[computer-go] an idea for a new measure of a computer go
program's rank.
Don Dailey
drd at mit.edu
Sun Jan 21 18:43:43 PST 2007
On Sun, 2007-01-21 at 15:50 -0800, steve uurtamo wrote:
> > > If you guys are correct thinking the nature of the game is such
> that
> > > humans cannot improve with time, then the computers will pull
> > > ahead more and more at longer time controls.
>
> let's adjust this to avoid the strawman and say that the
> counter-argument
> is that humans cannot improve much with significantly more time.
Computer DO improve with thinking time - so this is obviously not about
that,
the question is indeed whether humans follow this same basic pattern of
improving "almost" linearly with each time doubling.
- Don
More information about the computer-go
mailing list