[computer-go] an idea for a new measure of a computer go program's rank.

[Don Dailey]

On Fri, 2007-01-19 at 01:12 +0100, dave.devos at planet.nl wrote:
> In my opinion lowering the time limit just forces players (human and 
> computer) towards random play. 

It's a useful and meaningful experiment, but it can't be accurately
performed at meaningfully fast levels.   The human interface is
rather like network lag in on-line games.   A really fast game
could not be very meaningful as a result.   A human player can 
think of his move about 10 times faster than physically making it.  

At fast time controls your hand-eye coordination is an issue,
a younger player with better hand-eye coordination might have
a significant advantage over an older but stronger player. 


- Don
 


> I am sure there exists a time limit 
> where a random playing program can beat Lee Chang-Ho 50% of the time. 
> But what is the use of that? To me it sounds like an invention to be 
> able to show some progress in computer go, even if programs don't 
> become very much stronger over the years: at least they will become 
> quicker :) 



> Dave