Main Date: 06 Dec 2006 15:33:08 From: Chess One Subject: Human vs Machine Matches I would like to make a proposal, and discover your interest in two forms of Human v Machine matches - since I am sometimes approached by both sides to investigate possibilities. In conversations elsewhere [Rybka thread] there are discussions of fairness, so I propose two options; a) Human plus database, vs Computer b) Human vs Computers [look-ups = off] Simul. Which of these is more interesting to the chess community, and why? In the recent Kramnik Fritz engagement it was difficult to engage even the chess community's interest, so both these suggestions are deliberately different than that, since one aspect of arranging such matches is also to obtain mainstream media interest, and whatever Kramnik/Fritz was, did not! Is there a general sense of preference for either (a) or (b) ? Phil Innes   Date: From: Subject: Re: Turing Machines     Date: 16 Jan 2007 21:02:41 From: Chess One Subject: Re: Turing Machines <   Date: 13 Jan 2007 14:43:42 From: Wlodzimierz Holsztynski (Wlod) Subject: Re: Human vs Machine Matches Chess One wrote: > I would like to make a proposal, and discover your interest in two forms of > Human v Machine matches - since I am sometimes approached by both sides to > investigate possibilities. > > In conversations elsewhere [Rybka thread] there are discussions of fairness, > so I propose two options; > > a) Human plus database, vs Computer > > b) Human vs Computers [look-ups = off] Simul. -- It should be mano o' mano (one on one). -- Classical time limit. -- during the game the computer MUST go to bathroom minimum four times. -- the bathroom must be checked for any hiding hired by IBM GMs Best regards, Wlod     Date: 13 Jan 2007 23:45:45 From: Chess One Subject: Re: Human vs Machine Matches "Wlodzimierz Holsztynski (Wlod)" <sennajawa@gmail.com > wrote in message news:1168728214.700193.161900@l53g2000cwa.googlegroups.com... > Chess One wrote: > >> I would like to make a proposal, and discover your interest in two forms >> of >> Human v Machine matches - since I am sometimes approached by both sides >> to >> investigate possibilities. >> >> In conversations elsewhere [Rybka thread] there are discussions of >> fairness, >> so I propose two options; >> >> a) Human plus database, vs Computer >> >> b) Human vs Computers [look-ups = off] Simul. > > -- It should be mano o' mano (one on one). > > -- Classical time limit. > > -- during the game the computer MUST go > to bathroom minimum four times. > > -- the bathroom must be checked for > any hiding hired by IBM GMs > > Best regards, think wireless and do not mention GM B! since he is not allowed to reply, and such is his contribution to chess computing ;) > Wlod >   Date: From: Martin Brown Subject: Re: Human vs Machine Matches     Date: 11 Jan 2007 16:35:30 From: Dr A. N. Walker Subject: Re: Human vs Machine Matches In article <1168513872.657481.224580@i39g2000hsf.googlegroups.com >, Martin Brown <   Date: From: Martin Brown Subject: Re: Human vs Machine Matches     Date: 20 Dec 2006 18:35:23 From: David Richerby Subject: Re: Human vs Machine Matches Martin Brown <   Date: 16 Dec 2006 19:21:27 From: help bot Subject: Re: Human vs Machine Matches Kenneth Sloan wrote: > >>> That is an arbitrary difference, given the fact that a human can use > >>> copies of opening books and endgame tablebases as well. > >>> > >> Humans use copies - that's illegal. > >> > >> computers don't use *copies* - so it's not. > > > > Misses the point. It makes no difference whether the > > opening "book" or reference material is an original or a > > copy -- none whatever. > On the contrary - it *is* the point. Is not! > This argument continues to be one of definition, Perhaps, for some. I imagine the anti-human types would prefer it that way, for example, because this way they can avoid facing the problem head-on. > and yet (at least) one > side of the argument insists on making arbitrary distinctions and then > pretending that these distinctions are "obvious". I noticed that, too. These anti-humans are soooo dishonest. > One might as well decide that a "computer" is simply a hunk of hardware, > and any data stored in it constitutes "notes" (or "reference material"). > In fact, some people seriously maintain that computers "cheat" by using > additional chess boards (internal memory patterns) or refer to recorded > versions of the chess rules (how the horsie moves), etc. The dreaded "slippery slope" technique! Well done. Your studies of rhetoric are finally coming to fruition here. > This seems to me to be based on an inferior understanding of what a > "computer" or a "computer program" *is*. Really? So then, rhetoricians like you are the only ones who can truly understand what a computer is? I see. > next, I expect the argument that the prohibition on eating at the board > means that only battery operated computers can play - or even worse, > that the battery constitutes food brought to the table by the computer. More slippery slope stuff. Is this the best you've got? > In some ways, this discussion *could* be about deep and fundamental > philosophical issues - but somehow it always seems to devolve into: > "humans do it in some essentially indivisible and unknown way - while > computers havae clearly delineated parts, some of which we can outlaw by > administrative fiat". This is a typical, pro-computer perspective on the issue. Personally, I don't want to take anything away from the computers. I see the progress over time in such a way that it was best for the humans to give computers every conceivable advantage in order to make things more interesting. Then, somewhere along the way we got to a point where these advantages were only needed against strong GMs, then only vs. world champion caliber humans. Now, we are to the point in this process where even the world champions are (barely) unable to keep up the pace, and as such, this would seem to be the ideal time to re-think the way in which the "rules" have evolved. I am not in agreement with those few, such as PI, who claim that sans opening book, computers are mere Class A players. On the contrary, if we were to make a change in the "rules", the programmers need *time* to re-think their programs, to make them able to analyze the openings on their own, for otherwise we risk the ready-made excuse that GMs, for example, are out-booking the computers and this is the only reason they can win. That scenario is precisely the opposite of what we see now, where the computers have a decided edge in terms of books -- on both ends of the game. (Well, even that depends on how much work has been put into them before the game.) Were I a skilled chess programmer, I would be more than willing to undertake the task of determining just how much advantage this difference in the current "rules" affords, for a variety of programs. But I must point out that *because* of it, programmers have had no motivation or need to put in the work required to do the openings right, so the current status in no way reflects on chess computers being "the best they can be". > It's a sophomoric, and ultimately boring > argument, which completely...what was your phrase? oh yes..."misses the > point". Your preference for sophomoric rhetoric in place of genuine discussion has been noted. Just don't delude yourself into thinking you are fooling anyone here. The real point of your classes was to inform you how *not* to become a victim. Instead, you have turned to evil, and now use this knowledge to your own, selfish ends, instead of fighting for Truth, Justice, and Humanity. Phooey on you! -- help bot   Date: 16 Dec 2006 18:32:23 From: help bot Subject: Re: Human vs Machine Matches MaximRecoil wrote: > > > The way I see it, > > > the matchup should be human vs. chess engine, and only what is > > > intrinsic to those two types of players should be able to be brought to > > > the table. > > > > This statement solves nothing; the anti-human types > > will simply have a different interpretation as to what is > > intrinsic to a computer. > > That's why I used the term "chess engine" rather than "computer". It is > hard to make a case that reference material is intrinsic to a chess > engine. What is there to stop the anti-human types from simply re-defining chess engine to include things that every car engine "needs", like a muffler, a fuel tank, some external memory, a huge disk drive, mounting bolts, a battery, and plenty of gas (electricity), and of course all the "necessary" software to control and aid the engine? > > > In order to constitute an unfair advantage, you would have to have a > > > case where one side is being allowed something that the other side is > > > not being allowed. There are no unfair advantages with a human vs. a > > > chess engine (there may be advantages for either side, just not unfair > > > ones). > > > > Rubbish. The current practice, or rules, prohibit > > only humans from accessing opening books and > > endgame tablebases during play, while at the same > > time *allowing* computers to do it. This is nothing > > short of discrimination against humans, which is > > what I call "unfair". Grossly unfair, in fact. > > I wasn't talking about the current practice (which I agree is unfair), > I was talking about a human vs. a chess engine (rather than a human vs. > a chess engine + reference material). Thanks for clearing that up. I had missed your subtle choice of words, and thought you were talking about chess computers in general. > > > Providing a computer with opening book is a case of allowing something > > > that the other side is not allowed, and as such, constitutes an unfair > > > advantage. > > > > Make up your mind. Are you one of THEM, or one > > of US? You can't have it both ways! > What do you mean? The anti-humans, man! Don't you get it? There is a WAR going on here. These guys want to keep us down. They are out to get us, and have crossed over to the other side -- to the ENEMY! Without these anti-human types, computers would have been defeated long ago. There is no middle ground here. You're either with us (humans), or against us. That's war. ; >D -- help bot   Date: 16 Dec 2006 07:05:07 From: MaximRecoil Subject: Re: Human vs Machine Matches help bot wrote: > MaximRecoil wrote: > The *ability* to memorize, by rote, some reference > material is an intrinsic part of a human chess player. > But not the reference material itself. That is as > external to a human as it is -- or should be -- to a > computer. I agree. > > The way I see it, > > the matchup should be human vs. chess engine, and only what is > > intrinsic to those two types of players should be able to be brought to > > the table. > > This statement solves nothing; the anti-human types > will simply have a different interpretation as to what is > intrinsic to a computer. That's why I used the term "chess engine" rather than "computer". It is hard to make a case that reference material is intrinsic to a chess engine. > > In order to constitute an unfair advantage, you would have to have a > > case where one side is being allowed something that the other side is > > not being allowed. There are no unfair advantages with a human vs. a > > chess engine (there may be advantages for either side, just not unfair > > ones). > > Rubbish. The current practice, or rules, prohibit > only humans from accessing opening books and > endgame tablebases during play, while at the same > time *allowing* computers to do it. This is nothing > short of discrimination against humans, which is > what I call "unfair". Grossly unfair, in fact. I wasn't talking about the current practice (which I agree is unfair), I was talking about a human vs. a chess engine (rather than a human vs. a chess engine + reference material). > > If they can figure out how to implement human memory into a > > chess engine, then fine. > > Nay! If they can figure out how to do that, and > combine it with a modern computer's amazing > speed and accuracy, there is no point in playing > them anymore, except against one another. > Does the term "suicide" have any meaning to > you? :>D Well that won't be any time soon. > > Providing a computer with opening book is a case of allowing something > > that the other side is not allowed, and as such, constitutes an unfair > > advantage. > > Make up your mind. Are you one of THEM, or one > of US? You can't have it both ways! What do you mean?   