CCRL - Supports clones and illegal engines ?

[Uri Blass]

Again, I'm thinking i'm talking about the truth, because ELO points are the most importent factor for a ratinglist if engines going to be tested/listed or not.

Best,
Daniel

Have you seen the extensive list of amateur engines that we test?
I don't think you're being fair with that statement.

Regards, Graham.

Well Graham, that's a nice trick as well.
Of course many amateur are tested by the CCRL. But that's not the point. The point is that top engines are always interesting and basicly that's okay and i would prefer to test such engines as well. So, basicly there is a very high interest by the tester to test Strelka of course and that makes it difficult if problems comes up like in this case.

Best,
Daniel

BTW, I'm happy already that we have a open talk and that shows me that the CCRL is open for arguments.

testers are free to test the programs that they like to test and I think that it is better if programmers do not complain about their decisions because it is not productive.

Testers have the right not to publish their results if they continue to get responses like your response and they may simply do it.

I do not see how it is going to help programmers because testers will not test other engines instead of strelka but simply not publish their results and programmers are not going to get more games for their engines but less games because they will not get the games of their engines against strelka.

Uri

[Graham Banks]

Vas needs to say something. Until then, the axiom "innocent until proven guilty" should apply.

Regards, Graham.

Graham, this won't work with Vas and you know that. You know no new proofs will come. No court decision will be done, it never happend in the whole history of computerchess.

I believe all these points are well known for you, but you're hiding behind it.

Best,
Daniel

These are the posts I can find by Vas on the Rybka forum regarding Strelka:

Ok, obviously, the author deliberately did some things that will make us think that this is a Rybka clone.

I have no idea how it was done or why - maybe as a joke?! I don't know if it's legal, or even in fact what should be legal. And in fact I don't really care - this Rybka 1.0 is ancient. If somebody wants to have some fun with this version, knock yourself out.

Vas

Hi,

I got quite a few emails about this. Let me clarify a few points:

1) There is no doubt in my mind that the similarities (in executables and in output) between Rybka 1.0 and Strelka 1.8 are not a coincidence. This is in contrast to Strelka 1.0, where the similarities didn't seem to me to be excessive.

2) I have no idea how this was achieved. Whether something 'wrong' was done, whether Strelka author is just making fun of me and Rybka, whether Strelka 1.8 should be tested by CEGT, CCRL, etc - these are deeper questions. I am 100% sure that nobody has gotten a hold of my source code - this stays on just one machine which is not connected to the internet. This has been the case since well before Rybka 1.0.

3) This Strelka release does not bother me personally, partly because I don't really know what was done, but mainly because these similarities are with Rybka 1.0, which is ancient, incomplete, prototype-level code. If the similarities were with Rybka 2.3.2a, and if the playing-strength was on par with Rybka 2.3.2a, then Convekta would need to investigate this and consider their options.

4) From the point of view of the computer chess community, this is an issue which is in my view worth investigating. I'd like to thank the guys who have contributed to this - it is important. Writing something of Strelka 1.8 strength is a significant effort which requires multiple thousand man hours of development and testing. In light of this, we should have a procedure which is fair to the Strelka author and also fair to other aspiring engine authors. It's good to have an environment which is conducive to productive contributions from everybody.

Vas

Note that this explanation is itself bogus:

a) 'Osipov' claims that he changed the Fruit board representation from mailbox to bitboard and got a 2x speedup in performance. This is simply a clueless comment, there would be no speedup of anywhere near this magnitude.
b) 'Osipov' claims to take only Rybka's eval and search, yet Strelka 1.8 uses Rybka's exact UCI output strings.
c) 'Osipov' claims that he added a Winboard parser (after date of Fruit 2.1 release) so that Strelka could play in Ridderkerk - another clueless comment.
d) ...

I will think a little bit about this. Maybe what I should do is get the Strelka 1.8 source code, claim it as my own, and release it under GPL.

With these anonymous cloners who risk nothing, and with current Rybka level, computer chess may be headed for some turbulence.

Vas

Regards, Graham.

[Tord Romstad]

Everyone should do an opinion if Strelka is a clone, illegal or legal.

What makes you believe the CCRL testers don't have opinions about this? The point is that they don't all have the same opinion. The CCRL is not some sort of authoritarian organization; it has always given its members considerable freedom in how to test, and in what engines to test. Some CCRL testers choose to test Strelka, and some choose not to test it.

It seems to me that what you want is not that everyone should have an opinion on whether Strelka is a clone, but that everyone (at least those who test for the CCRL) should share your opinion. Because opinions differ, even among people who know the case much better than you and me, this is too much to expect. Allowing each tester to make his own choice seems like the right approach.

I will ask the CCRL to be done a choice: Strelka or Homer, but not both engines in one list!

I hope this contribution will be readed by many other programmers and i want that they doing, in this case requesting and pushing, the same statement like me to the CCRL with the demand confront: Her engines or Strelka, but not both. Maybe this “pressure” will be help....

Trying to put "pressure" on the CCRL by means like this cannot possibly achieve anything good. When you find yourself in disagreement with someone about something which is very important to you, the best approach is always to try to explain them your point of view, and hope that they will arrive at the same conclusions as you. You cannot convince someone to change their opinions by using threats. Trying to do so can only result in conflicts and hostility.

Tord

[Alessandro Scotti]

testers are free to test the programs that they like to test and I think that it is better if programmers do not complain about their decisions because it is not productive.

