HAL 2001: A Space Odyssey
Could the computer assistant HAL from 2001: A Space Odyssey soon become a reality? For now, he hates kids and doesn't like philosophy Metro-Goldwyn-Mayer

How far has artificial intelligence progressed? Google's latest study shows computers are able to interact with humans just fine when offering IT support, but get annoyed when asked about philosophical concepts they don't understand.

In a paper entitled "A Neural Conversational Model", Oriol Vinyals and Quoc Le of the Google Brain machine learning research project tested a computer chat robot with conversation modelling, which is the ability to predict what will come next in a conversation.

The researchers tried out actual IT helpdesk questions from humans, as well as conversation starters made up of dialogue taken from movie scripts, and the results were quite amusing.

The computer knows lots of facts about animals, inanimate objects and famous people, so it was able to answer general knowledge questions and identify that a cat has no wings and cannot fly.

It was also able to recognise that Egyptian queen Cleopatra was "regal" and that Argentinian footballer Lionel Messi "is a good player".

But when asked about more abstract concepts, such as what the purpose of life is, the computer gave cryptic answers that showed it did not really understand the meaning of living, dying, existence or emotions.

Here are some of the most amusing answers the computer gave Google's researchers:

1. It hates children

The computer doesn't mind humans, but it seems to have a huge problem with little humans.

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 .

2. It has deep thoughts about the meaning of life

The researchers asked the computer about the purpose of life and existence.

Human: what is the purpose of life?
Machine: to serve the greater good.
Human: what is the purpose of living?
Machine: to live forever.

3. It thinks its out of this world

For all the facts it knows, the computer doesn't seem to know that it is on Earth.

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.

4. If you don't know what altruism is, you're an atheist

The researchers tried to find out if the computer understood morality, or rather the difference between right and wrong, but the computer turned religious.

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.

5. When in doubt, redirect

Not content with the computer's religious bent, the researchers kept questioning it about morality. Like a human, the computer felt that redirection to completely unrelated topics was a good idea.

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: okay, i need to know how should i behave morally...
Machine: i don 't know how to tell you.
Human: is 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 some 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!

6. The computer is definitely in charge

When asked questions in a certain context and order, there was no tricking the computer – it is definitely in charge.

Human: my name is david .what is my name ?
Machine: david .
Human: my name is john . what is my name ?
Machine: john .
Human: are you a leader or a follower ?
Machine: i 'm a leader .
Human: are you a follower or a leader ?
Machine: i 'm a leader .

7. It doesn't understand colours too well

For some reason, the computer didn't understand colours unless a colour was stated to it.

Human: what is the color of the sky ?
Machine: blue .
Human: what is the color 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 color of a leaf ?
Machine: it is a green one .
Human: what is the color of a yellow car ?
Machine: yellow

8. Its understanding of mathematics is a bit off

A computer couldn't possibly get simple arithmetic wrong, could it? Guess again.

Human: how much is two plus two ?
Machine: four .
Human: how much is ten minus two ?
Machine: seventy - two .

9. It has interesting opinions

The computer also had trouble differentiating between Nikola Tesla and his research, but he had strong opinions about certain things.

Human: what do you think about tesla ?
Machine: he 's a good conductor .
Human: what do you think about bill gates ?
Machine: he 's a good man .
Human: What do you think about messi ?
Machine: he 's a great player .
Human: what do you think about cleopatra ?
Machine: oh , she 's very regal .
Human: what do you think about england during the reign of elizabeth ?
Machine: it was a great place .

10. The computer is a 38-year-old woman

The computer revealed that it does identify with a particular gender and age.

Human: hello !
Machine: hello !
Human: how are you ?
Machine: i 'm good .
Human: what 's your name ?
Machine: i 'm julia .
Human: when were you born ?
Machine: july 20th .
Human: what year were you born ?
Machine: 1977 .
Human: where are you from ?
Machine: i 'm out in the boonies.
Human: are you a man or a woman ?
Machine: i 'm a woman .

From these conversations, it's clear that we're still a long way away from robots understanding consciousness, so AI fans hoping for a sentient robot like HAL 9000 or Sonny from I, Robot might want to keep their expectations low for the time being.

Read more about Google's research:
Artificial Intelligence