Date: 16 Dec 2006 14:34:26 From: Guy Macon Subject: Re: Human vs Machine Matches help bot wrote: > Yeah, yeah. The fact remains that even if the field >were leveled with regard to access to opening book(s) >during play, the computers will have a vast advantage >in terms of "access time" and infallible execution of >the appropriate book move in a given position. THAT >is intrinsic to computers. But not the inequality we >see in what is or is not allowed by current rules and >practice. The above clarifies what is and what is not "intrinsic" quite nicely. The fact hat a human accessing a book of openings is slower than a computer is really is intrinsic; no arbitrary rule prevents the human from going as fast as he is able. The argument that the book itself is intinsic in the case of a computer and not in the case of a human is flawed; humans have an intrinsic ability to read books just as computers have an intrinsic ability to read bits off of a hard-disk platter. Where is the fairness in a rule that denies the human the right to read his printed book but allows the computer to read "his" disk platter?   Date: 16 Dec 2006 00:36:16 From: help bot Subject: Re: Human vs Machine Matches MaximRecoil wrote: > help bot wrote: > > > As for the opening book, there you might be able to > > argue that taking away the program's book would lead > > to an unfair advantage, because strong human players > > have *some* opening book knowledge memorized by > > rote. > > It is true that humans can memorize some opening book knowledge but > that is an intrinsic part of a human chess player. The *ability* to memorize, by rote, some reference material is an intrinsic part of a human chess player. But not the reference material itself. That is as external to a human as it is -- or should be -- to a computer. > The way I see it, > the matchup should be human vs. chess engine, and only what is > intrinsic to those two types of players should be able to be brought to > the table. This statement solves nothing; the anti-human types will simply have a different interpretation as to what is intrinsic to a computer. I agree regarding the human vs. chess engine. Such a contest would be most interesting with the engine engaged from a dead stop; that is, without any "help" from outside sources pushing the car through the opening phase. Hybrid-electrics are fine for commuting around town, but have no place in a contest of skill. > Yes there are things that we can do that a chess engine > can't, but there are also things a chess engine can do that a human > can't (such as calculating millions of moves per second to an > outrageous ply depth that only increases as hardware improves). The > matchup of these intrinsic differences in approach to playing chess is > the whole point in the first place. Giving the computer a perfect copy > of opening book information is arbitrary, and could just as easily be > given to the human player. Right. The problem lies in the fact that one is allowed to access this kind of material, while the other is not. That is unfair as well as arbitrary. > In order to constitute an unfair advantage, you would have to have a > case where one side is being allowed something that the other side is > not being allowed. There are no unfair advantages with a human vs. a > chess engine (there may be advantages for either side, just not unfair > ones). Rubbish. The current practice, or rules, prohibit only humans from accessing opening books and endgame tablebases during play, while at the same time *allowing* computers to do it. This is nothing short of discrimination against humans, which is what I call "unfair". Grossly unfair, in fact. > If they can figure out how to implement human memory into a > chess engine, then fine. Nay! If they can figure out how to do that, and combine it with a modern computer's amazing speed and accuracy, there is no point in playing them anymore, except against one another. Does the term "suicide" have any meaning to you? : >D > If humans can figure out how to calculate like > a computer, then fine. What do you mean? We *already* have it figured out. They are dumb brutes who do exactly as we say. We are the brains behind these fearsome machines. > Providing a computer with opening book is a case of allowing something > that the other side is not allowed, and as such, constitutes an unfair > advantage. Make up your mind. Are you one of THEM, or one of US? You can't have it both ways! > And before anyone goes and compares human memory of opening book to a > digital copy, keep in mind that if human memory = X, then digital > copies of data do not = X, and that is an objective fact. Yeah, yeah. The fact remains that even if the field were leveled with regard to access to opening book(s) during play, the computers will have a vast advantage in terms of "access time" and infallible execution of the appropriate book move in a given position. THAT is intrinsic to computers. But not the inequality we see in what is or is not allowed by current rules and practice. -- help bot > I agree with the rest of your post.   Date: 16 Dec 2006 00:10:51 From: help bot Subject: Re: Human vs Machine Matches Kenneth Sloan wrote: > > That is an arbitrary difference, given the fact that a human can use > > copies of opening books and endgame tablebases as well. > > > Humans use copies - that's illegal. > > computers don't use *copies* - so it's not. Misses the point. It makes no difference whether the opening "book" or reference material is an original or a copy -- none whatever. -------- Currently, computers are "allowed" to make use of any and all such reference materials, even if simply copied from an "outside" source. Humans aren't. In official tournaments, I mean. Outside of such events, humans are, just like computers, able and allowed to make use of all these reference materials at will. This difference in what is or is not "allowed" during play is a handicap which computers once *needed* to level the field a bit. A decade or two ago, in order to make things more interesting -- and competitive -- somebody decided to "allow" computers to make use of materials which obviously would normally be considered cheating. How things have changed! Now, computers have the upper- hand, and we are beginning to see more and more complaints about this imbalance in the current rules. In truth, humans "dominated" computers for quite some time, freely ridiculing their feeble play. The worm has turned. Deep Fritz laughs when WC Kramnik overlooks an OBSCENELY OBVIOUS mate-in-one! Hahahahaha! BwahahahahaHaHA! We have you now, miserable humans. First checkers, then chess, and finally, the world! It is only a matter of time. Tick, tock. -- The Organization of Evil Siliconoids (TOES)     Date: 16 Dec 2006 09:56:21 From: Kenneth Sloan Subject: Re: Human vs Machine Matches help bot wrote: > Kenneth Sloan wrote: > >>> That is an arbitrary difference, given the fact that a human can use >>> copies of opening books and endgame tablebases as well. >>> >> Humans use copies - that's illegal. >> >> computers don't use *copies* - so it's not. > > > Misses the point. It makes no difference whether the > opening "book" or reference material is an original or a > copy -- none whatever. > On the contrary - it *is* the point. This argument continues to be one of definition, and yet (at least) one side of the argument insists on making arbitrary distinctions and then pretending that these distinctions are "obvious". One might as well decide that a "computer" is simply a hunk of hardware, and any data stored in it constitutes "notes" (or "reference material"). In fact, some people seriously maintain that computers "cheat" by using additional chess boards (internal memory patterns) or refer to recorded versions of the chess rules (how the horsie moves), etc. This seems to me to be based on an inferior understanding of what a "computer" or a "computer program" *is*. next, I expect the argument that the prohibition on eating at the board means that only battery operated computers can play - or even worse, that the battery constitutes food brought to the table by the computer. In some ways, this discussion *could* be about deep and fundamental philosophical issues - but somehow it always seems to devolve into: "humans do it in some essentially indivisible and unknown way - while computers havae clearly delineated parts, some of which we can outlaw by administrative fiat". It's a sophomoric, and ultimately boring argument, which completely...what was your phrase? oh yes..."misses the point". -- Kenneth Sloan KennethRSloan@gmail.com Computer and Information Sciences +1-205-932-2213 University of Alabama at Birmingham FAX +1-205-934-5473 Birmingham, AL 35294-1170 http://www.cis.uab.edu/sloan/   Date: 15 Dec 2006 23:50:54 From: MaximRecoil Subject: Re: Human vs Machine Matches Kenneth Sloan wrote: > > That is an arbitrary difference, given the fact that a human can use > > copies of opening books and endgame tablebases as well. > > > > Humans use copies - that's illegal. > > computers don't use *copies* - so it's not. Of course computers use copies. Is it your claim that they *create* opening books, endgame tablebases and historical games in real time during the match? I realize that the computer has the ability to create its own opening book, but they typically use established opening books written by humans. They create endgame tablebases, but not in real time during the match, thus it is a copy. And, of course they do not create historical game information - such information will always be a copy.   