What's the best way to celebrate the end of 2023 in Chessengeria style? Of course, by organizing a tournament of the absolute chess engines elite ;) This entry will be in a somewhat humorous tone and more in a relaxed vein than most of the content on chessengeria.eu. After all, I'm celebrating the new year on the pages of our blog :) The strongest versions of the engines that have reached at least 3500 Elo on the *MCERL rating list have been invited to participate in this unique tournament. Only about 3% of chess engines, of which there are exactly 15, can boast such tremendous strength. Here is the list of participants in alphabetical order: Here is the list of participants in order of Elo rating, from the strongest: The average Elo of players at a high level of 3625 indicates that there are no random players, weak and untested engines among the participants. All of them are real "tough guys", who in many battles (thousands of games) have proven their belonging to the heavyweight category of computer chess players. The tournament was run under the terms of MCERL, that is: Each engine played 10 games with every other engine, making a total of 1050 chess games in this tournament. The tournament began on December 31, 2023 and ended on January 1, 2024 just after midnight. The winner was determined with literal fireworks going on :) Which chess engine will prove to be the winner? Which one will play the most interesting and spectacular game? Which one will impress by defeating its opponent in the shortest duel? Before we delve into the coverage of the tournament, a few words about the participants. Of the 15 players: as many as 14 are development engines whose successive versions have been released over the past year. The exception in this group is the Revenge engine, which came out in as late as 2022, and still, despite the passage of more than 1 year, it plays with the strength to participate in the Elites tournament. The Seer 2.6 engine is a development version, just before the release of Seer 2.7 in October 2023. 2 participants are commercial engines. Only two: Dragon by Komodo Chess and the aforementioned Revenge. 12 participants are open-source engines. Only 3 engines do not share their sources, commercial Dragon By Komodo Chess and Revenge as well as free rofChade. This paints a picture of a very healthy situation in the world of the most powerful chess engines at the end of 2023. Most of the authors of chess engines and the communities around them take a transparent approach to sharing sources and sharing their knowledge and experiences. Anyone interested can trace how Stockfish, Berserk, or RubiChess, for example, is created. And it works! Every day newer versions of engines are published, almost every week new ones are presented. C, C++, C#, Go, Java, Pascal, Rust, Zig and others - various programming languages are being used in increasing numbers to create chess engines. I would venture to say that the community interested in computer chess is increasingly active, and the creation and development of chess engines is gaining popularity. And maybe, just maybe... chess engines have never played so great chess before :) What I will show you dear reader with examples from the 2023 Elite tournament. Category: fastest victory - Dragon 3 By Komodo Chess White: rofChade 3.1 Black: Dragon 3 by Komodo Chess Game length: 25 moves Black's 22nd move. What is there to write, the whites stand at a loss. This is the result of their several poor decisions on the Queen's wing. 22...Nf4! Dragon does what is expected of an engine with 3700 Elo on its counter - it natively exploits weaknesses near the white King. Three more moves and black checkmate the white King. 23.Qb2 Resistance was prolonged by 23.gxf4 with a possible continuation: 23...exf4 24.Hf3 Qh6 25.Qh3 Bd4+ 26.Be3 Qg7 27.Bxd4 Qxd4+ 28.Ne3 f3!! rofChade probably decided (rightly) that further play would not provide a chance for survival in this game, and thus ensured Dragon by Komodo Chess victory not only in this skirmish but also in the category for the shortest game ;) 23...Qh6 And two moves to checkmate white King. 24.Bd3 Frees up the f1 square for the King. 24...Qh2+ 25.Kf1 25...Qh1# The end of this game. 25 moves, it's almost a chess miniature. As you can see, and at this level, it is possible to finish quickly. Download game: Fastest victory_rofChade 3.1 vs Dragon 3 by Komodo Chess Category: most spectacular finish - Seer 2.6.0 Game 1 White: Seer 2.6.0 Black: Dragon 3 by Komodo Chess White's move. The name of the category speaks for itself, so - let's start crashing! 