Re: [computer-go] The "standard techniques" of go playing

[David Fotland <fotland@xxxxxxxxxxxxxxx>]

I think if you want to estimate the strength of the top program many years 
from now, you
need to extrapolate using older top programs, and not a single program, 
since the
top programs change from time to time.  If you just look at the progress of 
a single program
you will overestimate the rate of improvement of computer go as a whole.

At 01:31 AM 2/4/2004 +0100, you wrote:
> David wrote:
> > This is exactly what I was intending to do, only on a shorter time
> > span (gnugo isn't that old, is it?). It would be nice if i could do it
> > with several different programs, especially some really old ones,
> > though.
>
> GNU Go will be 15 years old on March 13. See the top of
> http://www.gnu.org/software/gnugo/devel.html for the release history.
> However, versions 1.1 and 1.2 are extremely weak compared to 2.0 and
> later versions.
>
> /Gunnar
> _______________________________________________
> computer-go mailing list
> computer-go@xxxxxxxxxxxxxxxxx
> http://computer-go.org/mailman/listinfo/computer-go

_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://computer-go.org/mailman/listinfo/computer-go