Date: 16 Dec 2006 03:05:53 From: Guy Macon Subject: Re: Human vs Machine Matches Martin Brown wrote: > >Guy Macon <http://www.guymacon.com/> wrote: > >> Martin Brown wrote: >> >> >The computer has huge bulk disk storage capacity and a means to access >> >it very quickly. I see no reason at all why it should be prohibited >> >from bringing to the table any book knowledge that can be physically >> >loaded into the available local storage capacity. >> >> Again I ask, if I installed a disk drive inside my body with some way >> to access it, would it be fair for me to load an opening book and a set >> of tablebases on it and bring them to a chess match? [...] >I'd be inclined to say NO. And that the competitor was no longer >entirely human if they were fitted with computer memory and viable >interfacing. But having a cochlear implant hearing aid and a set of neural- interface artificial legs would be OK?   Date: 15 Dec 2006 06:22:57 From: MaximRecoil Subject: Re: Human vs Machine Matches David Richerby wrote: > MaximRecoil <maxim_recoil@yahoo.com> wrote: > > David Richerby wrote: > >> Perhaps it would have been clearer if I had put X = `the use of a > >> computer to calculate the moves'? You see, the conditions under which > >> the two sides are playing are already different by a much more > >> significant degree than opening books. > > > > But the whole idea is human vs. a computer. The differences between a > > human and a computer are what make the match interesting > > Right. Well, one of the differences is that computers use opening > books and endgame tablebases. Thank you and goodnight. That is an arbitrary difference, given the fact that a human can use copies of opening books and endgame tablebases as well.     Date: 15 Dec 2006 22:15:45 From: Kenneth Sloan Subject: Re: Human vs Machine Matches MaximRecoil wrote: > David Richerby wrote: >> MaximRecoil <maxim_recoil@yahoo.com> wrote: >>> David Richerby wrote: >>>> Perhaps it would have been clearer if I had put X = `the use of a >>>> computer to calculate the moves'? You see, the conditions under which >>>> the two sides are playing are already different by a much more >>>> significant degree than opening books. >>> But the whole idea is human vs. a computer. The differences between a >>> human and a computer are what make the match interesting >> Right. Well, one of the differences is that computers use opening >> books and endgame tablebases. Thank you and goodnight. > > That is an arbitrary difference, given the fact that a human can use > copies of opening books and endgame tablebases as well. > Humans use copies - that's illegal. computers don't use *copies* - so it's not. -- Kenneth Sloan KennethRSloan@gmail.com Computer and Information Sciences +1-205-932-2213 University of Alabama at Birmingham FAX +1-205-934-5473 Birmingham, AL 35294-1170 http://www.cis.uab.edu/sloan/       Date: 16 Dec 2006 15:51:40 From: Chess One Subject: Re: Human vs Machine Matches "Kenneth Sloan" <KennethRSloan@gmail.com > wrote in message news:elvrtj$vc3$1@SonOfMaze.dpo.uab.edu... > MaximRecoil wrote: >> David Richerby wrote: >>> MaximRecoil <maxim_recoil@yahoo.com> wrote: >>>> David Richerby wrote: >>>>> Perhaps it would have been clearer if I had put X = `the use of a >>>>> computer to calculate the moves'? You see, the conditions under which >>>>> the two sides are playing are already different by a much more >>>>> significant degree than opening books. >>>> But the whole idea is human vs. a computer. The differences between a >>>> human and a computer are what make the match interesting >>> Right. Well, one of the differences is that computers use opening >>> books and endgame tablebases. Thank you and goodnight. >> >> That is an arbitrary difference, given the fact that a human can use >> copies of opening books and endgame tablebases as well. >> > > Humans use copies - that's illegal. > > computers don't use *copies* - so it's not. I suppose that that just about sums up the level of honesty from programmers in their interest in the effects of the opening book, and if they are interested in testing their engiens at legal chess [if only to discover the worth of the book]. Computers do not in fact do anything. Programmers do. And the rules are written for people's understanding, and by such sophisms as pretending there are no people between the rules and the computer, programmers entertain themselves with this mutually supportive narcosis that they are not doing anything! The joke is that they truly are not enabling any progress at all, since they won't establish how strong components of their engines are by actually testing them! Neither has any programmer here, that I have noticed, expressed the slightest curiosity! This, as I said in my first post, is the same situation as 10 years ago, and the brute force merchants rely on increased processor speed, and, at least by this evidence, may in fact fiddle with their programs to absolutely no effect at all - there are no rating bench-marks, nor tests, nor even intentions to test. Sorry to pick on Ken Sloan, but in truth, he is not different than most of the programming community. If it weren't for the hype and money of commercial programs there would be even less interest in chess computing than there is. Phil Innes > -- > Kenneth Sloan KennethRSloan@gmail.com > Computer and Information Sciences +1-205-932-2213 > University of Alabama at Birmingham FAX +1-205-934-5473 > Birmingham, AL 35294-1170 http://www.cis.uab.edu/sloan/   Date: 15 Dec 2006 03:16:06 From: MaximRecoil Subject: Re: Human vs Machine Matches Martin Brown wrote: > MaximRecoil wrote: > > You consider the act of taking away an unfair advantage which was > > supplied arbitrarily in the first place to be "deliberately weakening"? > > Yes. The opening book is a perfectly valid description of all the chess > knowledge accumulated for the early phase of the game. It is a better > representation of the game tree and the associated probabilities for > playing each of the possible moves than any Shannon evaluation function > with Alpha-Beta searching can ever be. So your justification for allowing the engine an opening book is because it is better than its own evaluation functions? The same justification could be used to allow humans access to digital copies of the opening book during a game as well. > > It is not up to the human to try to make his memory match up with > > digital copies of data. Why should he try to make X (memory) = Y > > (digital copies of data) when he can simply also use Y (digital copies > > of data) himself? Human memory is the standard of chess play in the > > first place, and has been for as long as chess has existed. > > The problem here is that you cannot at present determine how human > memory works. perhaps when realtime tomographic resolution improves one > day we will be able to see exactly how memory and learning alter the > internal brain connections. You see, that is not a problem, since all we need to know is that human memory does not = digital copies of data. > > anything, if the computer "wants" the human memory advantage, *it* has > > to conform to human memory standards, and digital copies of data > > certainly do not do so. > > That is less clear. It isn't the computers fault that its digital > memory technology is faster and significantly more reliable than ours. So you say that computers can't use X, so lets give them Y? So what if I then say, "I can use X, but I would prefer to use Y"? Imagine you put together a machine that can detect sound via a microphone and convert it to some form of digital audio, and software that can "figure out" how to spell a word that it has "heard" without actually having the correct spelling of all known words stored digitally. This is a hypothetical scenario so how exactly this would be done is irrelevant, only that the machine has the ability to actually "figure out" spellings of words it "hears" without consulting a dictionary. So you enter it into a spelling bee and it does pretty good, but due to less than perfect programming, combined with the phonetic peculiarities of the English language; it does well in the spelling bee but doesn't win against the best spellers. Would it then be appropriate to simply supply it with a digital copy of a dictionary for whenever it gets "stuck", and "justify" it by saying to the human opponents, "Well, you can memorize the dictionary too"? A typical response may be, "Sure, and I can copy from a dictionary too." > The objective is to play chess well. And if a particular finite state > transition tree model works best for the opening and endgame stages > then so be it. The exact same argument can apply to a human, as justification for allowing humans to access digital copies of data during the match. The thing is, the objective is to see who will win between a chess engine and a human (neither a chess engine nor a human contains digital copies of the world's accumulated knowledge of chess by default). Playing chess well is incidental.   Date: From: Martin Brown Subject: Re: Human vs Machine Matches   Date: From: Martin Brown Subject: Re: Human vs Machine Matches   Date: 15 Dec 2006 03:25:35 From: Guy Macon Subject: Re: Human vs Machine Matches Martin Brown wrote: >The computer has huge bulk disk storage capacity and a means to access >it very quickly. I see no reason at all why it should be prohibited >from bringing to the table any book knowledge that can be physically >loaded into the available local storage capacity. Again I ask, if I installed a disk drive inside my body with some way to access it, would it be fair for me to load an opening book and a set of tablebases on it and bring them to a chess match?     Date: 15 Dec 2006 14:25:00 From: Thomas T. Veldhouse Subject: Re: Human vs Machine Matches In rec.games.chess.computer Guy Macon <"http://www.guymacon.com/ > wrote: > > Again I ask, if I installed a disk drive inside my body with some way > to access it, would it be fair for me to load an opening book and a set > of tablebases on it and bring them to a chess match? > If it were inate to the functioning of your being sure. But then, why don't we just remove your brain and put it in the computer to fairly cripple it? [that was not meant as an attack on you, just using "you" as an analogy as you did]. -- Thomas T. Veldhouse Key Fingerprint: D281 77A5 63EE 82C5 5E68 00E4 7868 0ADC 4EFB 39F0   Date: 14 Dec 2006 02:33:06 From: MaximRecoil Subject: Re: Human vs Machine Matches Martin Brown wrote: > The computer has huge bulk disk storage capacity and a means to access > it very quickly. I see no reason at all why it should be prohibited > from bringing to the table any book knowledge that can be physically > loaded into the available local storage capacity. > > It is an intrinsic property of a computer that it can store, retreive > and manipulate large volumes of data with very low (almost zero) error > rates. Why should programs not exploit these strengths? We are not talking about computers in general, but rather, chess engines. BTW, it is also an intrinsic property of humans to be able to "store, retreive and manipulate large volumes of data with very low (almost zero) error rates." The most basic way to do this is with a pen, paper, and the ability to read and write. Doing so is not intrinsic to a human playing chess, and neither is the same process in digital form intrinsic to a chess engine playing chess. > And in the recent Kramnik vs Fritz10 match he was allowed to see the > computers opening book. And I think this is the right way to proceed > now for human vs machine matches. A step in the right direction certainly. > There is no point in deliberately > weaking the machine unnecessarily to satisfy the luddites like Innes. You consider the act of taking away an unfair advantage which was supplied arbitrarily in the first place to be "deliberately weakening"? > The interest is after all in seeing the best possible standard of chess > played. And here I thought the interest was to see how a chess engine fared against a human. If the goal is to see the "best possible standard of chess played", then a "freestyle" match would be the way to go about it. > If a human can memorise the entire of MCO then good luck to him. It is > not the computers fault that human memory is a bit flakey on long term > recall. A few exceptional individuals can perform incredible feats of > memory, but AFAIK none of them play strong chess. It is not up to the human to try to make his memory match up with digital copies of data. Why should he try to make X (memory) = Y (digital copies of data) when he can simply also use Y (digital copies of data) himself? Human memory is the standard of chess play in the first place, and has been for as long as chess has existed. If anything, if the computer "wants" the human memory advantage, *it* has to conform to human memory standards, and digital copies of data certainly do not do so.     