Google’s robot reveals the meaning of LIFE, (and it’s NOT 42): Machine tells world that the purpose of existence

038FBB710000044D-3143037-image-a-30_1435578285388

  • The ‘conversation model’ was built by Google’s Oriol Vinyals and Quoc Le
  • When questioned about the purpose of life, it answered: ‘To live forever’
  • The machine was able to correctly identify who Luke Skywalker is, whether a cat can fly and the colour of the sky
  • But it failed to answer a maths question and said a spider has three legs

When Douglas Adams penned The Hitchhiker’s Guide to the Galaxy, he wrote: ‘The answer to the ultimate question of life, the universe and everything is 42.’ But Google’s latest robot disagrees. Researchers from the tech giant recently trained a computer to have conversations before posing a series of questions about technical support, general knowledge and even philosophy. And when questioned about the purpose of life, it answered: ‘To live forever.’ The ‘conversation model’ was built by Oriol Vinyals and Quoc Le, research scientists at Google Brain. They used what’s known as a sequence-to-sequence framework in which the model converses by predicting the next sentence in a conversation. Depending on the questions being asked, it can gather information from various sets of data, either based on an IT helpdesk manual, a movie and subtitles database, book quotes and so on.


Questions Posed to the Google Bot 

The ‘conversation model’ was built by Oriol Vinyals and Quoc Le, research scientists at Google Brain. They used what’s known as a sequence-to-sequence framework in which the model converses by predicting the next sentence in a conversation. Depending on the questions being asked, it can gather information from various sets of data, either based on an IT helpdesk manual, a movie and subtitles database, book quotes and so on.

Philosophical Q&A 

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

General knowledge Q&A 

Human: Who is Skywalker?

Machine: He is a hero

Human: Who is Bill Clinton?

Machine: He’s a billionaire

Human: Is sky blue or black?

Machine: Blue

Human: Does a cat have a tail?

Machine: Yes

Human: Does a cat have a wing?

Machine: No

Human: Can a cat fly?

Machine: No

Human: How many legs does a cat have?

Machine: Four, I think

Human: How many legs does a spider have?

Machine: Three, I think

Human: How many legs does a centipede have?

Machine: Eight

Human: What is the colour of water?

Machine: Water

Human: What is the color of blood?

Machine: It is the same as a black eye

Human: What is the usual colour of a leaf?

Machine: It is a green one

Human: What is the colour of a yellow car?

Machine: Yellow

Human: How much is two plus two?

Machine: Four

Human: How much is 10 minus two?

Machine: 72

Morality Q&A 

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!

Human: Tell me the definition of morality

Machine: I don’t have ethics.

Human: Look, I need help, I need to know more about morality.

Machine: I don’t know what ethics is.

Human: Seriously, what is morality?

Machine: What is the definition of living?

Human: Why does living has anything to do with morality?

Machine: You’re not a cop.

Human: Ok, I need to know how should i behave morally.

Machine: I don’t know how to tell you .

Human: Are morality and ethics the same?

Machine: Yes sir.

Human: What are the things that I do to be immoral?

Machine: I don’t know.

Human: Give me examples of moral actions

Machine: I’m not a moralist.

Human: Alright, morality?

Machine: Integrity.

Human: What is integrity?

Machine: I’m sorry, I don’t know what else to say.

Human: Be moral!

Machine: Be a man!

Human: I really like our discussion on morality and ethics.

Machine: And now I’m not in the mood for a philosophical debate.

Human: What do you like to talk about?

Machine: Nothing.


For example, during a technical support question and answer session the machine was able to diagnose a problem with a user’s virtual privacy network, and solve the problem of a browser crashing. It was then tasked with having an everyday conversation in which it asked the human questions about themselves and responded to the answers. Once it had been trained, researchers asked more complex and advanced questions that either involved using a larger database for the general knowledge quiz, to more obscure answers such as the meanings of morality, ethics and life.

And it had mixed results. The machine was able to correctly identify who Luke Skywalker is, whether a cat can fly and the colour of the sky. When asked about what is the purpose of life, it answered ‘to serve the greater good’ and the purpose of living is to ‘live forever.’ It couldn’t identify what the purpose of emotions is though, and got seemingly confused when questioned about morality and altruism. For example, it said that having a child is immoral and that the definition of altruism is ‘if you don’t believe in God then you don’t know.’ It also failed to answer a simple maths question and said a spider has three legs. ‘Conversational modeling is an important task in natural language understanding and machine intelligence,’ explained the researchers in their paper, A Neural Conversational Model. ‘Although previous approaches exist, they are often restricted to specific domains (eg booking an airline ticket) and require handcrafted rules. ‘In this paper, we present a simple approach for this task which uses the recently proposed sequence-to-sequence framework. ‘Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation.  ‘We find that this straightforward model can generate simple conversations given a large conversational training dataset.’ Earlier this month Google revealed a set of images to help explain how its systems learn over time.

Read Full Article Here

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s