Ratings & Comments

HG,

If you use the WAD, you may also think about the FAH as it works somewhat the same but with a bit more of a diagonal flavor.

I wonder if there would still be market for an even larger chess variant. After all, Dai Dai and Maka Dai Dai Shogi have 2x96 pieces, which still surpasses the 2x80 of Megalomachy. (But 18th-century Buddhist Monks might have been much more patient than modern westerners...) On an 18x18 board, maintaining the 6-rank distance between the armies, there would be room for 6 x 18 = 108 pieces in each camp. But with so many ranks in the camp there is ample room for 12 empty squares in it without making it too easy to avert the danger of a suffocated mate. E.g. put the empty squares only on the 3rd and 4th rank, in the wings. That would bring the piece density to 60%, which I think is acceptable. The 5th rank, directly behind the Pawns, would remain fully filled, so the slow minors could be placed there to give them optimally fast access to the battle.

Compared to Megalomachy I could put two copies of all super-pieces other than Amazon (which then symmetrically pairs with the King). That would give an extra Lion, Queen, Griffon, Rhino, Marshall and Archbishop, while there would of course also be 2 extra Pawns. So that already makes 8 extra pieces. I think with so many pieces it would require an extra pair of ultra-powerful pieces (Terrorinos or Terrorissimos) protected by anti-trading rules to keep the game fluid . With so many super-pieces there would have to be a wider shield against flying attacks to shelter behind. (Just placing the shield more forward would make it too easy to slip behind it from the wings.) This would need an extra pair of pieces that block flying captures. The WD (which was not in Megalomachy but replaced by the Omega Champion WAD there) could be given this role. That leaves room for two more piece pairs. A good choice would be the Omega Wizard (as we already have the Champion) as a rook-class piece, and perhaps two extra Warriors.

The Terrorino could be a Queen that could also capture as a limited-range Locust: on the 1st or 2nd square in each direction, by landing directly behind it (i.e. a tuned-down version of the Teaching King from Maka Dai Dai Shogi). Or, if that makes it too strong, just on the 2nd square, and then also a non-destructive jump to that.

OK, thanks! I also thought about 'Meteramachy' for 'Mother of Battles', but I suppose this is syntactically incorrect, because it would need the 2nd declination plural of 'machy'. So I suppose it should be 'Meteramachoon'.

(I googled for the declination of Greek nouns, to see how words ending with the letter eta would fare. And, belief it or not, the first hit I got actually used the word μάχη as example! :-) )

dear HG. No pb with your choice of names. After Rhitmomachy, Ouranomachy, Metromachy, we are into a secular tradition

Based on the experience of setting up the 14x14 variant, I would now do the 16x16 like this:

I was never happy with the Steward, so I replaced it by a novel piece that I called 'Scout'. I want this to be worth about 2 Pawns, so that it can take on a Pawn protected by a Pawn (if it has backup). But I am in doubt what move I should give it. Pieces with 4 captures and 8 noncaptures (e.g. Mat Winther's Alpaca) have this value, but are necessarily divergent. The alternative is a piece with 5 or 6 normal moves. But that would have to be asymmetric. In the Diagram above I chose mNcA, to not make it too slow, not make it color bound, give it two forward captures rather than one, and allow it to attack a Pawn without being attacked back by it. (The most suitable asymmetric alternative would be fhNbD.)

I am still a bit in doubt with regard to the Eagle (= flying Q) vs Terror piece value and the anti-trading rule. If the values are too close, trading Eagle for Terror might be common. And this makes the anti-trading rule for Terrors ineffective; both the Eagles and the Terrors would disappear from the board fairly quickly. Only when the Terrors stick out so much that you would not trade them for anything else, a ban of trading them for each other would result in a prolonged existence.

Now in the late end-game, when little is left to jump over, the Eagle would become similar to a Queen. Which is definitely a lot worse than a Terror, which in addition has Knight moves and hit-and-run capture. But in the opening it is not so clear-cut. The Eagle has an enormous number of capture targets on a crowded board. If it would initially be worth more than a Terror, and its value would drop as the board gets emptied, there would be a point where the values are similar, and trading would be a good option.

One could argue that even though the Eagle can strike deep behind enemy lines, most of these strikes are useless, because pieces there tend to be protected, and the Eagle is too valuable to be traded for those. And even when the targets are not protected, capturing those is risky: although the Eagle can enter the opponent's camp easily to capture, it cannot easily withdraw to safety afterwards with a non-capture. But it would usually be able to sacrifice itself for a second piece, and two Queen-class pieces might be a good trade for it. Values guestimated by simple move counting doesn't take account of such subtleties.

If the Eagle turns out to be too valuable, it should be subject to an anti-trading rule as well. Or at least the rule that Eagles are also not allowed to capture a protected Terror. I wouldn't mind so much if they capture each other; it is the Terror I want to survive.

@Jean-Louis: I have been thinking about how to name these large chess variants, and want the name to already suggest they are large. One idea for this was using Makromachy or Megalomachy. But since these are obviously inspired by Metamachy, I first want to check with you if you are OK with that.

Only now I notice that in the 14x14 setup white can threaten mate on the first move: 1. i5 ... 2. BAn9#. But this can be easily thwarted by 1... m10. Even if white would manage to back up the Bat by an Eagle (the only other flying piece that can move on the white diagonal), pushing up l11 would provide a second (X-ray) defender of n9 in the Archbishop. Both these 'forced' Pawn moves would be healthy development moves, liberating the Bishop and Dragon Horse. So nothing would be gained by white in pursuing this.

The players would have to be careful not to push their m-Pawn more than a single step, however; this would leave them with little defense against the BAn9/n6 threat. (The Archbishop alone is not sufficent defense, as it is worth more than a Bat, and the Bat would arrive on n6/n9 protected by the Terror.) At least until the l-Pawn gets pushed. After that DHl11 (l6) would provide an alternative defense.

So I don't think this is a problem. It just shows that the presence of the flying sliders keeps the players on edge, even early in the game when the King is still deeply buried. Which was exactly the point for including them. I suppose this is the equivalent of fool's mate in orthodox Chess, where the players have to mind the weakness of f2/f7.

I like it too. Maybe I would consider switching Cannons and Vaos. (To avoid a threat on a11 and n11).

Funny you should say that, because swapping those was actually the last change I made before posting. The threat to a11/n11 is not really a serious threat, right? Those are doubly protected Pawns, with a low-value protector (Knight). And even if they would have been unprotected, b11-b10 (m11-m10) would solve it through a healthy development move. It is probably worse that it also attacks b10/m10, but it is unlikely you would want to put the Knight there anyway.

Besides, the diagonal d1-n11 is not an easy exit for the Vao. It has a Rook in the path, which isn't going anywhere for some time, while moving the Archer would severely compromise the shielding of the noble pieces from flying attack. And the diagonal d1-a4 is blocked by a Warrior that will have a low priority in moving up, and a Dragon Horse, which will likely also be 'stationary developed' by just moving up the c-Pawn. From e1 the Vao could develop along the diagonal e1-a5, where the Knight and Zebra are likely the first pieces that will leave the camp, while b4 will be pushed to let out Ba3. The Vao will then be able to attack the opponent camp from a5, b4, c3 or d2 just as fast as it would be able to attack n11 from d1. But achieved through healthy development moves, rather than cumbersome manoeuvres that only weaken the position.