Well said Uri, and I don't see how it's possible to object to this. Testers do what they do for passion and fun and it goes without saying they are free to test whatever engines they like (including clones, which it seems Strelka is not by the way).
Besides, it's just a game.

[Chuck Wilson]

Well said Tord, Uri, and all. CCRL appreciates your keen understanding. It doesn't seem like justice to force the testing organizations to take an official stance that coincides with certain individuals' "popular" opinion.

The first rule of valid testing is to maintain objectivity.

[Daniel Mehrmann]

Again, I'm thinking i'm talking about the truth, because ELO points are the most importent factor for a ratinglist if engines going to be tested/listed or not.

Best,
Daniel

Have you seen the extensive list of amateur engines that we test?
I don't think you're being fair with that statement.

Regards, Graham.

Well Graham, that's a nice trick as well.
Of course many amateur are tested by the CCRL. But that's not the point. The point is that top engines are always interesting and basicly that's okay and i would prefer to test such engines as well. So, basicly there is a very high interest by the tester to test Strelka of course and that makes it difficult if problems comes up like in this case.

Best,
Daniel

BTW, I'm happy already that we have a open talk and that shows me that the CCRL is open for arguments.

testers are free to test the programs that they like to test and I think that it is better if programmers do not complain about their decisions because it is not productive.

Testers have the right not to publish their results if they continue to get responses like your response and they may simply do it.

I do not see how it is going to help programmers because testers will not test other engines instead of strelka but simply not publish their results and programmers are not going to get more games for their engines but less games because they will not get the games of their engines against strelka.

Uri

You're trying to show that i'm the "bad" guy here, because i don't want have Strelka listed. Futhermore you think that would blocking the testing in some ways ?!
I don't think so. CCRL will do what they want to do anyway, with or without me. I just trying, that some people of the CCRL, who wants testing Strelka, rethink about the views.

Besides of this general attack, with no arguments, of me, do you have real arguments for me in the Strelka case or just some hot air ?

Do you think about the future of computerchess already ?

Best,
Daniel

[Martin Thoresen]

To be honest I feel very unhappy to read a thread like this after all the effort CCRL put in every day, just to get something like this in our face.

The testers test the engines they like, nothing more, nothing less. I am one of those testers who won't test Strelka. Other people test it. That's the way it is.

If you (Daniel) is going to come here and tell us what to do and threaten with this and that, I'm feeling that the computerchess society has fallen.

You show a total lack of respect for CCRL and what we stand for. Obviously you aren't even aware of the man-hours we put into this project.

It's sad.

[Daniel Mehrmann]

Vas needs to say something. Until then, the axiom "innocent until proven guilty" should apply.

Regards, Graham.

Graham, this won't work with Vas and you know that. You know no new proofs will come. No court decision will be done, it never happend in the whole history of computerchess.

I believe all these points are well known for you, but you're hiding behind it.

Best,
Daniel

These are the posts I can find by Vas on the Rybka forum regarding Strelka:

I know these statements already.
It says nothing, because Vas must say that, because his engine was attacked. He can't agree this boy during this guy attacked Rybka and Vas himself. If he would agree, only in some points or just one point,Rybka himself would run in problems of course. But i said that in some previous postings already. So, these are no arguments.

Best,
Daniel

[Daniel Mehrmann]

Everyone should do an opinion if Strelka is a clone, illegal or legal.

What makes you believe the CCRL testers don't have opinions about this? The point is that they don't all have the same opinion. The CCRL is not some sort of authoritarian organization; it has always given its members considerable freedom in how to test, and in what engines to test. Some CCRL testers choose to test Strelka, and some choose not to test it.

It seems to me that what you want is not that everyone should have an opinion on whether Strelka is a clone, but that everyone (at least those who test for the CCRL) should share your opinion. Because opinions differ, even among people who know the case much better than you and me, this is too much to expect. Allowing each tester to make his own choice seems like the right approach.

Tord, i think you misunderstood me. Of course some CCRL people like to test Strelka and some CCRL tester dislike testing Strelka. They have different meanings.
But this is not the point. The point is that Strelka is still listed and the public result of this listing for me, is that the CCRL accept Strelka of global ways.
So, i don't know what was going on in this group internal, it doesn't count anyway, but the public statement is, we're going to test Strelka in any ways. You can't pursue the ways of each CCRL tester. However, the public statement has the weight, not a single tester and this statement looks as it look.


Best,
Daniel

[Steve B]

Vas needs to say something. Until then, the axiom "innocent until proven guilty" should apply.

Regards, Graham.

Graham, this won't work with Vas and you know that. You know no new proofs will come. No court decision will be done, it never happend in the whole history of computerchess.

I believe all these points are well known for you, but you're hiding behind it.

Best,
Daniel

These are the posts I can find by Vas on the Rybka forum regarding Strelka:

I know these statements already.
It says nothing, because Vas must say that, because his engine was attacked. He can't agree this boy during this guy attacked Rybka and Vas himself. If he would agree, only in some points or just one point,Rybka himself would run in problems of course. But i said that in some previous postings already. So, these are no arguments.

Best,
Daniel

HI Daniel

as far as i know there are TWO major testing teams(not counting the SSDF)
The CCRL and the CEGT

do you know if the CEGT is testing Strelka and if not can you say why not?

if they are testing Strelka can i ask you why do you single out the CCRL for your objections?

Best Regards
Steve