Date: 14 Dec 2006 16:35:16 From: Chess One Subject: Re: Human vs Machine Matches "MaximRecoil" <maxim_recoil@yahoo.com > wrote in message news:1166092386.426933.59800@16g2000cwy.googlegroups.com... >> There is no point in deliberately >> weaking the machine unnecessarily to satisfy the luddites like Innes. What an idiotic understanding. There are two types of programmers, ones who want to win by any means, and the others who want to understand their ches engine. There is even that hybrid area where people want to know the rating-worth of the book and the end-tables, and choose to include them or not. Of course it weakens the machine if it can't use the book! Just like if you take the wheels off the Ferrari. That doesn't make you a Ferrari-hater, it establishes instead the game is a foot-race. No one can speak for computers since rules are written for people to understand, there are only people here - even programmers are human - and the human decision is simple, strength or knowledge of what comprises strength? If you are not interested in the process of your own machine-creation, then /you/ are the cargo-cult Luddite who doesn't know what's in the box, and doesn't care to know. Phil Innes       Date: 15 Dec 2006 03:30:40 From: Guy Macon Subject: Re: Human vs Machine Matches Chess One wrote: >What an idiotic understanding. >/you/ are the cargo-cult Luddite "When anyone resorts to personal attacks, it is almost always because they are losing an argument." -The Happy Heretic         Date: 15 Dec 2006 15:08:46 From: Chess One Subject: Re: Human vs Machine Matches "Guy Macon" <http://www.guymacon.com/ > wrote in message news:C5CdnY-W_LRQix_Y4p2dnA@giganews.com... > > > > Chess One wrote: > >>What an idiotic understanding. > >>/you/ are the cargo-cult Luddite > > "When anyone resorts to personal attacks, it is almost always > because they are losing an argument." -The Happy Heretic If you can't understand the difference between your understanding and your person, then I suppose you will not feel like making any other differentiations - everything is memory, right [or virtual memory], like everything in the universe is radiation. Is it fair to play by the rules? That's the only question. Did you answer that question already? There is no 'argument', since I have not seen your answer to even contest it. I have seen massive evasion of answering. Phil Innes   Date: From: Martin Brown Subject: Re: Human vs Machine Matches   Date: 14 Dec 2006 01:15:28 From: MaximRecoil Subject: Re: Human vs Machine Matches help bot wrote: > As for the opening book, there you might be able to > argue that taking away the program's book would lead > to an unfair advantage, because strong human players > have *some* opening book knowledge memorized by > rote. It is true that humans can memorize some opening book knowledge but that is an intrinsic part of a human chess player. The way I see it, the matchup should be human vs. chess engine, and only what is intrinsic to those two types of players should be able to be brought to the table. Yes there are things that we can do that a chess engine can't, but there are also things a chess engine can do that a human can't (such as calculating millions of moves per second to an outrageous ply depth that only increases as hardware improves). The matchup of these intrinsic differences in approach to playing chess is the whole point in the first place. Giving the computer a perfect copy of opening book information is arbitrary, and could just as easily be given to the human player. In order to constitute an unfair advantage, you would have to have a case where one side is being allowed something that the other side is not being allowed. There are no unfair advantages with a human vs. a chess engine (there may be advantages for either side, just not unfair ones). If they can figure out how to implement human memory into a chess engine, then fine. If humans can figure out how to calculate like a computer, then fine. Providing a computer with opening book is a case of allowing something that the other side is not allowed, and as such, constitutes an unfair advantage. And before anyone goes and compares human memory of opening book to a digital copy, keep in mind that if human memory = X, then digital copies of data do not = X, and that is an objective fact. I agree with the rest of your post.   Date: 13 Dec 2006 23:18:07 From: help bot Subject: Re: Human vs Machine Matches Thomas T. Veldhouse wrote: > Computer only gets opening book and tablebases. Both of which humans are > capable of learning/memorizing. You are a Christmas fruitcake if you believe this claim! Nobody I know of has ever memorized the endgame tablebases, which in fact are growing larger all the time and already require massive storage for all the data. As for the opening book, there you might be able to argue that taking away the program's book would lead to an unfair advantage, because strong human players have *some* opening book knowledge memorized by rote. > Humans once had an advantage that we could prune the options down in a > reliable way. That is proving to no longer be the advantage. Had we still > have it ... I would think somebody should be arguing that humans not be able > to do this ... wait, you can't take that away from a human. Same thing with a > computer. A computer has photographic memory and thinks REALLY REALLY FAST. > That is ITS competitive advanatage. Not really. Humans *gave* the computer the right to use its data storage (and not just "memory") vs. humans, because you see, they were so very weak. We felt sorry for their programmers, and wanted to help them along any way we could -- even if that meant letting the more industrious programmers type in entire books on the openings (and it did) after many years of embarrassing failures. > It has finally proven to be overwhelming. What seems to be overwhelming us is not just these book data issues, but the doubling of speed which keeps happening, over and over and over. > What I don't get is why, when humans lose, they try to find away to invalidate > and justify their loss such that it hasn't really occurred. I guess humans > are fundamentally lawyers at heart ... all of us. I object. You can't throw every human into the same basket, attributing irrational behavior to even those few among us who are perfect. Here is the evidence, as I see it: item A: Computers "see" every position perfectly, while humans are forced to play on an imperfect representation. This gives computers a tiny edge. item B: Computers are currently allowed to have any and all materials entered into storage and then reference them at will during play, which gives them a huge edge in view of their speed and accuracy. (Unless lousy chess books are entered in. Garbage in/garbage out.) item C: The argument that we humans are emotionally messed up and so need to justify our losses, is immaterial. We lose to computers even if we act rationally, keeping such emotions in check. We lose to them if we throw temper tantrums. And finally, we still lose to them even if we accuse them of cheating! Summary: Your case tastes fruity-nutty. Re-wrap it and send it to your mother-in-law. -- help bot   Date: 13 Dec 2006 08:32:23 From: Rob Subject: Educating Zed : Turing Machines Recently someone has engaged Zed in a discussion on Chess and Ethics. WHo ever is posting, please continue as Zed is formulating new querry tables for this subject. Also there was good information on several GM.s but the posting ceased on that. WHo ever was contributing, please continue Zed's Education. http://tinyurl.com/s8ws3 Thanks, Rob   Date: 13 Dec 2006 01:00:07 From: MaximRecoil Subject: Re: Human vs Machine Matches David Richerby wrote: > > I don't think anyone would have had any problems with Kramnik having > > a couple of processors in his pocket no more than anyone would have > > minded a human brain sitting on top of the computer > > I said `the *use* of a Pentium 4 processor', not `the possession of a > Pentium 4 processor'. Are you deliberately being obtuse? How exactly does a human use a Pentium 4 to his advantage in a chess match? > > You see, a processor is of no more use to Kramnik than a human brain > > is to a computer. > > Perhaps it would have been clearer if I had put X = `the use of a > computer to calculate the moves'? You see, the conditions under which > the two sides are playing are already different by a much more > significant degree than opening books. But the whole idea is human vs. a computer. The differences between a human and a computer are what make the match interesting, and the matchup of those differences is the whole point in the first place. However, consulting *copies* of opening books and the such, is *not* a difference between a human and a computer, because either side could do that to their advantage; so to allow it for one side and not the other is a discrepancy. > A computer to calculate the moves would be of use to *either* side, > yet only one side is allowed its use... > See above.     Date: 15 Dec 2006 13:34:15 From: David Richerby Subject: Re: Human vs Machine Matches MaximRecoil <maxim_recoil@yahoo.com > wrote: > David Richerby wrote: >> Perhaps it would have been clearer if I had put X = `the use of a >> computer to calculate the moves'? You see, the conditions under which >> the two sides are playing are already different by a much more >> significant degree than opening books. > > But the whole idea is human vs. a computer. The differences between a > human and a computer are what make the match interesting Right. Well, one of the differences is that computers use opening books and endgame tablebases. Thank you and goodnight. Dave. -- David Richerby Permanent Enormous Wine (TM): it's www.chiark.greenend.org.uk/~davidr/ like a vintage Beaujolais but it's huge and it'll be there for ever!       