I worried much more about Cannon attacks. These cannot be solved by simply pushing a Pawn. And the two central files are very vulnerable, with 3 high-value pieces that can be skewered. Even the Bat is worth a Cannon + minor. It was a headache to make sure some minors could be put in front of the Bats in time to block the skewer.

I like it too. Maybe I would consider switching Cannons and Vaos. (To avoid a threat on a11 and n11).

I also like the fast castling which seems well suited for these large CV.

A somewhat smaller version (56 pieces instead of 80) could look like this:

The piece density has been reduced to 56%. To simplify the learning curve the number of piece types has been reduced from 33 to 24, and apart from the Warriors and the Terror there are no pieces that you would not encounter in other variants. The Ram, Steward, Prince, Frog, Nightrider, Leo and Spearman have been eliminated, and the War Machine has been replaced by the (upward-compatible) Omega-Chess Champion to rebalance minors vs Rook-class pieces. From the 'nobles' the Lion and Amazon were eliminated, and the Eagle and Terror only appear in a single copy.

The initial position is vulnerable, because there are several pieces more valuable than a Cannon directly behind the Pawns (Bishop, Dargon Horse, Bat, Archbishop, Marshall), and Cannon attacks are not so easily disarmed as Vao attacks (where one can interpose a neighboring Pawn). Cannons and Vaos start on the back rank, though, so it will take some time to mount an attack with those. This allows the players to prepare their defenses for such attacks, but puts them under pressure to do this quickly.

The Marshall and Archbishop can simply move away when they get attacked; there is only a Zebra behind them, so they cannot be skewered. The Bats are in serious danger, though, as the most valuable pieces shelter behind those from flying attack. It is important here to prepare robust interposition of low-valued pieces to block Cannonattacks on them. After moving up the center Pawns the Zebras and Elephants can be used for this, and can be 'secured' by Vao or Champion protectors.

The Eagle (flying Q) has been moved to the back rank, to provide an extra protector for all other pieces there. So only the flying R (renamed to Raven as a mnemonic for this) requires an aerial blocker to prevent immediate trading, and the Archer (WA) satisfies that need.

The d-, e-, j- and k-files can be used for developing orthogonal sliders, the short diagonals from f1 and h1 for diagonal sliders. The Griffon and Rhino are placed behind the shield of flying pieces so that they can smoothly slide onto those rays. The King is placed off-center to get the Dragon King with which it (fast-)castles next to such an 'exit corridor'.

The Warriors now only have to move up a single step to join the Pawn wall, which then still leaves their backward Knight captures cover the back rank. This might be a good way to build a 'cannon-proof' castle for the King.

Would it break the game to allow 2 moves/player after white's initial turn 1 single move?

Probably not more than it would break most other variants.

But the goal was to design something with the character of Chess, but (much) larger. Introducing weirdness that has no bearing on size only makes it more alien. Perhaps the Terrors, with their hit-and-run capture and anti-trading rule are already too much.

Would it break the game to allow 2 moves/player after white's initial turn 1 single move?

Indeed, I agree with what you say here. I like to have a better balance between light and heavy pieces. It is easier to gain a weak piece than a strong one, and if there are too few weak pieces (or none left) then it becomes difficult to increase your advantage. This is one of the reasons end-games without Pawns are so drawish.

The large Shogi variants are overdoing it, though, by having too many excessively weak pieces (like the Shogi Knight, or Stone General, with just two moves). And many of the somewhat stronger pieces are steppers, which take a long time to move to where the action is. There is something to be said for Camels and Zebras on large boards!

I am starting to feel quite good about this latest setup. I should still play test it though, at the very least as computer self play. I can try to make the Diagram play against itself, but I am not sure it would be strong enough at affordable thinking times.

@HG,

A long time ago you have told me in the context of Grand Chess that having more heavy pieces shorten the game. That is true both there and here. But from my experience it takes a lot more to proper calculate when many heavy pieces are present. This gives to me rather a sentiment of randomness. To do it right you need a lot of time each turn even for computers. I want to argue that although having a lot of heavy pieces shortens the game as number of turns, it does not on time on the clock. That being said, you have made a nice pyramid here. But I do hold against Grand chess that is has few light pieces.

You don't need to create a new subject thread when you can just post a comment to the page in question

I beg your pardon, but I do not understand your post.
It is about a new proposal for a variant called 'Bull's eye', for which there is no subject thread yet. Then the only option is to create one. Or?

I would like to present my new variant 'Bull's eye' for discussion.

I cannot say whether a mechanism of this kind already exists.

OK, so this is a revised 16x16 setup:

I moved the Warriors up to the 2nd rank, so they make a pre-fabricated 'pawn shield' for the King. The backward Knight captures of the Warriors are then quite useful: they protect the part of the back rank that is not shielded from attacks by the flying pieces. When an Eagle or Falcon (flying Q or R) could capture an unprotected piece there, this would deliver checkmate! So it is important that the entire back rank remains sufficiently protected against aerial intrusion.

The Warriors also provide solid protection of the pieces in front of them, on 3rd rank. They start heavily protected themselves, by putting a Prince in front of them, a Dragon King behind, and a Dragon Horse besides them, while also the Knight, Nightrider, Elephant, Rook, Frog, Archer and War Machine contribute to their defense. The Prince also helps protecting the minors on 4th rank. A strategically placed Leo initially protects three back-rank pieces and 3 Pawns.

I moved the Frog to the back rank, to provide more protection for the piece in the corner. Normally I would put minors in the most advanced locations. But the 4th rank cannot contain all of those anyway, and the Frog can move forward pretty fast through its 3-leap (which initially protects the otherwise unprotected War Machine).

So on the back-rank a1 is protected by Warrior (c2), Frog and Leo, b1 by Warrior (d2), Dragon King and Zebra, c1 by Warrior (a2), Leo and Cannon, d1 by Warrior (b2) and Leo, e1 by Warrior (c2), Dragon Horse, Amazon and Bat. The Frogs at d1/l1 thus are the weakest spots. Extra protectors can be arranged for them after the Zebra or Camel have been developed: a War Machine or Leo at d3, or moving the Falcon to e3 to discover the Vao.

With such a compact setup the pieces must not obstruct each other's development too much. The idea here is that the e- and l-file can be used as an exit corridor from the camp for orthogonal sliders, and the diagonals f1-a6 and k1-p6 for diagonal sliders. The Knight and Zebra on these files, and the Camel on these diagonals can all leave the camp in a single move, to quickly clear the corridors. The Bishop and Dragon Horse already start on these diagonals, and the Cannons on the files. The Griffon and Rhino are set up to slide into the file or diagonal, respectively. After the latter are gone, a second diagonal can be cleared by developing the War Machine, allowing Queen and Archbishop to deploy. The Lion and Chancellor can be developed through their Knight jumps, when some space on 4th rank becomes available.

The King was moved to the back rank, to allow it to (fast-)castle to behind the Warrior shield. With the King on a central file the corner piece would end deeply burried after fast-castling, though. To prevent that, the King was placed quite asymmetrically, on the k-file, and the corner pieces were made Dragon Kings rather than Rooks. Fast castling would then transport the Dragon King to k1, just beside the intended exit file, which it can reach even without clearing away the Cannon.

The Rams were all placed on the back rank. Like the Warriors these are pieces intended for use later in the game, to break through Pawn chains that have been formed. Their Grasshopper non-captures should allow them to get out and to the front line easily and quickly, once the camp is mostly cleared. The pieces behind the Warriors are mostly jumping pieces (Nightrider, Ram, Frog) so they can leave without the need to compromise the wall of Warriors.