24.Nfxe5! 24...dxe5 Dragon must accept the sacrifice. 25.Rxe5 Re8 26. Bxh7! 26...Kxh7 Again, the sacrifice must be accepted, otherwise the situation will become even worse for blacks. 27.Nf6+!! Another third sacrifice, and this time it should also be accepted, otherwise there will be checkmate of the black King in two moves (27...Kg6 28.Qh5+ Kxf6 29.Qf5#). 27...Qxf6 28.Qh5+ Seer includes his Queen in the immediate development of events. White has three fewer pieces. 28...Kh7 29.Rg5+ Kf8 30.Rf5 White's last move put the black Queen in a lost position. Soon Seer will begin to make up material losses without letting the opponent's King breathe for a moment. 30...Bd8 Dragon was left with few options. Due to black's stubbornness in continuing this lost game, the game lasted several dozen more moves. Probably Dragon by Komodo Chess couldn't get out of the shock that another engine, which is not Stockfish, could win with it in such a style ;) Below are some final moments of this skirmish: 35Qxf5+ 41.Qxd6 55.Bd4 61.Be3# Absolute destruction...! A big applause for the Seer chess engine :) This is probably not what Dragon By Komodo Chess expected when playing against a theoretically weaker opponent. Download game: Most Spectacular Finish_Game_1_Seer 2.6.0 vs Dragon 3 by Komodo Chess Category: most spectacular finish - RubiChess 20231230 Game 2 White: RubiChess 20231230 Black: Seer 2.6.0 White's move. And this time one of the participants in an interesting game is the Seer engine, although by a twist of fate, it is to RubiChess in this skirmish that the chess goddess smiles ;) 23.Rxg7+! RubiChess smelled "chess blood".... No discount - smash the defense and get to the opponent's King! 23...Kxg7 What's next? How to lead the attack, maybe 24.Bxh6+ or 24.Re3, hmmm.... Are white sure they've calculated their forces well against their intentions? 24.Nxd6! This is an important and meddlesome move. Knight is invulnerable, if black decides to take the white Knight 24...Qxd6 then in response 25.Bxh6+ with the loss of the black Queen in the next moves. 24.Kh7 The Black King steps off the square of fire of the white Bishop (h6). 25.Bc3 Perfectly timed. White Bishop does nothing on the h6 square, changes his position occupying the best diagonal at that moment. 25...Ng6 26.Qd4 increasing the pressure on Knigt f6 and creating potential checkmate threats on the g7 square. 26...Nh5 27.Bxg6+ Kxg6 28.Rxe4!! A unique sacrifice of the white Rook. RubiChess throws all its forces into the attack. 28...Qe7 Correct. If 28...fxe4 then 29.Qxe4+ Kg5 30.h4# 29.Nxf5! 29....Rxf5 Any other move by the blacks leads to a faster defeat. 30. g4 Qg5 31.h4 Cool position, two white pawns attack three black pieces. This is great illustration of the meaning of a chess attack on the position of the opponent's King. Even if not everything can be counted, in the situation when one or more foreign pieces do not participate in the defense, then it is worth the risk. 31...c5 32.Qd1 Rd8 33.Qb1 Qe7 34.gxf5+ Taking a pawn leads to checkmate in three moves: 34...Kxf5 35.Re5+ Kg4 36.Qf5+ Kxh4 37.Qxh5# 34...Kh7 35.f6 White dominance. Two advanced Pawns and the exposed position of the black King. 35...Nxf6 36.Rf4 Kg8 37.Bxf6 Black got the checkmate within a few moves. 46.h5# This is what a chess engine with over 3700 Elo on the strength meter is capable of, precise, unforgiving, making maximum use of available resources - this is what RubiChess is ! Download game: Most Spectacular Finish_Game_2_RubiChess 20231230 vs Seer 2.6.0 Category: most interesting game - Black Marlin 8.0 White: Black Marlin 8.0 Black: Alexandria 5.1.1 12.d5 Black Marlin chose the Spanish game, a closed variant (Chigorin). This system is often characterized by complex play, full of figurative maneuvers with many opportunities for both sides. 14...Ne8 First little surprise. In these kinds of positions, usually black decides, for example, ...Nfd7 or ...c4 to initiate developments on the Queen's wing (occupation of the c5 square by Knight, etc.). Whether Alexandria plans to ...f5 in the future, we will see. 15.a4 Better than passive Nbd2. 