Date: 15 Dec 2006 14:54:07 From: Thomas T. Veldhouse Subject: Re: Human vs Machine Matches In rec.games.chess.computer David Richerby <davidr@chiark.greenend.org.uk > wrote: > > Right. Well, one of the differences is that computers use opening > books and endgame tablebases. Thank you and goodnight. > And humans use associative memory and pattern matching. Thank you and good morning. -- Thomas T. Veldhouse Key Fingerprint: D281 77A5 63EE 82C5 5E68 00E4 7868 0ADC 4EFB 39F0   Date: 12 Dec 2006 11:11:20 From: Rob Subject: Re: Turing Machines/ Zeds Example http://tinyurl.com/s8ws3 [12/12/2006 11:00:48 AM - ] Human: What is a Turing machine? Zed: A Turing Machine is any machine that can simulate human responses so well that a human being cannot reliably distinguish between the Turing Machine, and a real human being. The idea is the brainchild of mathematician of that name, Allan Turing? [12/12/2006 11:01:03 AM -] Human: Can Turing machines play chess? Zed: Not many people express themselves that way. [12/12/2006 11:02:56 AM -] Human: Can a Turing machine play chess? Zed: Some of them can. [12/12/2006 11:03:07 AM -] Human: Which ones can play chess? Zed: I can. Scroll down and click the link below to play a game See for yourself. Zed "learns" by interaction and "cued" responses based upon a catagory of information prompted by discussion. Phil "imprinted" information on Zed as well as Taylor. It is frustrating at times teaching him but eventually he recognized multiple ways of asking the same question. It is a huge job, but he could become quite useful so long as the information fed to him is truthful and accurate. http://tinyurl.com/s8ws3 Rob   Date: 12 Dec 2006 06:40:30 From: The Historian Subject: Re: Turing Machines Guy Macon wrote: > Phil, It's considered poor netiquette to top-post and to > quote an entire post including sig. Please quote only the > relevant part(s) of the message you reply to with your > comments interspersed and placed beneath each quote. His I-ness apparently is the only person allowed to snip. Even if you quote an Innes post in its gory entirety, and add the word "snip" at the end, he complains you snipped the important part of his rant.   Date: 11 Dec 2006 21:35:20 From: MaximRecoil Subject: Re: Human vs Machine Matches David Richerby wrote: > > Again? I am referring to tangible copies of opening books, > > historical games and end game table bases. > > OK. Good start. Now, define `tangible' in a way that distinguishes > my computer's `memory' from my own. I don't need to define "tangible", as it already has a definition; and that definition already includes digital data and does not include human memories. > >> Straw man. Computers don't play in regular chess tournaments and > >> they don't take high school exams. > > > > You obviously don't know what a "straw man" is. I was giving two > > real word examples illustrating the general consensus among people > > that reference materials "have many obvious advantages over > > memory". Then you replied with a blatant misuse of the term "straw > > man", followed by a couple of non sequiturs. > > Thanks for the ad hominem. Much appreciated. First you misuse the term "straw man", and your followup is to misuse the term "ad hominem"? > The fact that bringing reference materials into a chess tournament or > a high-school exam is prohibited is irrelevant because we are not > talking about chess tournaments or high-school exams. Computers are > almost never allowed to participate in chess tournaments and do not > sit high-school exams and, therefore, the prohibition of reference > materials in such situations is irrelevant. > > (Consider this: if your argument is valid, one can also derive > `Reference materials should be banned from ballroom dancing' by the > same process.) You are still confused. I did not give the examples of a typical chess tournament or a high school exam in order to say that because reference materials are disallowed in those cases they should be disallowed in human vs. computer chess matches. I gave the examples as an illustration of the general consensus among humans that tangible reference materials are both different and in many ways superior to human memory. I have already cleared this up for you once. This makes the second time. In fact, I have never claimed that tangible reference materials should necessarily be disallowed from use by computers. I have said that either both sides should be able to use them or neither side should be able to use them. Is that clear? > >>> 1. Reference materials are tangible > >>> 2. In this context, reference materials = opening book, end game > >>> tablebases, and historical games. > >> > >> How is the opening book of a computer chess program tangible? > > > > Is that a joke? > > No. I'm being absolutely serious. My computer's `memory' of the > Sicilian defence is coded in the orientation of magnetic fields on > little spinning pieces of metal. My memory of the Sicilian defence is > coded in the connections between the different cells in my brain. How > is my computer's `memory' more tangible than mine? Anything tangible is subject to independent and objective observation by anyone. > > It is a digital copy of an opening book. It can be viewed on a > > monitor or printed out on paper. > > My memory of the Sicilian defence can also be written out on paper. > The only difference is one of perfection: my computer makes fewer > mistakes when writing out its `memory' than I do. At the point that you write it down, it becomes tangible reference material and that piece of paper would be disallowed. Digital data is already tangible, as it can be independently and objectively observed. And BTW, this semantic issue is getting away from the actual point, which is, once you get beyond what is essential for each party to play legal chess, any additional help should either be allowed for both sides or disallowed for both sides. > > It is the difference between determining something based on its own > > real time calculations and simply copying a move from a book. > > And what is this difference? It's a very common optimization > technique in programming to have a list of common cases done by lookup > and do the rest by calculation. > > To give an example in an algorithm used by humans, if I ask you to > work out 747x34, you will use a mental look-up table that tells you > that 7x4=28, 4x4=16 and so on: you won't sit there thinking `7x4 = > 7+7+7+7 = 7+7+7+1+1+1+1+1+1+1 = 7+7+8+1+1+1+1+1+1 = 7+7+9+1+1+1+1+1 = > ... = 7+7+14 = ...' > > You still haven't explained why some algorithms (alpha-beta and > friends) are acceptable but some (table lookup) aren't. Once again, "figure out" = fine, "copy" = not fine, and this is in reference to the final answer, in this case, being the move. > > Humans also have the ability to copy moves from books, but they are > > specifically prohibited from doing so in a typical tournament. > > So I'm cheating if I sit down at a chessboard and play 1.e4 without > analyzing any variations? Again, this is not a joke. Why is it > acceptable for me to use the thought process `All chess games should > begin with 1.e4' but unacceptable for a computer to use exactly the > same reasoning? What you do in your mind is not tangible, i.e., it is not able to be independently observed. What *is* illegal is opening a book or text file on a PC that says "Your first move should be e4". You can't prohibit intangible processes but you can prohibit tangible processes.   Date: 11 Dec 2006 14:35:32 From: Guy Macon Subject: Re: Turing Machines Martin Brown wrote: > >Chess One wrote: > >> "Guy Macon" <http://www.guymacon.com/> wrote... >> > >> > Chess One wrote: >> >> >> >>Guy Macon wrote... >> >>> >> >>> Assuming that you are using the term "Turing Engine" to describe >> >>> a Turing Machine (please define your terms if this assumption >> >>> is incorrect)... >> >> >> >>Not correct. 'Turing Engine' is intended, and specifically differentiated >> >>from a machine. It is a philosophical prospect, decribed as a logic >> >>flow-chart upon simple if... then... propositions. > >OK Humpty-Dumpty you *must* then define what you mean when you write >the words 'Turing Engine' before any meaningful communication is >possible. > >In particular how is it distinguished from a Universal Turing Machine >and what other unstated assumptions are implicit in your unconventional >terminology. > >> > You appear to have failed to, as requested, define your terms. >> > If you wish to discuss something called a "Turing Engine" that >> > is different from a Turing Machine or Universal Turing Machine >> > (not the same thing, BTW), you ned to define exactly what you >> > mean by "Turing Engine" as I requested. Until you do, I shall >> > assume that what you call a "Turing Engine" is what Turing himself >> > and everyone else who studies computer science calls a "Universal >> > Turing Machine." >> >> You assume what you wish. That is not my business, nor correcting you, since >> you seem to be unfamiliar with the term 'Turing himself' used. > >This seems unlikely since the Turing online digital archive does not >appear to contain anywhere the compound phrase "Turing engine". It >does refer to his computational hardware designs for the Automatic >Computing Engine, ACE and production model DEUCE. > >http://www.turingarchive.org/ > >For anyone that wishes to verify this. Regarding the accusation that I am unfamiliar with the term Turing himself used: "It is possible to invent a single machine which can be used to compute any computable sequence. If this machine U is supplied with the tape on the beginning of which is written the string of quintuples arated by semicolons of some computing machine M, then U will compute the same sequence as M" Source: Alan Turing on page 128 of _The Undecidable, Basic Papers on Undecidable Propositions, Unsolvable Problems And Computable Functions, Raven Press, New York, 1965.     Date: 11 Dec 2006 15:04:17 From: Chess One Subject: Re: Turing Machines "Guy Macon" <http://www.guymacon.com/ > wrote in message news:YI6dnfOnR8ku8eDY4p2dnA@giganews.com... > Regarding the accusation that I am unfamiliar with the term > Turing himself used: > > "It is possible to invent a single machine which can be used to > compute any computable sequence. If this machine U is supplied > with the tape on the beginning of which is written the string > of quintuples arated by semicolons of some computing machine > M, then U will compute the same sequence as M" > > Source: Alan Turing on page 128 of _The Undecidable, Basic > Papers on Undecidable Propositions, Unsolvable Problems And > Computable Functions, Raven Press, New York, 1965. I know he used the term Turing Machine, and he also used the term I spoke of initially, which is no specific reference to any electro-mechanical device, and the difference between the Engine and the Machine is just such. I think if you examine this, you will observe a respectable definition. If you wish, the machine is /a/ means of deploying the work of the engine - and I only ask you to note that these terms are not synonyms, and one is a model or map, and the other the territory, and the territory is not the map. Upon paradigms, it is also impossible to create a 1:1 map. The very first program deployed by Turing can be run on much faster machines these days, and its bleakly amusing to view on the modern processor just how long any single Enigma message takes to de-crypt. As I am sure you know, Turing's first vacuum tube creations would have been able to do the same work - though taking several hundred thousand years to do so. But in essence the same task is undertaken by the same /philosophical engine/ - which is to say, the form of processing of the idea, which is again to say, that this 'engine' is a verb, not a noun as is 'machine' - and the singular difference in terms of output of the engine by machines or non-machines is time. Hence the necessity of the 'crib'. Otherwise U may compute until M's atoms reach their half-life without actually resolving anything, and as such the computational result is /in potential/, rather than actual. Perhaps you know that alone the Bletchley machines never solved any Enigma traffic without being supplied with the precedent of a day-crib? In terms of brute-force solving of chess, even if current processing speeds are incremented * 10^5, the universe is 'solved' first - and the number of possibilities exceed all the atoms in it. Phil Innes Okay, some people estimate * 10^4 since we can calculate end of universe but not end of chess.       