Re: Go program strength

[Tim Hunt <T.J.Hunt@xxxxxxxxxxxxxxx>]

On Tue, 9 Feb 1999 rbrown@xxxxxxxxxxxxxxxxx wrote:

> Nick Wedd <nick@xxxxxxxxxxxxxxxxx> writes:
> 
> > Tim Hunt <T.J.Hunt@xxxxxxxxxxxxxxxxx> writes
> > 
> > >There is also the theory that since the Computer Ing Cup and simmilar
> > >events are the main testing ground for go programs, the programs are
> > >designed to perform well there, rather than against humans. What do people
> > >here think about that? Is it just slander, or is there some truth in it?
> > 
> > I think that there is truth in this.
> 
> Me too.
> 
> Tim, I have to ask, why did you choose the word "slander"?

It is always better to flame yourself rather than waiting for someone else
to do it :-) I didn't use the word seriously, I just wanted people to
realise I knew that my remarks were potentially a bit rude, when many
people on this list have spent many hour developing their go programs and
I only have a theoretical interest in the subject.

I suppose that the point is that if you want to test and tune your go
program then it is good to be able to set it up to play 1,000 games
against some other program and adjust its internal parameters to try
and maximise its winning percentage. Then you go and have a cup of
coffee (or week off, however long it takes) then come back and have a look
at the results. You are never going to find a human who has the patience
to do that much testing. 

Tim.

            ..  ..      ..  ..                  ..  ..      ..  ..
Tim Hunt, 63 Panton Street, Cambridge, CB2 1HL, UK.  Tel +44 1223 500769
   or     DAMTP, Silver Street, Cambridge, CB3 9EW, UK.
            ..  ..      ..  ..                  ..  ..      ..  ..