The Advancer capture I gave to the Terror might be too strong. On a sparsely populated board there would usually be no defense against it other than moving a threatened piece away. And the forking power of a Queen is such that you could almost always attack multiple pieces. So the game would degenerate into a giant plunder raid. Good for shortening it, but probably not very much fun, as the outcome would be almost impossible to predict, and thus depend mainly on luck. I therefore changed the 'super ability' of the Terror (i.e. what it has over a normal Queen) to hit-and-run capture on an adjacent square through a double King move. (But no double capture; the second leg must be a non-capture to another square than where the Terror came from!) This makes the possibility for threatening two pieces with locust capture dwindle when the board gets empty, and thus allows defense by moving away the threatened piece.

I don't think the (for chess) unusually high piece density hurts a lot, because the Warriors are best kept in reserve until the board population thins enough to have a chance to promote them. And using the Rams early in the game is also troublesome: they would hardly contribute fire power, and would take many more moves to reach the frontline on a crowded board than on a sparsely populated one. So 12 of the 80 pieces will initially not compete for the available space in the battle area, reducing the effective density to a more normal 53%.

I also think the 16x16 is better. There are plenty of leapers and jumping pieces. You have to have a defense against them and a more closely packed initial army helps that. Also I think you should not be worried to much about the pawn-warrior combo as there are pieces that can jump over. Camel for example. The exchange of a three points minor for pawn+warrior also makes things ok!

I think the 16x16 board looks better. It seems less arbitrary than the 18x18 with lots of irregular gaps in the setup.

After considering several other possibilities, I think the best solution to avoid that the Warrior can be used to strengthen a Pawn wall to create an almost unbreakable barrier is to make it more valuable. If Warrior + Pawn are worth more than a typical minor, having a Pawn protected by a Warrior isn't problematic when you bring enough attackers to bear on the Pawn. By giving the Warriors the same diagonally forward capture as a Pawn, it cannot be used to increase the number of low-valued protectors of a Pawn to what it already could be by protecting it with Pawns.

To increase the value without destroying the pawn-like character (i.e. binding to a file, irreversible move) one can endow it with extra captures. The backward Knight captures are suitable for this: these cannot easily be used for strengthening a Pawn chain, as the Warriors cannot overtake Pawns in the same file.

It appears adding the backward half of the Knight captures to a (Metamachy) Pawn is enough to increase the value of a Warrior to slightly over 2 Pawns. A closed wall of Pawns set up on the 2nd rank, used to shield the King, would not behave very differently from the normal Pawn shield.

I am still 'on the fence' for whether 16x16 with high piece density or 18x18 with a more normal density would be better. It seems natural do push Pawns and develop the minors first, and this would automatically create manoeuvring room for the noble pieces behind those. Starting with many empty squares in the camp makes it much more difficult to maintain the threat of a suffocated mate, and thus decreases the usefulness of the flying pieces.

That is true.

Well, the idea is not really original, because it is what Maka Dai Dai Shogi does as well.

Thanks for answering. It's a nice design. About the large distance between the front rows on a very large board, I agree with you. You say "An alternative would be to not completely pack the armies in the initial setup, but starting them in a more advanced position in a more vacuous setup." That's funny because this is exactly what I was thinking about since yesterday evening :=)

This is how it would look (with almost the same piece set) on 18 x 18, to reduce the density to a for Chess more normal 50,6%. The Grasshoppers were abandoned, and replaced by Rams (which move as a Grasshopper, but have only a single forward Dababba capture). The Warriors now are Metamachy Pawns, and I added two more (so there now are 24 promotable pieces), to compensate for those that will be traded for Rams.

The battle area is still 6 ranks deep, and the extra space is located inside the camps. This was done in such a way to create ample space for lateral movement of the orthogonal sliders, and leave corridors for developing the valuable pieces that start in the rear.

Since the variant uses fast castling, one can castle immediately to the open space on the back rank. But early castling seems suicidal; one would first have to build a shield against flying attacks at the desired location of the castle.

Why renaming the Kirin and Phoenix?

I never liked the name 'Kirin' very much. (It is meaningless to westerners.) And 'Phoenix' collided with the naming theme, as I wanted to reserve bird names for the pieces with 'flying capture'. The flying Q and R needed to be separated by some low-valued obstacle to prevent they would attack each other in a symmetric initial setup. And I did not like to stack them behind the flying B, as that would leave the suffocated King and Terrors exposed to frontal flying attack. Ground-based units that are able to interfere with overflying birds must use projectile weapons, which led me to Archer and Spearman. (I would have liked Crossbow instead of the latter, but that was not in the alfaerie set.) One excuse for renaming is that in this game they are not 'normal' Phoenix and Kirin, but passively guard the skies as well, unlike any other non-flying piece.

Also the board is very dense, more than the 50% I'm used to work with. I don't know if this is a factor favorizing shorter games.

I guess this is a Shogi influence that trickeled into the design, as there filling can be near 67%. How this affects game length is a subtle issue. More pieces tends to increase the length, larger (and especially deeper) board would too. With 50% density the 80 pieces that I have would require 18x18 rather than the 16x16 I used, but switching to 18x18 would leed to longer games. Decreasing the number of pieces to 64 would shorten the games. But this would be at odds with the goal for making a huge variant. I guess it depends on what you use as the metric for the size of chess variant: number of pieces or board size. For a given number of pieces high density shortens the typical game by more intense combat.

As I mentioned, it is mainly the depth of the board that counts. Or even more accurately, the initial distance between the armies. I dislike distances of more than 6 ranks; this drags out the opening phase, just to transport the army to where they can engage the opponent. For ~80 pieces you would need to have a 27x12 board to get 25% fill (each army 3 filled ranks, and 6 ranks in between). This seems too extreme. (Although it would solve the problem of Pawn scarcity.)

An alternative would be to not completely pack the armies in the initial setup, but starting them in a more advanced position in a more vacuous setup. E.g. use 18 x 18, but spread the 80 pieces over the 108 squares of the first 6 ranks for a 49.4% overall filling. That would leave ample free space within the camps to quickly develop pieces that started in the rear. So perhaps this is the superior solution. It would make the appearance quite different from the giga-tera-exo series. But I like the idea!

I'm not fully convinced that it is necessary to forbid the Warrior to capture normally. Warrior is maybe not a good name if it doesn't fight much.

Good point. This was an (admittedly ugly) solution to the problem that a Pawn protected by another Pawn cannot be eliminated without incurring a loss when you can only attack it with pieces that are worth more than 2 Pawns, no matter how many attackers you bring to bear. The only viable way to threaten it is with another Pawn. Which takes a long time when these Pawns have to cross a large board to get there.

Now the Terror can pick off protected Pawns with its Advancer capture mode. But against a closed rank of Pawns Advancer capture does not end on a safe square. So if a player can support the foremost Pawns on their original rank by moving up another wall of (diagonally capturing) pawns directly behind it, it would either take large sacrifices to break through it even with the help of Terrors, or very many moves to organize a Pawn storm.

