Author: Rolf Tueschen
Date: 16:14:56 06/13/04
Go up one level in this thread
On June 13, 2004 at 09:51:07, Mike S. wrote: >On June 12, 2004 at 21:50:04, Rolf Tueschen wrote: > >>On June 12, 2004 at 19:43:27, Mike S. wrote: >> >>>(...) > >>Now if you repeat only one time such a nonsense about Bob in CSS, you get no >>more response from me. You want to doubt that his "opinion" is correct, that >>Stellungstests are not able to make Elo ratings for computerchess programs??? > >I never have claimed that testsuites can produce true Elo ratings like they >evolve from game competition! And I have never said that I have it from Country Joe MacDonald that a test is causing depressions. Where do you have this from? Please do not insinuate such things into our serious debate. But seriously - What YOU have claimed is of almost no interest for the question here. I'm talking about the presentation of data by Gurevich&Meiler. > Actually I don't know anybody who claims this. Nobody gives a ranking place with an Elo like number ?? Nobody? Please prove it. >I >cannot understand why people are adressing *me* as if I would claim that. LOL. As your Dr. Freud let me explain this to you. Perhaps it is because you are always speaking so much in defense of the CSS test and Dr. Gurevich in person? Tell me what you feel when you are acting as a CSS spin doctor to tell the people what they should think? >What >is this based upon?? I don't say this, the WM-Test staff doesn't say this >either. Testsuites produce *test ratings*. Yes, Mike, that's my point!!! These ratings with exact "numbers". That's it what it's based upon. > Often, people use only the number of >solutions to compare the engine's performances, or that and the time usage is >"somehow" combined in a reasonable formula, to allow comparisons between the >engines. - That's it; I see no big secret and no problem whatsoever. I don't either. But the point is that such a doing is nonsense and it simply doesn't WORK. [Robert Hyatt!] > >Take a look at my own test, [.... nope, please concentration on the CSS test! Not your test.] >That was NEVER my point!! I was ONLY talking about the test condition of stable >solutions, now. This really stinks! This is the CSS-Test, Mike, sorry. >One point of the critizism is proven >invalid, so you and H. simply skip it and come up with the Elo like ratings. I'm >not interested in that sub topic. I know that testuites cannot produce true FIDE >or SSDF Elos. You mean, SSDF can create real Elos?? > I'm not defending "Test Elos" (although, there indeed exists >something which really deserves that name; see below). > Please calculate the Elo of UFOs, Mike, because they at least do exist! But test Elos don't exist. >>But the whole work of Gurevich&Meiler is >>only reasonable in its limited design, if they pretend to get a valuable result. >>They give typical Elo ratings. But you want to imply that nobody NEVER presented >>such numbers. Nonsense! Of course they did it. > >They just *called* it Elo, or Test-Elo. Doesn't anybody notice anyway, that >these numbers aren't game-based? So what? ROTFL Mikey. You mean I should take these guys of the CSS test for serious when they are talking about Test-Elo? You mean it's as if I'm looking into the Moon and after your'e telling me that I saw a green cheese, then I should obey to you as my spin doctor? > >Ok - the word, or name, "Elo" may have been used in a wrong place. But that is >not a very scientific argument against the test method, quality, importance and >interpretability of the results :-)) because *all these remain just the same*, >no matter if the ratings are called > >"Elo," >"Test-Elo," >"Testrating," or >"Schakiquaki Numbers"... > >It remains the same test, the same method, the same positions and the same >validity of the engines performance comparisons no matter how you call it. So >that critizism is simply ridiculous and I feel mucked. You have no reason to feel this way. You should better apologize for the support by CSS for such a flawed test! This test simply doesn't work. [Robert Hyatt] And you have the guts to teach me how I should react if the test authors are talking about test Elo?? I should obey to you and simply forgetting what they are talking about? I am your personal Dr. Freud, Mike. You cannot tell me what I should think about you and this CSS test. > >Btw. I being told that the WM-Test ratings calculated with the original formula, >aren't called Test-Elo anymore (but ...Rating). But Michael Gurevich is still calling himself Gurevich or what? You mean they are quickly changing the name of something and then they are hoping that their methodology could be accepted? Nope, that won't fly! Rejected, Mike. Please, next proposal! [...] >(Actually CSS is *never* treated >fair in CCC, but that's nothing new. Play your games without me in the >future...) > >I guess I'm leaving now, finally (probably I'll check back once or twice to read >replies, only). > >Regards, >M.Scheidl Somewhere else in CCC I wrote an urgent appeal to Bob Hyatt to let science a bit out of computerchess, so that it could be a bit more fair for the German CSS. Bob hasn't answered yet. Perhaps he will obey and re-define scientifical basics. Who knows - he is free to do so!! Since he's the expert number one. Let's wait patiently, Mike. Perhaps you are lucky and Bob states that you could become senior chief of ChessBase or MicroSoft. Who knows what Bob has in his sleeves again...
This page took 0 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.