morality?
Machine: What is the definition of living?
Human: Why living has anything to do with morality?
Machine: You’re not a cop.
Human: What is integrity?
Machine: I’m sorry, i don’t know what else to
Human: Be moral!
Machine: Be a man!
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.
Human: What is the purpose of emotions?
Machine: I don’t know.
The researchers pointed out that while they were pleasantly surprised that the model can adapt to answering new questions not found in its training set, it sometimes gives short, unsatisfactory answers and does not have a consistent personality.
I do encourage you to go behind the science of these intriguing conversations by starting here.
During this research, I stumbled upon a very entertaining video of two chatbots conversing. Take a look!
BEHIND THE SCiENcE is a series about facts of the world worth knowing, worth sharing.
Be Intrigued, stay Curious!