The Turing test has been
passed by a robot named Eugene. It may be time to pledge fealty to the machines
http://www.theguardian.com/technology/2014/jun/09/what-is-the-alan-turing-test
Programmers worldwide are
preparing to welcome our new robot overlords, after the University of Reading
reported on Sunday that a computer
had passed the Turing test for the first time.
But what is the test? And
why could it spell doom for us all?
The Turing Test?
Coined by computing pioneer
Alan Turing in 1950, the Turing test was designed to be a rudimentary way
of determining whether or not a computer counts as "intelligent".
The test, as Turing designed
it, is carried out as a sort of imitation game. On one side of a computer
screen sits a human judge, whose job is to chat to some mysterious
interlocutors on the other side. Most of those interlocutors will be humans;
one will be a chatbot, created for the sole purpose of tricking the judge into
thinking that it is the real human.
On Sunday, for the first
time in history, a machine succeeded in that goal.
Or a Turing test?
But it might be better to
say that the chatbot, a Russian-designed programme called Eugene, passed a Turing
test. Alan Turing's 1950 paper laid out the general idea of the test, and also
laid out some specifics which he thought would be passed "in about 50
years' time": each judge has just five minutes to talk to each machine,
and the machines passed if more than 30% of the judges thought that they were
human. Those somewhat arbitrary, if historically faithful, rules were the ones
followed by the University of Reading.
It remains impressive that
Eugene had 33% of the judges "he" spoke to convinced of his humanity,
but the robots still have a long way to go to pass the gold standard of modern
Turing tests, using rules laid out in 1990 by the inventor Hugh Loebner. Those rules call for
the computer and a human to have a 25-minute conversation with each of four
separate judges. The machine only wins if it fools at least half the judges
into thinking it's the human (though every year there is a "bronze
medal" awarded to the machine that convinces the most judges).
The hardest Turing test
described so far is one set up as part of a $20,000 bet between the
futurologist Ray Kurzweil and the Lotus founder, Mitch Kapor. Kapor bet that no
robot would pass the test before 2029, and the rules call for
the challenger and three human foils to have two-hour conversations with each
of three judges. The robot must convince two of the three judges that it is
human, and be ranked as "more human" on average than at least two of
the actual human competitors.
How do the robots win?
Turing test competitions
have been held for more than 20 years, and the strategies the robots employ
have changed over time. Where originally the stumbling blocks were simply
understanding the questions asked by the judges, now the bigger challenge is in
answering them in a human-like manner. In recent years, winners have started
changing the subject, asking questions of the judges, and simulating moods and
typos.
The big breakthrough behind
Eugene, the University of Reading's winner, was in giving the robot the persona
of a 13-year-old boy. "Our main idea was that [Eugene] can claim that he
knows anything, but his age also makes it perfectly reasonable that he doesn't
know everything," said the robot's creator, Vladimir Veselov. It also
makes affectations like misspellings look more plausible than they would coming
from an "adult".
What does a conversation
with Eugene look like?
Here's the transcript of a 2012
conversation with a judge which resulted in them picking Eugene over
the human interlocutor on the other side of the screen:
[16:11:25] Judge: what music
do you like?
[16:11:32] Eugene: I like
Eminem – because he doesn't have a thing to do with
"polite-correctness".
[16:11:46] Judge: OMG i love
eminem, he's my favourite artist!
[16:12:00] Eugene: I wonder
what Eminem's nick mean. I associate it only with a word "enema". But
he is a cool guy, I like his "The Real Slim Shady".
[16:12:55] Judge: i know
what his nick name means, his real name is Marshall Mathers. From the initials
M&M phynetically sounding like Eminem.
[16:13:06] Eugene: Eminem is
a famous crapper. No, raper... ripper... Yeah, I mean - rapper. I like his
"Stan" and "The Real Slim Shady".
[16:13:32] Judge: I like
"Hailies song"
[16:13:46] Eugene:
Interesting tastes. I like science fiction books, by the way. Where do you came
from, by the way? Could you tell me about the place where you live?
[16:14:22] Judge: Epsom,
home of the derby. yourself?
[16:14:27] Eugene: My guinea
pig says that name Derby sounds very nice.
[16:14:41] Judge: i shopuld
talk with him sometime
[16:14:48] Eugene: I think
you should take some typing lessons. Or just type more accurately.
[16:15:04] Judge: that's
very rude?
[16:15:09] Eugene: Ummm...
Frankly, I didn't get your question:-(
[16:15:49] Judge:
"Ummm" isnt a word. i think you need typing lessons
[16:15:58] Eugene: My
thoughts are same. By the way, I still don't know your specialty - or,
possibly, I've missed it?
At the time, Eugene passed
28% of such conversations. Two years on, that extra 5% has made all the
difference.
Is it time to pledge
allegiance to our new robot overlords?
Probably not. For one thing,
winning a competition by pretending to be a child with gaping holes in their
knowledge does not exactly reinforce the idea that machines are something to be
scared of.
But moreover, chatbots are a
fairly limited application of the sort of artificial intelligence which
science-fiction authors have been imagining for decades. By having to pretend
to be human, they are prevented from being more than human.
They still offer new
problems and possibilities for the future, from automatic scambots which carry
out phishing attacks to customer support algorithms that don't need to reveal
that they aren't actually a person.
But really, these machines
say more about us than them. "You don’t write a program, you write a
novel," explain Eugene's creators. "You think up a life for your
character from scratch – starting with childhood – endowing him with opinions,
thoughts, fears, quirks." When the best way to pretend to be human is to imitate
our foibles and weaknesses as much as our strengths, the victors of Turing
tests will continue to be the least scary output of artificial intelligence
research.
No comments:
Post a Comment