17...Rb8 Black is playing actively. More and more opportunities are born on the chessboard. 19...f5 And yet! This is a much more interesting than 19...Nb3 or 19...h6. Pawn's temporary sacrifice on f5 is intended to weaken the important d5 square on which white Pawn stands. If black succeeds in occupying this square, it may gain an advantage by breaking up Chigorin's closed variant. 20.exf5 Not accepting black Pawn could weaken white's abilities on the King's wing, such as 20.Bg5 and strong 20...f4! 20...h6 21.Nd2 Bg5 22.g4 Bxd2 23.Bxd2 c4 The situation is escalating. In the meantime, white defended its Pawn f5 and started offensive actions through 22.g4. Black, on the other hand, set up exchanged their weak black-square Bishop for a strong Knight d2 and set up better and better squares. 24.Be3 Bb7 25.Rad1 Nf6 26.Qf3 Black strengthens the pressure on the d5 square. White defends this square where their Pawn stands. 26...Ba8 27.Kh2 Rb2!= The position is balanced, although increasingly complicated. As correct a heavy figure move as possible; perhaps hoping for 28.h4 which would allow black to play a strong 28...e4! 28.Bc1 Rbb8?! Black's first a weaker move. Rook's retreat is a loss of tempo. Better to brave 28...Ra2! and accept the loss of Rook in exchange for Bishop but in keeping with the spirit of breaking Chigorin's variant, Alexandria could gain the important point on the chessboard that is d5. Possible continuation: 28...Ra2! 29.Bb1 Ra1 30.Bb2 Rxb1 31.Nxb1 Nb7 32.Ba3 Nd8 33.Nd2 Bxd5 -> with equal position (2 free and strong black Pawn in the center) Diagram formed after 33...Bxd5 at the end of a possible continuation Back in the game. 29.g5 Black Marlin immediately seizes the opportunity and launches offensive operations on the King's wing. 29...hxg5 30.Rg1 Qc5 31.Rxg5 Bxd5 Alexandria finally managed to capture a key point on the chessboard - d5. So should black be satisfied with the position obtained? Comparing the current position to the position obtained at Rook's price (diagram above), I think not. Now white has a highway for its heaviest figures leading directly to the black King. Anyway, it's getting more and more interesting, with both sides having a lot of possibilities. 32.Qg3 Rf7 33.Rg1 Rb7 In response to the powerful white pressure, black defends Pawn g7 by doubling on the seventh line both Rook; this is not the end of their possibilities - the black Queen can also join in to support the defense from the c7 square. Black's defense seems to be strong enough to protect their King. This kind of position is such a good illustration of how an early loss of one tempo can enable the other side to take the initiative. 34.Rg6?! Like black before, with this move white loses tempo, their onslaught will slow down. Due to the effective defense of Pawn g7 protecting the black King, it seems more logical to shift their forces to the h-line via 34.Qh4 and attach the future to the play of both Bishops on the c1-h6 and d1-h5 diagonals. 34...Nc6 35.Qh4 e4! Good move! Limits the white Bishop c2 and frees the e5 square for the black Knight. In my opinion, the position is close to full equalization. Some chess engines indicate white's advantage, although after a longer analysis it is clear that black is able to hold. 36.Rh6 Another interesting move was 36.Bd1, which led to further maneuvers. 36...Kf8= The perfect moment to reposition the black King. The position is equal. This is the culmination of this game. The white's efforts, while ingenious, have not yet given them a decisive advantage. Black, on the other hand, having lost tempo earlier, activates his forces in the last moves and improves its position from move to move. Unless Black Marlin does something decisive, the game will end in a draw at best, yet there is no shortage of weaknesses in his camp: Pawn f2, f5, Knight a3 out of play. 37.Rxg7!! What an impact, what a sacrifice :) Two exclamation marks for this move, not because it's a finishing and winning move, but because it's the only one that gives white a chance to win. A beautiful move, a risky move, a creative move - one that can bring out the balance, one that can lead to a win.... or a loss. Black Marlin throws the gloves in Alexandria's face. 37...Kxg7? The mistake that white was waiting for. Probably black was counting on 38.Rh8 Qxf2+ 39.Qxf2 Kxh8=) The balance was maintained by 37...Rxg7! with a possible continuation 38.Qxf6+ Kg8 39.Be3 Qxa3 40.Qh4 Rh7! 