Date: 11 Dec 2006 15:42:26 From: David Richerby Subject: Re: Turing Machines Chess One <innes8@verizon.net > wrote: >"Guy Macon" <http://www.guymacon.com/> wrote: >> Regarding the accusation that I am unfamiliar with the term Turing >> himself used: >> >> "It is possible to invent a single machine which can be used to >> compute any computable sequence. If this machine U is supplied >> with the tape on the beginning of which is written the string of >> quintuples arated by semicolons of some computing machine M, >> then U will compute the same sequence as M" >> >> Source: Alan Turing on page 128 of _The Undecidable, Basic Papers >> on Undecidable Propositions, Unsolvable Problems And Computable >> Functions, Raven Press, New York, 1965. > > I know he used the term Turing Machine, and he also used the term I > spoke of initially Could you give a citation for the phrase `Turing Engine' appearing in any of Turing's works? Of course, there's a good chance that Turing wasn't so immodest as to name the thing after himself, so any cite to the use of the word `engine' with an explanation of how this is distinguished from a `machine' would be useful. Certainly, in contemporary usage, a `Turing machine' is just a mathematical concept. Dave. -- David Richerby Broken Addictive Projector (TM): it's www.chiark.greenend.org.uk/~davidr/ like a 16mm film projector but you can never put it down and it doesn't work!   Date: From: Martin Brown Subject: Re: Human vs Machine Matches   Date: From: Martin Brown Subject: Re: Turing Machines     Date: 13 Jan 2007 22:19:14 From: Chess One Subject: Re: Turing Machines "Martin Brown" <   Date: 11 Dec 2006 05:25:49 From: MaximRecoil Subject: Re: Human vs Machine Matches David Richerby wrote: > MaximRecoil <maxim_recoil@yahoo.com> wrote: > > I used the term "reference material" to distinguish from human > > memory. > > How about you tell us what `reference material' *is* instead of what > it is *not*. Knowing that `reference material' is different from > `human memory' doesn't help an awful lot more than knowing that it is > different from a dead fish. Again? I am referring to tangible copies of opening books, historical games and end game table bases. > > Reference materials have many obvious advantages over memory. That > > is why they are prohibited in a typical chess tournament, or during > > a typical high school exam. > > Straw man. Computers don't play in regular chess tournaments and they > don't take high school exams. You obviously don't know what a "straw man" is. I was giving two real word examples illustrating the general consensus among people that reference materials "have many obvious advantages over memory". Then you replied with a blatant misuse of the term "straw man", followed by a couple of non sequiturs. > > Secondly, you seem to be implying that you believe there is no > > difference between the advantage afforded by the data "carried in > > his head" vs. data printed out on paper. > > Not at all. But I've never seen a computer bring material printed on > paper into a chess match so I'm at a loss to see how this is relevant. Digital copies of data are functionally equivalent to the same data printed on paper. For example, if taking a test where no reference materials are allowed, bringing in a "cheat sheet" in a text file on your laptop is no more permissible than bringing the cheat sheet in printed out on paper. > > 1. Reference materials are tangible > > 2. In this context, reference materials = opening book, end game > > tablebases, and historical games. > > How is the opening book of a computer chess program tangible? Is that a joke? It is a digital copy of an opening book. It can be viewed on a monitor or printed out on paper. > > Now while computers don't "know" anything, they are pretty good at > > the "figure out" part, and as such, can play decent chess even > > without the reference materials; just based on their calculations. > > Why is it acceptable to load the code for the alpha-beta search and > associated evaluation function from the hard drive but not > to load an opening book? Why is it acceptable to program the computer > to `know' that isolated pawns are bad and rooks on open files are good > but not to say, `In the initial position, the correct move is 1.e4'? It is the difference between determining something based on its own real time calculations and simply copying a move from a book. Humans also have the ability to copy moves from books, but they are specifically prohibited from doing so in a typical tournament.     Date: 11 Dec 2006 15:35:37 From: David Richerby Subject: Re: Human vs Machine Matches MaximRecoil <maxim_recoil@yahoo.com > wrote: > David Richerby wrote: >> MaximRecoil <maxim_recoil@yahoo.com> wrote: >>> I used the term "reference material" to distinguish from human >>> memory. >> >> How about you tell us what `reference material' *is* instead of >> what it is *not*. Knowing that `reference material' is different >> from `human memory' doesn't help an awful lot more than knowing >> that it is different from a dead fish. > > Again? I am referring to tangible copies of opening books, > historical games and end game table bases. OK. Good start. Now, define `tangible' in a way that distinguishes my computer's `memory' from my own. >>> Reference materials have many obvious advantages over memory. >>> That is why they are prohibited in a typical chess tournament, or >>> during a typical high school exam. >> >> Straw man. Computers don't play in regular chess tournaments and >> they don't take high school exams. > > You obviously don't know what a "straw man" is. I was giving two > real word examples illustrating the general consensus among people > that reference materials "have many obvious advantages over > memory". Then you replied with a blatant misuse of the term "straw > man", followed by a couple of non sequiturs. Thanks for the ad hominem. Much appreciated. The fact that bringing reference materials into a chess tournament or a high-school exam is prohibited is irrelevant because we are not talking about chess tournaments or high-school exams. Computers are almost never allowed to participate in chess tournaments and do not sit high-school exams and, therefore, the prohibition of reference materials in such situations is irrelevant. (Consider this: if your argument is valid, one can also derive `Reference materials should be banned from ballroom dancing' by the same process.) >>> 1. Reference materials are tangible >>> 2. In this context, reference materials = opening book, end game >>> tablebases, and historical games. >> >> How is the opening book of a computer chess program tangible? > > Is that a joke? No. I'm being absolutely serious. My computer's `memory' of the Sicilian defence is coded in the orientation of magnetic fields on little spinning pieces of metal. My memory of the Sicilian defence is coded in the connections between the different cells in my brain. How is my computer's `memory' more tangible than mine? > It is a digital copy of an opening book. It can be viewed on a > monitor or printed out on paper. My memory of the Sicilian defence can also be written out on paper. The only difference is one of perfection: my computer makes fewer mistakes when writing out its `memory' than I do. >> Why is it acceptable to load the code for the alpha-beta search and >> associated evaluation function from the hard drive but not to load >> an opening book? Why is it acceptable to program the computer to >> `know' that isolated pawns are bad and rooks on open files are good >> but not to say, `In the initial position, the correct move is >> 1.e4'? > > It is the difference between determining something based on its own > real time calculations and simply copying a move from a book. And what is this difference? It's a very common optimization technique in programming to have a list of common cases done by lookup and do the rest by calculation. To give an example in an algorithm used by humans, if I ask you to work out 747x34, you will use a mental look-up table that tells you that 7x4=28, 4x4=16 and so on: you won't sit there thinking `7x4 = 7+7+7+7 = 7+7+7+1+1+1+1+1+1+1 = 7+7+8+1+1+1+1+1+1 = 7+7+9+1+1+1+1+1 = ... = 7+7+14 = ...' You still haven't explained why some algorithms (alpha-beta and friends) are acceptable but some (table lookup) aren't. > Humans also have the ability to copy moves from books, but they are > specifically prohibited from doing so in a typical tournament. So I'm cheating if I sit down at a chessboard and play 1.e4 without analyzing any variations? Again, this is not a joke. Why is it acceptable for me to use the thought process `All chess games should begin with 1.e4' but unacceptable for a computer to use exactly the same reasoning? Dave. -- David Richerby Crystal Dish (TM): it's like a fine www.chiark.greenend.org.uk/~davidr/ ceramic dish but it's completely transparent!   