On 07/24/2010 12:47 PM, Raymond Wold wrote:
Any challenge demonstrating the program's skill (such as John Tromp's bet) can be called into question in either direction, with speculation on whether the opponent knows of the flaw(s) or not. The game turns into something not go, but rather "do you know this program or not?" I am more interested in the game of go.
To say this isn't Go is ridiculous, and shows your own bias and intellectual dishonesty, even if you now regret putting these phrases into play.
I'll raise again my argument which you haven't responded to: "10 years ago the idea that a computer program would win this bet, even without allowing any kind of sparring, would be laughable." In 1997, John had no problems with not being able to probe the program in advance. It was actually part of the original bet: "2.It need not be the commercially available version (to prevent you learning weaknesses)."
Clearly programs have improved since then. This wouldn't even be under debate if there wasn't at least a reasonable chance that the computer would win. Does this one bet provide a "true" rating for the bot? No! But it is interesting, even if the program has weaknesses that could be exploited with repeated play.
_______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