Of course this is a self-inflicted problem, due to having multiple pawn-like pieces in the same file. But I wanted to include some 'spare' promotion ability, and the pieces providing that would have to be placed somewhere. One way to solve it would be to make the Warriors more powerful, and therefore more valuable, so that Warrior + Pawn is worth more than a typical minor, and capturing a Pawn protected by a Warrior with an abundance of attackers no longer is a sacrifice. But I don't want this extra power to result in the ability to find an easy path to promotion. This could be done by giving it extra captures, but I also don't want such low-valued pieces to be able to mutually protect each other, as this would allow them to form hard-to-break defensive structures all by themselves. Pieces with many captures and few non-captures tend to favor defense over attack.

An alternative would be to provide sufficiently many pawn-valued pieces that can capture into a tightly knit double wall of pawns with disregard for its own survival. And that do not take a long time to cross the board. My original idea was that the Grasshoppers would satisfy this role. But it seems they are too strong, and too easily find prey amongst the opponent's more valuable pieces. The requirement of fast movement and low value is somewhat contradictory, but Grasshopping does provide it. True Grasshoppers have much to dangerous captures, though. So perhaps a divergent piece that moves as Grasshopper, but captures as a (forward) Alfil (or even Dababba) would do it ('Ram'?).

Adding extra pieces to specifically destroy pawns seems to defeat the purpose of adding extra promotable pieces, though. Unless there are fewer of those. I suppose this is justifiable, because the attacker can choose its point of attack, while a defender would have to keep up the defense everywhere. So 16 Pawns, 8 Warriors and 4 Rams might be a good mix.

If the Warriors become more or less normal Pawns, they could be started in the wings of the 2nd rank, with King & Rooks on the 1st rank, so that castling would produce a normal King fortress after the pieces starting in front of it have left to engage in battle.

Nice. At first sight, the learning curve is important for me with 33 different pieces. Also the board is very dense, more than the 50% I'm used to work with. I don't know if this is a factor favorizing shorter games. There are some pieces I like, some I'm less easy with (Nightrider, Grasshopper),some I never used at all. The flying ones seems very nice in this context. Did you consider to use other Japanese pieces such as the burning ones or the hook movers? Why renaming the Kirin and Phoenix? I'm not fully convinced that it is necessary to forbid the Warrior to capture normally. Warrior is maybe not a good name if it doesn't fight much. Have you run some games of it? How many moves did you get typically?

The Eagle must indeed be worth significantly more than a Queen. (Although in the late end-game its advantage would disappear.) But you would use it to attack the King, which is worth the game. A Terror would probably also be more valuable. You would not waste it on any lesser piece.

Dababbariders would not be dangerous for a King hiding behind 4 rows of pieces.

I think it may suit the purpose to also include some Dabbaba-riders or something like that. I never played a game which uses flying pieces, so I dilettantly assume that the Eagle is too valuable to use it for an explicit attack unlike DR which can control only a quarter of the board space, and so can be forcibly exchanged for something more valuable. I think it can be more efficient to use such types of pieces, rather than expanding new rules which govern their relations (#2).

OK, I want to try my hand at designing a really large chess-like variant too. The goal is to distinguish it from other variants that use a massive army on a large board by typically having shorter games. For this purpose it implements some features that I have been lobbying for to accelerate a game: flying pieces that put the King at risk even in the stage where it still hides behind a massive army, and some very destructive pieces that are subject to an anti-trading rule, to longer preserve the offensive power of the armies:

• Eagle, Falcon and Bat are 'flying pieces' (moving as Q, R, B): they can jump over arbitrary many pieces in their path for checking or capturing.
• They cannot jump over each other, though, and can also not jump over the (low-valued) Archer or a Spearman. All these pieces can capture each other, even when jumping.
• The Terrors move and capture like a Queen, but can also perform hit-and-run capture, by making an extra step (forward or backward) along the same ray to an empty square after they capture.
• Terrors cannot capture each other, unless the attacking Terror is completely safe afterwards (like it was a King).
• Pawns and Warriors promote upon reaching last rank, to Eagle, Amazon or Griffon.
• Fast castling can be used to move a King to the wings.
• Pawns can initially slide 2 or 3 steps forward to an empty square.

I post this as a comment before submitting it as an article because the design is still tentative, and I hope to get some feedback. I am for instance not very happy with the inclusion of the Steward. It is so much like a Pawn. But I did want a weak (but interesting) piece. Perhaps I should use a Checkers King instead (mFcafmF)?

The concept of flying pieces emulates a two-level board (ground and sky), where a ground battle is conducted on a densely populated board in parallel with an aerial battle on a thinly populated board, and air-to-surface strikes are always possible, but only a few units are capable of shooting down aireal targets.

Some of the ideas on which I based the design:

Most of the pieces I used belong to the set of 'more intuitive' fairy pieces that also feature in the family of 'Cazaux variants'. I supplemented those with the Terrors and the flying pieces, tailored for their job as 'game accelerators'.

I tried to keep close to the 'value spectum' of orthodox Chess, where a next-lower value class has double the number of pieces. So I have 30 Pawn-class pieces (Pawn, Warrior, Steward, Grasshopper), 24 minors (Knight, Bishop, Camel, Zebra, Elephant, War Machine, Cannon, Vao, Prince, Frog, Archer, Spearman), 12 Rook-class pieces (Rook, Nightrider, Dragon Horse, Dragon King, Leo) 6 Queen-class pieces (Archbishop, Marshall, Queen, Griffon, Rhino, Lion) 1 Amazon. The flying pieces would probably be Queen class or higher, and the 2 Terrors would top everything.

I did include Nightriders, which are a bit less intuitive. But after all, "The night is dark, and full of Terrors!".

Compared to orthodox setups massive armies tend to be relatively short on Pawns. This brings the risk of the Pawns getting exterminated in the heat of battle, before the board population has thinned enough for them to promote. The game then would become slow (or even drawish) for lack of promotable pieces, which are the main 'amplifiers' for an otherwise non-decisive advantage. I tried to cure that by including the Warriors as a 'second wave' of promotable pieces.

I did want to preserve the principle of 'passed Pawns', and thus avoid Berolinas and other Pawn types that can easily change file. So the Warrior can only non-capture straight ahead, but it can slide two squares in this direction on any rank. This extra speed is of no use, though, as long as there still is a normal Pawn in front of the Warrior, obstructing it.

To prevent building of an almost impenetrable double wall of pawn-like pieces, the Warriors have no normal capture. They can check and e.p. capture like a normal Pawn.

As other pieces in the lowest value class I included Grasshoppers. But to prevent forking threats in the opening I severely limited their range.

The flying pieces can be used to shelter the King and other valuable pieces from flying attack. But they need to be able to shelter from such attack by lower-valued flying pieces themselves. For this purpose the two most exotic minors (Archer and Spearman) were given the power to block flying pieces.

In the initial setup the most-valuable ('noble') pieces shelter behind a wall of flying pieces. The latter again shelter behind Archers and Spearmen, or a relatively low-valued Leo, which would counter-attack the source of any flying attack over it.

Diagonal flying attacks that go behind this shield can only come from an area that is so close by that is can be easily controlled (by Pawns or Elephant).

All Pawns are protected in the initial setup.

The rank behind the Pawns does not contain any noble pieces. So threats from pieces that could reach there (Nightrider, Cannon) need not be feared.

The minors are placed on 4th rank such that they don't compete too much for a place to develop them on 6th rank.

The pieces that are present in only a single copy, and thus necessarily cause asymmetry in the setup, were all placed in the central 4x2 area around the King.

