by Grania
There’s an entertaining article over on CNET about an actual conversation between a human (and an annoying one at that) and a Google computer program. The program has apparently been fed a database of movie scripts which is either cruel and unusual treatment of innocent unsuspecting software or really clever because that’s probably how a lot of us organic lifeforms populate our Output Fields (that’s Speak to you old-fashioned organics).
You can take a look at the paper yourself here: A Neural Conversational Model
The Machine has some brilliant one-liners, and is possibly laughing at us. Make that probably laughing at us. Snarky bastard.
For example:
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 . (Is it just me or does that sound a little like a threat?)
Being damned scary (if you think of it):
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 .
Or getting testy about philosophy, and children:
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 . (Take that, Organic Life Forms)
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 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 .
Then The Machine appears to get sulky. Admittedly, by this stage I would have wanted to kick the Human too.
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 how i ’m not in the mood for a philosophical debate .
Human: what do you like to talk about ?
Machine: nothing .
You’re not the boss of me either. But someone needs to ask CleverBot about the Ineffable Ground of Being.
“The cake is a lie!”
There is probably no good reason why machines cannot have a conciousness and I assume they get there eventually. But will skeptics accept it, when they converse with one? And what do we do with such “lifeforms”? All sorts of moral questions will emerge, and some might have scary answers. What I find more worrisome is that apparently a situation can exist where everyone thinks the development would be a bad idea (I think AI isn’t necessarily), yet we would still do it. That’s the old dilemma discussed in Dürrenmatt’s “The Physicists”.
For anyone interested in the subject of having conversations with computers, I recommend the book The Most Human Human by Brian Christian.
Every year, an organization runs a ‘Turing test’ where a panel of people have typed conversations with 20-30 screens; feeding those screens can be either computer programs or other people, and the panel has to guess which they are talking to. At the end, the organization gives two prizes: one for the most human computer (i.e., the program that fooled the most panelists) and one for the most human human (i.e., the human that was correctly identified as human the most). The author of the book learns about this competition, and sets out to (a) participate, and (b) win the most human human award, by studying the computer programs that have done well as well as what past participants did to win that award.
Does he win it? You’ll have to read to find out. 🙂
Seems like Google still can’t do any better than Eliza, even after all these years.
b&
This is a spectacular Turing test flunk. Bad machine! no biscuit!
I don’t know, if someone told me this was a submission to the iamverysmart subreddit, I’d probably believe it was a real person. It’s amazing what some people write.
Except this machine wasn’t trying to pretend to be human, it was being a sullen, petulant machine; thank you very much.
~Grania
That is why the pill was red.
“Ergo, some of my answers you will understand, and some of them you will not.”
How could they pass up the opportunity to ask it:
What is your name?
What is your quest?
What is the maximum airspeed velocity of an unladen swallow?
European or African?
Just in time for the new Terminator movie. Since life always find a way to be ironic, I do not like how this is setting up.
Love the sudden outburst, “You’re not a cop!”