Daniel Lepage on Thu, 21 Jun 2007 09:58:25 -0700 (MST)

[Date Prev] [Date Next] [Thread Prev] [Thread Next] [Date Index] [Thread Index]

Re: [s-d] [s-b] Oracle report

> As a Game Action, and with the utmost respect for Priest Wonko, I
> submit the Claim that Priest Wonko's ruling on Consultation #12 is
> inconsistent for the reasoning specified in my ruling of Consultation
> #11. It is apparent that Priest Wonko is exercising judicial activism
> (or would it be cardinal activism?) in redefining the specified phrase
> to fit the meaning he believes it intends, instead of the meaning it
> clearly states.

My response and defense:

My ruling does not redefine the phrase "Turing test". This phrase  
does not, as you say, refer to any test that attempts to distinguish  
between a human and non-human. It instead refers to a specific test  
where a human attempts to distinguish between another human and a  

Wikipedia's definition reads:
The Turing test is a proposal for a test of a machine's capability to  
perform human-like conversation. Described by Alan Turing in the 1950  
paper "Computing machinery and intelligence", it proceeds as follows:  
a human judge engages in a natural language conversation with two  
other parties, one a human and the other a machine; if the judge  
cannot reliably tell which is which, then the machine is said to pass  
the test. It is assumed that both the human and the machine try to  
appear human.

Many similar definitions are available online.

According to this definition, throwing a monkey and a rock off a  
cliff is NOT a Turing test. Nor is communicating with a rock and  
monkey to try and tell which is which. A Turing Test is precisely the  
case when a human judge attempts to distinguish between a computer  
and a human. A society is therefore NOT capable of passing a turing  
test, simply because the phrase "Turing test" does not include any  
test that can be performed on a society.


spoon-discuss mailing list