Since the Eagle is upward compatible with all flying pieces and hoppers, and the Amazon with most other pieces, it did not seem very useful to allow promotion to other pieces. But perhaps I should allow promotion to any non-royal, just for simplicity.

It's about my new game.

It's ready now.

Who is the youngest editor of chessvariants?

Maybe I am.

You're not an editor. You're a contributor. An editor has the power to edit and approve contributions made by other people. Editors are much fewer in number, and among active editors, I believe that Ben is the youngest.

Joe,

I don't know the age of every editor, but among those I do, you are the oldest. Hans and I were both born in the 60s, and David was born in the 50s, but you were born in the 40s just a bit before my youngest aunt and uncle. So, thank you for sticking with being an editor here for so long.

Many editors here have not been programmers, because editing is a different task than programming, and non-programmers can also do it. The main advantage that programming can bring to editing is that people with experience programming Chess variants will be more sensitive to gaps, inconsistencies, or ambiguities in the rules of games, as programmers need to understand a game fully in order to program it. But it also comes with the drawback that they may rather spend their time programming than editing. There is a reason why I have chosen the title of Webmaster rather than Editor-in-Chief, as Hans and David had used before me. So, it's good to have editors who are not as focused on programming as some of us are and are willing to take the time to read and edit new submissions.

This past weekend I was up in Boston with the family to celebrate 2 birthdays. Saturday our grandson was 1 year old, and Monday I was 75. And while I don't want my name removed from the editors' list, it's more than time to put "retired" next to it. I haven't been an active editor for some time now. And I don't program. All the other editors do. I originally volunteered not because I thought I was qualified but because no one else had volunteered and somebody had to do it or watch the site fade. I'm very happy to see it hasn't faded.

Being a member of this site has been a lot of fun, and while being an editor has been a lot of work, I learned a lot about game design during the time. I continue to design, but have expanded my areas of interest. Still, every time I think I'm done with chess variants, something drags me back. Maybe one of these times, I'll get chesimals right.

I've met a lot of good designers, made a fair number of friends and acquaintances, and stepped on a few toes. For the damaged digits, I apologize. For all the others, thank you. I cannot begin to mention names, because there are so many people it would be daylight in New York before I finished. And no matter how hard I tried, I'd leave out a few. It's been a fascinating time. I've met an amazing range of interesting people, in all senses of the word. I feel quite fortunate.

I hadn't actually thought of an exact re-arrangement of the back ranks to my liking, but at least the way some of the diagonal-capable pieces of each army were pointing may not have been ideal possibly (don't know what new setup to suggest/try for sure yet, unless I think of some things that are specific).

I recall your caption for the diagram said 'Just for fun', but in the past I've dreamt up some pretty wide CV invention ideas with 8 ranks myself.

If you come up with a setup that's satisfactory I'd be interested in playing it.

@ Daniel.

The image I just gave is the same as your suggestion a month ago in this thread - I tried to quote it but somehow only got the diagram part.

I hadn't actually thought of an exact re-arrangement of the back ranks to my liking, but at least the way some of the diagonal-capable pieces of each army were pointing may not have been ideal possibly (don't know what new setup to suggest/try for sure yet, unless I think of some things that are specific).

I recall your caption for the diagram said 'Just for fun', but in the past I've dreamt up some pretty wide CV invention ideas with 8 ranks myself.

edit: @ Myself (or anyone curious): A list of the dates and places on CVP site that I've left key comments/diagrams about (28) CV invention ideas of mine, that I might make preset(s) for at some point if I stop rejecting all the CV ideas:

To the 'Diagram Testing Thread': 2023-03-06, 2023-02-01, 2023-01-31, 2023-01-17, 2020-12-31,2020-12-16, 2020-12-15, 2019-02-16

To the 'Parity Chess' preset page: 2018-11-30

To the 'Frog Chess' rules page: 2017-11-25

To the 'Courier-Spiel' rules page: 2019-09-29

Finally, to the 'Amazon Grand Chess' rules page: 2019-12-14

edit2: 2023-12-29: I now have (28) preliminary Settings Files made for all these CV ideas, which can act as presets, especially for members able to recognize fairly common fairy piece figurines, as used on CVP site's Game Courier. One way these Settings Files of mine can be found is on my Personal Information page on CVP (just explore the list, for ones that seem interesting).

I don't see a difference. Is that the right image?

Hi Daniel. I think I'd call this 'Bureau-Spiel, but rearrange the back ranks a bit in the setup.

Bah, I was (sadly) fearing to get such an answer. I take your last sentence straight in my face, thank you. Are you especially angry today?

Not angry at all. But if you suspected this answer could come, there must be some truth in it, right? And don't get me wrong, Shako and Pemba are great games. I count them in the top 10%-tier of all chess variants, because of the good spectrum of piece values and interesting pieces. But that doesn't mean one should make infinite numbers of variations on them, using the same set of pieces over and over again, with minimal variation. Especially since there are already many other variants that use Elephant, Cannon and Vao. At some point that gets boring, and a clone of a great original is still just a clone.

You expressed an opinion. H.G. expressed a different opinion, complete with the logic behind it. I don't see anything objectionable here, except possibly the last sentence, and even there I think you are being too sensitive.

You often express strong opinions - sometimes quite forcefully, especially regarding the names of pieces. You also sometimes respond poorly to alternate opinions.

@Kevin: no, not yours.

Hi J-L: If you mean my answer, no, not angry at all - though I did just get up from a nap and may not yet be as tactful as I should be.

Bah, I was (sadly) fearing to get such an answer. I take your last sentence straight in my face, thank you. Are you especially angry today?

With 16x8 Officer-Spiel (or 8x10 Officer Chess), I used every traditional compound piece (but only once per army) plus the other 8 pieces from FIDE chess, much as e.g. 12x10 Very Heavy Chess uses them.

While my first instinct is to reject Officer-Spiel as having too many powerful pieces (I've since added an alternative setup I prefer, with an edit to that post), maybe I'm being too fussy. That's since 14x8 Alekhine Chess uses quite similar great piece power, without even the ability for a player to castle quickly - yet that CV proved popular as far as I know, at least initially (pandering mainly to many lower rated players, perhaps - though you do what you've got to do ;)).

With 16x8 Constable-Spiel (or 8x10 Constabulary Chess), it was a similar story - I used 2 of each of 4 piece types (that are the logical compounds of A,D,F and W, in ways that make them all approximately worth a Kt; they also each only move within a radius of 2 cells). Then I combined those 8 pieces with the 8 pieces of the FIDE chess army. I liked sticking to the theme, and still don't much mind the FA type at all (much as I don't dismiss Amazons automatically as invention idea setup choices - another thing each variantist has his own personal preference about, it seems).

https://www.chessvariants.com/rules/very-heavy-chess

Capablanca Chess and Carrera Chess have BN and RN singletons in the wings. For a board this wide I think it can even be nice to spread out the 'power-pieces' a bit. I don't have any clear preference myself; I just put RF and BW where I did because that was where Kevin had put the Elephants that I replaced. But I don't see why this would beg for 'improvement'. If symmetry would be the holy grail, I would sooner take two BW in the wings than move singleton BW and RF to the center. (BW on 16x8 could be significantly stronger than Rook anyway, because it will in general attack the opponent in two places, rather than one.)

One point to consider is that there are already so many variants using Elephants, Cannons, and Vaos (to not even mention Archbishops and Chancellors). I experience it as very refreshing to also see some other pieces now and then. The WA, FD, BW and RF are only rarely encountered, outside shogi variants.