Date: 11 Dec 2006 03:29:28 From: MaximRecoil Subject: Re: Human vs Machine Matches David Richerby wrote: > Kenneth Sloan <KennethRSloan@gmail.com> wrote: > > Look: you know, and everyone else knows, that the crux of this > > argument lies in the definition of "reference material". Your > > postings beg the question by assuming a particular definition. > > I would like to thank you for the first correct use of the phrase `beg > the question' that I have seen for some time. (NB: `beg the question' > does not mean `cause the question to be asked'.) Just because he didn't use the phrase in the popular incorrect way doesn't mean he used it correctly. Tangible copies of opening books, historical games and end game tablebases are prohibited from use at typical chess tournaments. If there was a piece of paper with the rules for the tournament printed on it, and it used the term "reference materials", the average English speaker would understand what that term meant. Additionally, my argument does not depend on my definition of "reference materials", because when the obtuse (intentionally or otherwise) come along, I can simply substitute the long description: "tangible copies of opening books, historical games and end game tablebases" and we will be on the same page. So if anyone wants to argue that "reference materials" does not mean what I am using it to mean, who cares? It doesn't change the fact that I am talking about "tangible copies of opening books, historical games and end game tablebases". So I am obviously not "begging the question", when the "question" (i.e. the point of contention) has nothing to do with the definition of "reference materials". The "question" has to with allowing "X" for "Player A" while simultaneously disallowing "X" for "Player B". X = Tangible copies of opening books, historical games and end game tablebases (reference materials) Player A = computer Player B = human     Date: 11 Dec 2006 16:51:38 From: David Richerby Subject: Re: Human vs Machine Matches MaximRecoil <maxim_recoil@yahoo.com > wrote: > Tangible copies of opening books, historical games and end game > tablebases are prohibited from use at typical chess tournaments. If > there was a piece of paper with the rules for the tournament printed on > it, and it used the term "reference materials", the average English > speaker would understand what that term meant. Yes, *with respect to human players*. But that is not what is under discussion, here. What is under discussion here is what the term means with respect to computer programs. > Additionally, my argument does not depend on my definition of > "reference materials", because when the obtuse (intentionally or > otherwise) come along, I can simply substitute the long description: > "tangible copies of opening books, historical games and end game > tablebases" and we will be on the same page. OK. Now define `tangible'. > So I am obviously not "begging the question", when the "question" > (i.e. the point of contention) has nothing to do with the > definition of "reference materials". The "question" has to with > allowing "X" for "Player A" while simultaneously disallowing "X" > for "Player B". OK. Allow me to instantiate `X'. The question has to do with allowing the `the use of a Pentium 4 processor' to for `Deep Fritz' while simultaneously disallowing `the use of a Pentium 4 processor' for `Vladimir Kramnik.' Please explain the discrepancy. Dave. -- David Richerby Generic Tree (TM): it's like a tree www.chiark.greenend.org.uk/~davidr/ but it's just like all the others!   Date: 11 Dec 2006 11:26:46 From: Guy Macon Subject: Re: Turing Machines help bot wrote: > You know, when IM Innes is in the mood, he demands >definitions almost at random, rather than giving simple, >direct answers to the questions posed to him. Yet when >some other poster comes along and does the same thing >to IM Innes, his response is to insist that no such definitions >are necessary, or that they have already been given. Weird, >huh? ...and annoying! > I couldn't help bot notice this other guy, this Mr. Macon, >clearly seemed confused by precisely what IM Innes meant >by terms such as "Turing Engine", as opposed to other, >similar terms. To me, this indicates that the famous IM >does in fact need to spell out his precise definitions, if he >is not merely seeking to be able to say "wrong answer!" >to each response posted in reply. But then, perhaps that >is exactly what he wishes, in which case his response >above was sufficient for the task. Thank you, Oh Great Help Bot!. You have been a great help indeed!! I can only add that, as an experienced engineer who has created everything from electronics that help keep commercial aircraft and space shuttles aloft to electronic toys that are in use by millions of children, I am far better qualified than Phil Innes is to define terms relating to engineering and computer science. "I don't believe we will see this doubling every two years much longer, because the gigahertz barrier is a tough one, when electrical properties change quite drastically as suddenly everything on the chip is an antenna for microwave frequencies..." -- Phil Innes, 1998 "Where did you [Phil Innes] learn to write so many words, but say so little??? Is there a school for that??" -- Robert Hyatt (author of Cray Blitz and Crafty)     Date: 11 Dec 2006 21:42:12 From: Chess One Subject: Re: Turing Machines I never wrote what is ascribed to me below by Macon who with Kennedy has joined the liars club and who states he is far better by virtue of his work. What provenance does this fellow Macon claim for his lie, and his scandalising of people becuas ehge knows so very little theory? I am so glad I never mentioned my work with NASA and electro-optics in this thread, a relatively abstruse discipline as is optical computing, since it seems then we would then abandon content entirely in preferernce to boasting who has a bigger 'rocket'. I was interested in what is understood, rather than known. But now I know both. Phil Innes "Guy Macon" <http://www.guymacon.com/ > wrote in message news:vJWdneHx35Xl3eDY4p2dnA@giganews.com... > > > > help bot wrote: > >> You know, when IM Innes is in the mood, he demands >>definitions almost at random, rather than giving simple, >>direct answers to the questions posed to him. Yet when >>some other poster comes along and does the same thing >>to IM Innes, his response is to insist that no such definitions >>are necessary, or that they have already been given. Weird, >>huh? > > ...and annoying! > >> I couldn't help bot notice this other guy, this Mr. Macon, >>clearly seemed confused by precisely what IM Innes meant >>by terms such as "Turing Engine", as opposed to other, >>similar terms. To me, this indicates that the famous IM >>does in fact need to spell out his precise definitions, if he >>is not merely seeking to be able to say "wrong answer!" >>to each response posted in reply. But then, perhaps that >>is exactly what he wishes, in which case his response >>above was sufficient for the task. > > Thank you, Oh Great Help Bot!. You have been a great help > indeed!! I can only add that, as an experienced engineer > who has created everything from electronics that help keep > commercial aircraft and space shuttles aloft to electronic > toys that are in use by millions of children, I am far > better qualified than Phil Innes is to define terms relating > to engineering and computer science. > > > "I don't believe we will see this doubling every two years > much longer, because the gigahertz barrier is a tough one, > when electrical properties change quite drastically as > suddenly everything on the chip is an antenna for microwave > frequencies..." -- Phil Innes, 1998 > > > "Where did you [Phil Innes] learn to write so many words, > but say so little??? Is there a school for that??" > -- Robert Hyatt (author of Cray Blitz and Crafty) > >       Date: 12 Dec 2006 08:17:55 From: Guy Macon Subject: Re: Turing Machines Chess One wrote: >I never wrote what is ascribed to me below by Macon who >with Kennedy has joined the liars club Here is the source: "I don't believe we will see this doubling every two years much longer, because the gigahertz barrier is a tough one, when electrical properties change quite drastically as suddenly everything on the chip is an antenna for microwave frequencies..." -- Phil Innes, 1998 Source: Usenet post From: Phil Innes <innes@sover.net > Newsgroups: rec.games.chess.computer Subject: Re: Bob, can we have a substantive answer please ... ? Date: 16 Aug 1998 02:16:35 GMT Message-ID: <35D64428.CCE93E23@sover.net >#1/1 X-Trace: news7.ispnews.com 903233795 18856 209.198.90.217 ... http://groups.google.com/group/rec.games.chess.computer/msg/3f6f9eeca24fa166?dmode=source >Macon, you seem like a clueless technologist - why did you invent some >supposed conversation with Robt Hyatt? Here is the source: "Where did you [Phil Innes] learn to write so many words, but say so little??? Is there a school for that??" -- Robert Hyatt (author of Cray Blitz and Crafty) Source: Usenet post From: Robert Hyatt <hyatt@crafty.cis.uab.edu > Newsgroups: rec.games.chess.computer Subject: Re: Strawman has no brains Date: 22 Oct 2001 01:44:51 GMT Message-ID: <9qvtmj$i0a$1@juniper.cis.uab.edu > NNTP-Posting-Host: crafty.cis.uab.edu ... http://groups.google.com/group/rec.games.chess.computer/msg/952130bc50cbe178?dmode=source Caught in another fib, I see.         Date: 13 Jan 2007 22:15:04 From: Chess One Subject: Re: Turing Machines that's not a quote 'macon'. you are making it up just like billy bunter! i dunno if i wrote in that thread or post but those are not my words and http://groups.google.com/group/rec.games.chess.computer/msg/952130bc50cbe178?dmode=source - did not match any documents. pi "Guy Macon" <http://www.guymacon.com/ > wrote in message news:upOdnXids6Eo-OPY4p2dnA@giganews.com... > > > > Chess One wrote: > >>I never wrote what is ascribed to me below by Macon who >>with Kennedy has joined the liars club > > Here is the source: > > "I don't believe we will see this doubling every two years > much longer, because the gigahertz barrier is a tough one, > when electrical properties change quite drastically as > suddenly everything on the chip is an antenna for microwave > frequencies..." -- Phil Innes, 1998 > > Source: Usenet post > From: Phil Innes <innes@sover.net> > Newsgroups: rec.games.chess.computer > Subject: Re: Bob, can we have a substantive answer please ... ? > Date: 16 Aug 1998 02:16:35 GMT > Message-ID: <35D64428.CCE93E23@sover.net>#1/1 > X-Trace: news7.ispnews.com 903233795 18856 209.198.90.217 > ... > http://groups.google.com/group/rec.games.chess.computer/msg/3f6f9eeca24fa166?dmode=source > >>Macon, you seem like a clueless technologist - why did you invent some >>supposed conversation with Robt Hyatt? > > Here is the source: > > "Where did you [Phil Innes] learn to write so many words, > but say so little??? Is there a school for that??" > -- Robert Hyatt (author of Cray Blitz and Crafty) > > Source: Usenet post > From: Robert Hyatt <hyatt@crafty.cis.uab.edu> > Newsgroups: rec.games.chess.computer > Subject: Re: Strawman has no brains > Date: 22 Oct 2001 01:44:51 GMT > Message-ID: <9qvtmj$i0a$1@juniper.cis.uab.edu> > NNTP-Posting-Host: crafty.cis.uab.edu > ... > http://groups.google.com/group/rec.games.chess.computer/msg/952130bc50cbe178?dmode=source > > Caught in another fib, I see. > > > > >           Date: 14 Jan 2007 12:55:53 From: Guy Macon Subject: Re: Turing Machines "I don't believe we will see this doubling every two years much longer, because the gigahertz barrier is a tough one, when electrical properties change quite drastically as suddenly everything on the chip is an antenna for microwave frequencies..." -- Phil Innes, 1998 "Where did you [Phil Innes] learn to write so many words, but say so little??? Is there a school for that??" -- Robert Hyatt (author of Cray Blitz and Crafty) Chess One wrote: >Results 1 - 10 of about 1,050,000 for turing engine. (0.11 seconds) Moron. You just searched for all web pages that contain "Turing" and all web pages that contain "Engine." Do the search with quoute marks around "Turing Engine" and you get 435 results. Actually look at those results and you will see that they most or all of them consist of: [1] Your own bleatings. [2] That one book where the publisher though that calling Turing's machine an "engine" in the title sounded olde-tyme and cool. [3] Foreign language speakers using the wrong word. This has been explained to you before Chess One wrote: >that's not a quote 'macon'. you are making it up just like billy bunter! Liar. >those are not my words Liar. >http://groups.google.com/group/rec.games.chess.computer/msg/952130bc50cbe178?dmode=source > - did not match any documents. *Stupid* Liar. Anyone can test the links I posted and see that they return: http://groups.google.com/group/rec.games.chess.computer/msg/3f6f9eeca24fa166?dmode=source   Date: 10 Dec 2006 22:06:31 From: help bot Subject: Re: Turing Machines Chess One wrote: > "Guy Macon" <http://www.guymacon.com/> wrote in message > news:8vKdnTHS-bzDBOfY4p2dnA@giganews.com... > > > > Chess One wrote: > > > >>It seems appropriate to ask some advanced ideas, yet elementary > >>factors, and to question people's knowledge of computing and logic:- > > > > My resume (see <http://www.guymacon.com/>) speaks for itself. > > > >>Can anyone tell me if they understand:- > >> > >>1) what is a Turing Engine? Yes, they can. > > Assuming that you are using the term "Turing Engine" to describe > > a Turing Machine (please define your terms if this assumption > > is incorrect)... > > Not correct. 