Re: Turing test

[Vincent Diepeveen <diep@xxxxxxxxx>]

At 10:59 AM 5/26/98 +0200, you wrote:
>> a game record between a person and a computer program.
>
>I shall assume that it is true that one color is a human, the
>other a program.
>
>> Now which is which, and why?
>
>Both colors are very inconsistent as to their playing levels.
>They create moves of the ingenious intuition type as well as
>horrible blunders. I would like to vote for "made up problem".
>But what if not? Then I have to conclude that according to
>Turing's definition the program IS intelligent! Seems we need
>to improve that definition or our intelligence...

It's not exactly true to conclude that it is intelligent.
That would be rather inconsistent based on one game.

One game is not representing. We need more games.
Also when playing a weak human, especially beginners, then you cannot
conclude a thing from it, because in contradiction to experienced players
beginners simply lack lots of knowledge, and therefore could be just as
'intelligent' as the program. Also beginners play very inconsistent. 

I've passed this experiment already myself in computer chess.
At the internet chess server i play regurarly people (guests) who don't
carry a name. I picked all computers out of it within 3 quick games.
Some of the programs i could even name.

This is because i'm playing at say 7 dan or so for chess. So recognizing
that you play a computer becomes more easy when you play it against 
stronger humans. Stronger humans are terribly well in predicting each other,
because they have this huge amount patterns, and the less knowledgeable
your opponent the easier you see whether its a computer.

On the other hand, sometimes i play a human grandmaster or international
master and if they're very young, they sometimes like to behave more like a
computer
than a human (picking all my pawns because they see tactics way further).

So let it play against an older go player and within few games you pick
the computer out of it.

A reason why you can pick the computer out of it is because unlike mankind
they're very bad in learning. So even if a computer would perform at the
same level like a human and would play the same moves, even then you can
pick it out after a few games.

So if it passes the test, then it doesn't pass the 'endurance test'.

Greetings,
Vincent

>-- 
>robert jasiek
>http://www.snafu.de/~jasiek/
>
>