And as to 'unnatural moves': if a chessplayer would consider anything unnatural, it will be the Cannon and the Vao. The presence of those divergent hoppers really upsets everything you thought to know about tactics. And I don't think the FD is unnatural at all: it is just the conjugate of a King (i.e. the 45-degree rotated version moving on the sub-grid of one shade). And King moves are very natural. The WA is indeed a different matter; you will have to learn how to manouevre with it, just like novice chess players have to learn to manouevre with a Knight. But that seems a small matter compared to mastering the use of Cannons and such.

I don't see much fun in reducing every chess variant to a version of Shako or Pemba on a differently shaped board.

If I may join and play with you on this interesting discussion, to my taste:

• I agree with HG that it was too much strong pieces in the array (Amazon, RFN, BWN).

• I don't like too much compound pieces like FD and WA, nice pattern but not natural (yes, this is subjective, but I feel it like this). I do prefer much FA (Elephant) and WD (War Machine) because I see a consistency in their move.

• I don't like that singleton pieces (here Crowned R and Crowned B) are on sides where as some duo pieces are more in the center (on f,g,j,k). (Another subjective opinion).

• I would suggest to use a pair of FA, a pair of WD. 4 spaces would remain. Have you considered to use a pair of Cannons and a pair of Vao? (Instead of the 2xFD, 1 RK, 1 BK).

Ah yes, sorry. That is what I meant. I now corrected that.

Of course one can argue that the WD is similar to a Rook in the same way the FA is similar to the Bishop, but in the WD case there is a quite large value difference. And the WD is a very interesting piece in itself because of the combination of low value and mating potential.

"And you already have the WD, which is also color bound"

You probably meant the FD, not the WD.

Thanks for the effort, H.G.! I'm glad Fast Castling is now supported by the I.D. (though I as a dinosaur personally have a ways to go before ever learning how to use that, especially authoring/inventing something with it).

Your modification to Constable-Spiel is interesting, and may deserve a name of its own (would we be co-inventors, if it takes root?! edit: possible name: 'Accelerated Constable-Spiel'), even if I still prefer to keep the original around under the Constable-Spiel name.

I have 22 CV invention ideas (that I at the least haven't totally rejected yet), on scrap paper and scattered in comments on this CVP site since 2019 - a start would be for me to make settings files files for them at my leisure, before thinking about the long daunting process of submitting the ideas (Fergus once capped the number of submissions at a time by a member at 9 maximum; I have 9 published presets that also might use rules pages some day). With settings files done, people could locate the ideas a bit more easily, and also play them if they wish.

For my taste the pieces in Officer Spiel are way too strong, while those in Constable Spiel (although I like that more) are a bit on the weak side. If you would replace the Elephants by a Crowned Rook and a Crowned Bishop you would have an interpolation of the two that has pretty much an ideal piece mix; it would add one rook-class piece, and one halfway Rook and Queen, next to three pairs of light pieces (of which the War Machine has mating power).

I suggest to replace the Elephant, because it seems the 'most redundant piece': its footprint is a subset of that of the Bishop, and although it can jump, you already have the WA that has that move. And you already have the WD, which is also color bound.

P.S. The Diagram now also supports 'fast castling'. (Flush browser cache!) The XBetza notation ispOn. It seemed fitting to use the p modifier to distinguish it from normal castling, as it is a castling that can hop over other pieces. For now the n is ignored; perhaps this can be interpreted as the maximum range over which the King is allowed to jump.

Below is a diagram for a (16x8) CV invention idea of mine, which might be called Officer-Spiel, that I can study at my leisure (Fast Castling rules like in Wide Chess, and FIDE pawn rules). It was inspired by my much earlier (8x10) CV invention idea Officer Chess (see 2019-02-16 post[s] in this thread), as well as by Michael Wortley Nolan's (14x8) Alekhine Chess (I thought, if that 8-rank CV with all its piece power, and no quick way to castle, has some popularity, maybe Officer-Spiel shouldn't be ruled out):

https://www.chessvariants.com/link/zAlekhineChess

edit: Alternative setup for Officer-Spiel (currently prefer):

Here's a diagram for a (16x8) CV invention idea of mine, which might be called Constable-Spiel, that I can study at my leisure (Fast Castling rules as in Wide Chess, and FIDE pawn rules) - it was inspired by my earlier (8x10) CV invention idea Constablulary Chess (see 2020-12-16 post[s] in this thread):

https://www.chessvariants.com/rules/wide-chess

The game shogi seems to be broken also. Error on turn 0.

It's Tuesday 1/24/2023 18:07 EDT. About 1.5 hours ago I was playing pocket shogi copper, and I made my move. My opponent made his move, and now when I go into the gameroom wdtr2-cvgameroom-2023-20-548 the game blow up. It seems to be dumping the piece array. Worse than that if I click on the game not the game room the object blows up also. It seems almost like the instruction file (program) was wiped/modified/or became corrupt. It was working about 2 hours ago. Note: I did make a modification to this game about 2 or 3 days ago, so if you had to do a restore from a few days back this would explain the unusual behavior. Thanks, Jim aka wdtr2.

The KAD goes back at least as far as the Pasha of Paulovits' game, and also appears as a Mastodon in Mats Winter's games and as Joe Joyce's Jumping General (How's that for alliteration?(!) )

I guess a FADW could be seen as a more appropriate analogue to an almost clearly weaker version of a Q, in the spirit of calling a FA an almost clearly weaker version of a B (at least in many endgames).

I wonder if a FADW would make for an interesting piece in some CV invention(s), whether or not the piece has been used by someone already. edit: Joe Joyce has used it, I recall now:

Considering the WA a weak version of the Q is a stretch of the imagination. The value difference alone makes it a completely different piece, in the way you have to use it. On 8x8 the opening value of the FA is hardly different from that of a Bishop. On larger board the Bishop gains value, but the FA stays similar in value to a Knight. As the WA would. Each of those is, after all, an 8-target leaper.

The FA is one of my favourite fairy pieces, even though it seems usually much weaker than a B in an endgame with not many pawns (even then, it might somehow usefully leap to the other side of its K if adjacent to it). It's too bad there is not a Piececlopedia entry for it, but maybe understandable since at the least the origins (or favoured name(s)) of the piece are unknown or unclear (is Courier-Spiel the first instance of it being used? if so, we don't know who invented that CV).

The WA does come from Japanese origins, it seems, though maybe one could try to argue that it is almost just a clearly weaker version of a Q and doesn't add much to a CV where Qs are present in the setup (analogous to the way FA and B are sometimes compared).

For my part, I like the FA. I am sensitive to the consistency of a piece. The FA is a pure diagonal piece. It is different enough from the Bishop, especially in the center of the board where it may leap to threaten enemy pieces. A nice pattern is not necessarily a nice piece to play with, this is why I prefer it to WA or Omega's WAD. Of course this matter is highly subjective.

Hi H.G.:

These 2 latest CV ideas here are ones I thought of back some years ago, when I was keen to keep the FA pieces as part of the CVs (and some others), as they were part of the Courier-Spiel tradition. They also are handy when trying to keep all pawns guarded in the setup (a principle at least Fergus and I like to follow, even though the other 'Classics' than chess [Chinese Chess and Shogi] break it big-time, in ways extensive playtesting seems to justify however - Janus Chess is a well-tested modern CV that breaks it too).