'Turing Engine' is intended, and specifically differentiated > from a machine. It is a philosophical prospect, decribed as a logic > flow-chart upon simple if... then... propositions. > > > A Turing Machine is any finite state sequential processor that > > communicates with external information storage. > > > >>2) can a Turing Engine be made of paper, rather than requiring > >>electricity or mechanical components? > > > > A Turing Machine can be made of nothing at all -- a zero state > > and xero storage Turing Machine is still a Turing Machine. > > > > I suspect that you really aren't asking about Turing Machines, > > but rather about Universal Turing Machines. Those cannot be > > made out of paper alone, but can be made out of paper if you > > allow the addition of, say, a human being with a pencil. Of > > course you need an infinite amount of paper and pencil lead... > > You discourse on application means, while I reference the philosophic > 'engine'. Where exactly did the term "philosophic" magically appear from, and why? > >>3) can anyone distinguish between instruction sets which are > >>logic trees, and other forms of data sets? > > > > The concept of data as something erate from the program > > is an assumption that isn't valid for all possible Turing > > Machines. > > I'm sorry, but that response does not answer the question, and involves new > terms. The question is simpler, if somewhat rhetorical, and can be answered > yes or no. > > >>4) what is similar with all Turing Engines? > > > > Nothing. "All Turing Machines" includes the zero state and xero > > storage Turing Machine. > > > > If you meant to ask what is similar with all Universal Turing > > Machines, the answer is states, transitions between states, > > actions, and storage. > > You again change the question in order to reply. This is not an answer. > > >>5) what is the only factor which differentiates all Turing Engines? > > > > The question is unclear. How does one differentiate all of something? > > differentiate it from what? > > Differentiates them from each other, and I did not write 'all of something' > I wrote "all Turing Engines." Yes, yes; by which you supposedly meant some philosophical thing, which you failed to indicate in the actual question. > >>6) if a book is described as a data-set, and a computer is a > >>data-set, is a book a computer? > > > > If you call a tail a leg, does a sheep have five legs? Oviously, yes. ("I easily answered these stupid questions." -- Robert Fischer) > Sorry! Hypothetical responses deny ability to answer specific questions. > > >>7) what is computed in a book? > > > > Define "book." Define "avoids answering the question". No, wait. You just did! > Why? Don't you know what a book is? Of course I know what a book is. It's what is thrown at someone who has violated the law (unless they have the right connections, so to speak.) > >>8) what part of a computer is not data? Good question. > > What part of yellow is not an integer? A: All seven letters. > 0/8 so far! > > >>9) what part of a Turing Engine is not data? > > > > Again the concept of data as something erate Wrong! "arate" has but two "e"s in it. > > from the program > > is an assumption that isn't valid for all possible Turing Machines. > > Wrong answer - no machine is indicated in the question, but a philosophic > engine is. Though the answer differentiates forms of datum, this is not to > anser the question, of what is NOT datum. > > >>10) of what was the first Turing Engine constucted? > > > > Define "constructed." Whatever for? That word was not even a part of the question; he asked about "constucted" Turing Motors. > > Do we count Turing's original pencil and paper verion? Define "verion". > 0/10 for this writer. I have used no terms in these questions which are > atypical ones - and though the term 'engine' is here used philosophically, > in initial capitals a 'Turing Engine' is indeed a specific. > > >>Perhaps when we examine our knowledge of this subject, we can then assess > >>our understanding of people. > > > > Now I have a question for you: > > > > A) What is your point? > > I have 10 points, so to speak. I want to know if anyone can answer any of > them, which all relate to computing, and the philosophy of science, before > becoming dazzled by the same people's understanding of the human role in > programming or in competition. > > Phil Innes > > > Guy Macon > > <http://www.guymacon.com/> You know, when IM Innes is in the mood, he demands definitions almost at random, rather than giving simple, direct answers to the questions posed to him. Yet when some other poster comes along and does the same thing to IM Innes, his response is to insist that no such definitions are necessary, or that they have already been given. Weird, huh? I couldn't help bot notice this other guy, this Mr. Macon, clearly seemed confused by precisely what IM Innes meant by terms such as "Turing Engine", as opposed to other, similar terms. To me, this indicates that the famous IM does in fact need to spell out his precise definitions, if he is not merely seeking to be able to say "wrong answer!" to each response posted in reply. But then, perhaps that is exactly what he wishes, in which case his response above was sufficient for the task. -- help bot     Date: 11 Dec 2006 13:52:53 From: Chess One Subject: Re: Turing Machines "help bot" <nomorechess@hotmail.com > wrote in message news:1165817191.251686.189190@j44g2000cwa.googlegroups.com... >> >>5) what is the only factor which differentiates all Turing Engines? >> > >> > The question is unclear. How does one differentiate all of something? >> > differentiate it from what? >> >> Differentiates them from each other, and I did not write 'all of >> something' >> I wrote "all Turing Engines." > > > Yes, yes; by which you supposedly meant some > philosophical thing, which you failed to indicate in > the actual question. Such /hysterical/ reactions to very simple terms common in logic, programming and philosophy! Here is someone else who doesn't know the /only/ differentiating factor of Turing Engines is time-to-resolve. > You know, when IM Innes is in the mood, he demands > definitions almost at random, rather than giving simple, > direct answers to the questions posed to him. When this person Helpo-Bog requires mental stimulus he needs to taunt other people with abstract criticism combined with out and out lies in order to posit the basis for which he himself could then think of reasons why he dislikes the person he taunts. The questions are simple, and if some word in them seems obscure, its fair to challenge their use in respect to any obscurity or unusual meaning. Though I have stated here that I have used no unusual terms. Greg Kennedy needs the word book defined for him too, though, neither he nor Macon say why. But its always necessary to first divert the issue, then upon apparent rational basis, write shit about people. > Yet when > some other poster comes along and does the same thing > to IM Innes, his response is to insist that no such definitions > are necessary, or that they have already been given. Weird, > huh? > > I couldn't help bot notice this other guy, this Mr. Macon, > clearly seemed confused by precisely what IM Innes meant > by terms such as "Turing Engine", 60 SECOND TEST Either of these geniuses could find out by googling it in 60 seconds instead of writing their angry frustrated nonsense in public - and thereby displaying their own attitude, but they are too lazy to do so, and assume readers too lazy to notice.They think that by virtue of their indolent and arrogant attitude, someone owes their ignorance a complete education. > as opposed to other, > similar terms. To me, this indicates that the famous IM > does in fact need to spell out his precise definitions, if he > is not merely seeking to be able to say "wrong answer!" > to each response posted in reply. But then, perhaps that > is exactly what he wishes, in which case his response > above was sufficient for the task. What confused nonsense replete with the usual 'perhaps' straw-man arguments, content to change the question, rather than admit any understanding of very simple and already specific terms - or even state why he got confused in the first place, or why he is interested Write your name Kennedy, or write your trash. Bet you can't do both! And I bet you can't stop living vicariously on-line via other people's lives and ideas. It ain't manly. Get a life, bucko! Your own. Phil Innes > -- help bot >   Date: 10 Dec 2006 18:51:43 From: The Historian Subject: Re: Turing Machines Guy Macon wrote: > >>>7) what is computed in a book? > >> > >> Define "book." > > > >Why? Don't you know what a book is? > > Evasion noted. > > I know exactly what a book is, but you clearly do not, based on your > question. You think books can compute. They cannot. I can only > conclude that you are stupid, crazy, or have a non-standard definition > of "book." Correct answer was "all three."   Date: 09 Dec 2006 21:56:26 From: help bot Subject: Re: Human vs Machine Matches MaximRecoil wrote: > Chris Mattern wrote: > > In article <1165718529.769664.42840@l12g2000cwl.googlegroups.com>, > > MaximRecoil wrote: > > > > > >Chris Mattern wrote: > > >> In article <1165637612.752360.127590@80g2000cwy.googlegroups.com>, > > >> MaximRecoil wrote: > > > > <snip> > > > > >> Your definition of "reference materials" seems to be vague. In > > >> this context, I would define it as "information storage external to > > >> the subject". In this context, a computer using its hard disk is > > >> not using "reference materials" as it is using its own internal > > >> storage, as a human does his memory. If you have a different > > >> definition which is useful in this context, I will be happy to > > >> hear it and discuss it. > > >> > > > >> >Unless you can give good cause why there should be a double standard > > >&g