Author: Ratko V Tomic
Date: 09:02:21 07/28/00
Go up one level in this thread
> There is no substitute for an objective assessment using a > large number games against a _variety_ of players. You make valid points about bias due to playing styles and holes in the knowledge/skill. But that still doesn't invalidate the point, you were supposedly arguing against, that from the small number of games a good human player will extract much better judgment about the player's strength than the mechanical rating calculator. After all, in your game example, you knew after a single game what the weaknesses and strengths of your opponent were and you rated his strengths in different phases. Yet the mechanical rating calculation from a single game (or even a handfiul of games) is useless. Similarly, if you analyze and think through a game against some new program, even after a single serious game you will have a fairly good sense on how strong it may be. At least against you. But the exactly same caveat 'strength only against you' applies to the rating calculator, too. The key difference is that after a single or a few games you'll be able to predict the future scores of the program 'against you' much better than the mechanical rating calculator. You have extracted much more info out of a small number of games than the rating calculator which counts only the final score. In conclusion, it is either out of malice or the blissful ignorance (or even malicious ignorance) that some folks ridicule Thorsten (and others) for making claims about the program strengths which would clearly be unfounded if one were merely calculating the ratings from the same small number of games.
This page took 0.01 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.