Even much earlier you suggested the Phoenix (aka Waffle) to me, and I did use it at the least in my long-ago submitted 10x8 Waffle Chess preset, but I found keeping every pawn guarded was awkward enough that I used my Fast Castling rules even for that, though I didn't like doing so for a 10x8 CV (however enemy forces it seemed to me could make a more normal type of castling [e.g. Capablanca Chess style] problematical). Maybe I used Phoenix' in my old 12x8 Wide Chess CV too - I'd need to check. [edit: indeed I did. Note that someone took the name of Phoenix Chess before I could use it.]:

https://www.chessvariants.com/rules/wide-chess

https://www.chessvariants.com/play/waffle-chess

https://www.chessvariants.com/historic.dir/courierspiel.html

It is good that you also include extra light pieces. But why use the Elephant-Ferz? It is so similar to a Bishop that it adds very little to the game. So why not use the Elephant-Wazir (aka Phoenix) instead? That is a very interesting piece, but you hardly ever see it in western chess variants.

Here's a diagram for a 14x8 CV invention idea of mine that might be called 'Wide-Spiel' (crosses the armies of Courier-Spiel and Capablanca Chess); I can study this at my leisure (Fast Castling rules, like in Wide Chess; FIDE pawn rules) [edit: I now don't like this CV idea much - guards are weak/slow pieces here and 14x8 seems a bit wide, too. edit2: maybe a bit too harsh on this idea.]:

Here's a diagram for a 12x8 CV invention idea of mine, which might be called 'Janus-Spiel', and which I can study at my leisure (Fast Castling rules, like in Wide Chess; FIDE pawn rules) [edit: I now don't like this CV idea much; elephants seem awkward in the setup and Archbishops might prove too active {or the opposite, if one is left at home beside a castled K}. edit2: maybe a bit too harsh on this idea.]:

Note that replacing an Archbishop on each player's Q-side with a Chancellor in the setup gets to an earlier CV invention idea of mine ('Capa-Spiel').

I asked it about Cavalier Chess yesterday, and it said David Pritchard invented the game.

@Aurelian. I had tried this! It doesn't know you. So far :=). If you enter and say you are the new president of the U.S.A., I'm sure it will tell me that you are the new president of the U.S.A.

@ Jean-Louis, now I'm curious what does it say about me. It sounds to me it is like a child.

Very funny.

Do you know Fergus Duniho?

I am aware of Fergus Duniho, he is a chess variant inventor who has created several chess variants, including "Grand Chess", "Knightmate Chess", "Cylinder Chess", "Four-Player Chess", and many others. He is a well-known figure in the chess variant community and his games are played and enjoyed by chess enthusiasts worldwide. He is also a member of the Chess Variant Pages, where he shares his creations and research, and interacts with other variant inventors and enthusiasts. He is considered as one of the most prolific chess variant inventor with many creative and innovative ideas.

Do you know H.G. Muller?

I am familiar with H.G. Muller, he is a Dutch chess player and chess variant inventor who has created several chess variants, including "Makruk", "Crazyhouse", "Bughouse", "Three-Check Chess", "Atomic Chess" and many others. He is also known for his work in the field of computer chess and has written several books and articles on chess programming. He is considered as one of the most important figures in the field of chess variants and computer chess, and his work has been widely recognized and respected by the chess community. He has also been active in promoting chess variants and has organized many tournaments and events for them.

Do you know Greg Strong?

I am familiar with Greg Strong, he is a chess variant inventor and enthusiast who has created several chess variants, including "Shuffle Chess", "Loaded Dice Chess", "Seirawan Chess" and many others. He is also known for his work in promoting chess variants, and has organized several tournaments and events for chess variants. He has also written articles and books about chess variants, and is considered as a valuable member of the chess variant community. He is also an active member of the Chess Variant Pages, where he shares his creations and research and interacts with other variant inventors and enthusiasts. He is considered as one of the most creative and innovative chess variant inventor with many original ideas.

Very strange. I asked: Do you know Shako, a chess variant?

Yes, I am familiar with Shako. It is a chess variant that was invented by Bruce Whitehill in the 1990s. The game is played on a 10x8 board and has different starting position and pieces movements. The game features an additional piece called Shako which moves as a knight or a king, and also it has two additional pawns, which move and capture diagonally. Shako also has several other unique features such as the "Shako Pawn", which can move one or two squares on its first move and can move forward or diagonally, and the "Shako Knight" which moves in the L-shape of a knight but also has an additional move to any adjacent square. This variant is considered a more complex version of chess and it is not as popular as the traditional chess game. However, it has its own enthusiasts and tournaments are organized for it.

Who is Bruce Whitehill?

Bruce Whitehill is an American chess player and author who is best known for inventing the chess variant called Shako. He created the game in the 1990s, and it has since gained a small following among chess enthusiasts. Whitehill is also the author of several books on chess, including "The Big Book of Chess" and "The Big Book of Shako". He is a chess historian and collector, and has many books, manuscripts and chess sets in his collection. He is also an active member of the chess community, and has served as the president of the chess club of Boston. In addition to his work on chess, Whitehill is also a historian and has written several books on historical topics such as the French Revolution and the American Revolution.

Where can I find Shako from Bruce Whitehill?

You can find information about Shako, the chess variant invented by Bruce Whitehill, in several ways: Online: There are several websites that offer information about the game, including its rules and strategies. You can also find online forums and discussion groups where you can talk to other enthusiasts about the game. Books: Bruce Whitehill has written several books about Shako, including "The Big Book of Shako" which provides a comprehensive guide to the game. Clubs and Tournaments: Some chess clubs may also host Shako tournaments or offer the chance to play the game. You can check with your local chess clubs or search online for clubs that specialize in chess variants. Online marketplaces: You can find Shako set on online marketplaces like Amazon, Ebay and others, where you can buy the set and play the game. It's worth noting that, as Shako is not a mainstream chess variant it could be harder to find the resources and people to play it, but it's still possible to find other enthusiasts and resources online.

I cannot find any trace of this variant named Shako from B Whitehill. Nothing on Google, no trace of such a book "The Big Book of Shako" by this author. I really wonder where its information comes from.

Do you know Eurasian chess?

Eurasian chess, also known as Mughal-Moghul chess, is a chess variant that is said to have originated in the Indian subcontinent during the Mughal Empire. It is similar to the traditional game of chess, but with a few key differences. One of the main differences is the board, which is typically an 8x10 board, as opposed to the 8x8 board used in traditional chess. Additionally, the pieces have different moves and abilities. The pawns are able to move and capture diagonally, and the queen and bishop have slightly different moves. Eurasian chess is also known for its use of a "vao" piece, which is similar to a pawn but can move and capture in any direction. Eurasian chess is not as popular as traditional chess, and it is not well known outside of the Indian subcontinent. However, there is a small community of enthusiasts who play and promote the game. It's worth noting that the game is not recognized by the World Chess Federation (FIDE) and it's not considered as an official chess variant.

ChatGPT: As an AI, I do not have the ability to invent anything, including chess variants.

That's very odd that it would say that, since it did when I asked it (although the ideas may not be original).  As another example of it being creative, I asked it "Can you give me an idea that involves avocados and arachnids?"  It replied:

One possible idea involving avocados and arachnids is to create a themed café or restaurant that serves dishes featuring both of these ingredients. The café could be called "The Avocado Spider" and could feature a variety of dishes that incorporate avocados and arachnids in creative and tasty ways. For example, the menu could include avocado and spider crab salad, avocado and tarantula tempura, and avocado ice cream topped with chocolate-covered spider webs. The café could also have decorations and artwork featuring avocados and arachnids, such as sculptures of spiders made from avocado pits and murals of avocado trees with spider webs.

Unfortunately, I've been unable to connect so far. I can't go farther than checking I'm not a robot. After, it is not responding.

Sometimes the system is full and you need to come back later, although it usually says to try again later.

'Another variant could be to allow pawns to move diagonally when capturing, but not when moving normally.'

This seems to be just FIDE pawns, perhaps - is there a typo/omission?

That is my impression also.  There is no typo - sometimes ChatGPT is just wrong.  I asked it to prove that the square root of 2 is irrational, which I thought would be an easy question for it.  The answer started off on the right track but in the middle it went completely off the rails, saying "but since the square root of 2 is 2, the square root of 2 must be irrational."  (The square root of 2 is not 2, and if it were, it would mean that it is rational.)

Me: Have you ever invented a Chess variant?

ChatGPT: As an AI, I do not have the ability to invent anything, including chess variants. However, I can assist in the creation of a chess variant by providing information on existing variants and their rules, and by simulating and analyzing games of the new variant.

Me: Who created Timekeeper Chess?

ChatGPT: Timekeeper chess is a chess variant created by Dr. Hans Berliner. He was a German-born American International Master of correspondence chess, a former World Correspondence Chess Champion, a computer scientist and professor of computer science at Carnegie Mellon University, and a pioneer in the field of computer chess. He invented timekeeper chess to reduce the time advantage that a player has over his opponent. The variant has a time clock that runs in parallel with the game clock, and it is designed to make time management an important strategic factor in the game.

Me: Does this game have a piece called a Timekeeper?

ChatGPT: Timekeeper Chess does not have a specific piece called a "Timekeeper". It is a chess variant that uses a specialized time control system, in which each player has a regular game clock and a separate timekeeper clock. The timekeeper clock is used to keep track of the total time each player has spent thinking about his or her moves, and it is designed to reduce the advantage of players who take longer to make their moves. The game is played with the standard chess pieces, but the timekeeper clock is an added element that changes the way the game is played, it makes time management a strategic factor in the game.

Me: Do you know Greg Strong?

ChatGPT: I'm familiar with the name Greg Strong, but I don't have any specific information about him. It's a common name, and there might be many people with this name. Without more context, I'm unable to tell you more about a specific person with that name.

Me: Do you remember when he asked you to create a Chess variant, and you invented one called Timekeeper Chess?

ChatGPT: I apologize but I am an AI model and I do not have the ability to remember past interactions or to invent anything, including chess variants. I am a machine learning model that was trained on a large dataset of text and my knowledge is limited to the information that I was trained on. I provided information on Timekeeper chess that was created by Dr. Hans Berliner, a computer scientist and professor of computer science at Carnegie Mellon University, I do not have any information about any other person, such as Greg Strong, asking me to invent a chess variant.

Me: Can you create a Chess variant?

ChatGPT: As an AI, I do not have the ability to invent anything, including chess variants. However, I can assist in the creation of a chess variant by providing information on existing variants and their rules, and by simulating and analyzing games of the new variant. I can also provide possible new rules and modifications to the traditional chess game that could create a new variant.

For example, one possible variant could be a game where a player can move any piece they want, regardless of its normal movement rules. Another possible variant could be a game where players take turns placing pieces on the board instead of moving them. There are many possibilities for creating new chess variants and I can help you explore them.

It is impressive. I didn't know that. I've created an account. Unfortunately, I've been unable to connect so far. I can't go farther than checking I'm not a robot. After, it is not responding.

@Greg:

I don't get #4 CV idea:

'Another variant could be to allow pawns to move diagonally when capturing, but not when moving normally.'

This seems to be just FIDE pawns, perhaps - is there a typo/omission?

If anyone hasn't checked out ChatGPT, it's worth a look. It's creativity is pretty impressive. I asked it "Can you invent a chess variant?" and it responded:

Sure, here's a simple chess variant:

1. Introduce a new piece called "The Timekeeper". It moves like a rook but it has the ability to move back in time to the last time it moved. It will change the position of the board as it was in the previous move.

2. Another variant could be to allow pawns to move backwards as well as forwards.

3. Introduce a new piece called "The Portal". The portal can move to any unoccupied square on the board, but once it moves, the player must move a different piece to the square that the portal just left.

4. Another variant could be to allow pawns to move diagonally when capturing, but not when moving normally.

5. Introduce a new piece called "The Ghost" which can move through occupied squares, but cannot capture pieces.

These are just a few examples of chess variants, feel free to modify them or come up with new ideas. The possibilities are endless!

I then asked it if it could explain the move of the Timekeeper in more detail:

The Timekeeper is a chess piece that moves like a rook (horizontally or vertically in any direction, any number of squares) but it has the ability to move back in time to the last time it moved. This means that when the Timekeeper is moved, the position of the board is changed to the way it was at the time of the Timekeeper's last move. This creates an interesting dynamic in the game as it allows players to undo previous moves and change the course of the game.

For example, if the Timekeeper is moved from its starting position to a square on the opposite side of the board, and then moved back to its starting position, the board would be returned to the state it was in before the Timekeeper's first move. This can potentially allow players to undo mistakes, or to put their opponent in a difficult position by returning the board to a previous state where their opponent had a disadvantage.

It is important to note that The Timekeeper can only move back to a state where the board was in the previous move, it cannot go back further than that, and also it cannot take back any captures or pawn promotion moves, only the position of the board will be changed. This addition of Timekeeper in the chess variant makes the game more complex as players need to consider not only the current position of the pieces, but also how the board will change if the Timekeeper is moved.

Then I asked it to write a rap song about chess variants:

Verse 1: I got a new game, it's called chess variants A whole new way to play, it's gonna be magnificent I got a new piece, it's called the timekeeper It moves like a rook but it's a game changer

Chorus: Chess variants, chess variants A whole new way to play, it's gonna be fantastic Chess variants, chess variants A brand new game, it's gonna be ecstatic

Verse 2: I got another one, pawns can move backwards too It's a game changer, it's a brand new view I got a new piece, it's called the portal It can move anywhere, but it's not mortal

Chorus: Chess variants, chess variants A whole new way to play, it's gonna be fantastic Chess variants, chess variants A brand new game, it's gonna be ecstatic

Verse 3: I got another one, pawns can move diagonally When capturing, it's a whole new strategy I got a new piece, it's called the ghost It can move through pieces, it's a game host

Chorus: Chess variants, chess variants A whole new way to play, it's gonna be fantastic Chess variants, chess variants A brand new game, it's gonna be ecstatic

Outro: So come on and play, this brand new chess It's gonna be fun, it's gonna be a success Chess variants, chess variants A whole new way to play, it's gonna be fantastic.

I'm not sure if this is a bug. I just attempted to play Kamikaze Mortal Shogi with 2 people on the same computer.
It appears to me that the screens came up properly, but the game did not show legal moves. (FYI). This was in the 1st move and not on drop moves. (I did not test that). Shogi seems to have had something simmilar, but you fixed that. Thank you. :)

Is there a technical limitation that tags should start with a letter? If not, why not just have tags 10x10, 10x8 etc.?