41.Bxe4 Bxe4 42.Rxh7 Rxh7 43.Qxe4 Qxc3 44.Qe8+ Kg7= 38.Be3!+- 38...Ne5! 39.Bd1! If white takes the Queen 39.Bxc5, then 39...Nf3+ 40.Kg3 Nxh4 41.Rxh4 dxc5-+ 39...Qc6 40.Rh8 Ng8 41.Qh7+ Kf6 42.Qxg8 A winning position for the whites. Two Bishops are just waiting to join in knocking down the black monarch. 42....Rg7 43.Qd8+ Kxf5 44.Rh5+ Ke6 45.Nc2 Nd7 46.Qe8+ Kf6 47.Rh6+ 47...Rg6 48.Rxg6+ Kf5 49.Nd4# Exquisitely flavored checkmate! This game, one of more than a thousand from this tournament, appealed to me. This game lasted about 4 minutes. Welcome to the world of computer chess, where art is painted with the chess moves of man's works! Thunderous applause for both players of this battle. This time, it was Black Marlin who proved superior, taking risks against a very strong opponent. Download game: Most Interesting Game_Black Marlin 8.0 vs Alexandria 5.1.1 Category: tournament winner - Stockfish 20231230 Here is the scoreboard of the Chessengeria's Chess Engines Elite Tournament - 2023. Table with results created in Banksia GUI Stockfish has not lost a single game!! Its domination was evident in each of the mini-matches, from which it emerged victorious against each opponent. Table with results created in Banksia GUI Congratulations for the achieved result and words of appreciation to the Creators of this remarkable chess engine :) Let's see how Stockfish, the winner of the Chess Engines Elite tournament, can play - the only chess engine in this tournament at a ranking level exceeding 3800 Elo. White: Stockfish 20231230 Black: Altair 6.0.0 White's move. In this game, we see the King's Indian opening in a classic variant. 11.a4 A natural move inherent in the strategy of this opening. White usually seeks to be more active on the Queen's wing, black, on the contrary, on the King's wing. 11...a5 12.b5 b6 13.Ra3 Taking advantage of the space gained, Stockfish launches a heavy figure early in the game. It's an interesting idea, the white Rook looks from the a3 square to the King's wing as well. 13...h6 14.exf5 Bxf5 15.h3 Nf6 16.g4 You can feel the confidence of the whites. They seize the space without hesitation. This is, so to speak, a provocation for black to take offensive action centered on Pawn g4. 16...Bd7 Of course, it's not worth giving up a figure for Pawn g4 at this moment. 17.Bd3 Qe8 18.Nh2 It supports Pawn g4 and frees up space to use Pawn f2. 18...Qf7 19.Qc2 h5 Altair builds tension by attacking Pawn g4. The situation on the chessboard looks promising for both sides of the game. 20.f3 Does Knight on the h2 square occupy the wrong position? Absolutely, no. It serves the important function of protector of the important g4 square. 20...Kh8 21.Re2 Here's a Stockfish-level move from 2023! Quiet, inconspicuous, not bringing anything new - it's just appearances. A very strong move, from a strategic point of view, like Rook a3, it performs many functions will be prepared to penetrate the f, g and h lines, at the end of which is the black King. 21...Ng8 22.Ne4 Go forward! White has made adequate preparations beforehand, now it's time for confrontation. The position is even. 22...Bh6 23.Ng5 Bxg5 Good. Black removes Knight, who could cause trouble. 24.Bxg5 Nf6 25.Bh6 It targets the g7 and f8 squares, probably with no intention of taking the black Rook. In this position, Bishop h6 is powerful, stronger than black Rook. 25...Nh7? Not the best move. More advisable would have been 25...Qh7 with possible continuation 26.Qd2 Rf7 27.Rg2 and regrouping of forces. 26.f4! A sharp spike from Stockfish! A nice sacrifice by Pawn to occupy the most important diagonal a1-h8 which, in cooperation with Bishop h6, tilts the balance of victory to the white side. 26...exf4 27.Qb2+ Kg8 28.gxh5 Releases the g4 square for the white Knight. 28...g5 29.Ng4 Nf5 Altair is fed up with Bishop's h6, which is so strong that it engages its Queen to defend the g7 square to defend against checkmate. 30.Bxf8 Qxf8 31.Ra1 I encourage you, dear reader, to pay attention to the movements of both Rook by Stockfish. There is no coincidence here. Now this Rook is heading to the e1 square aiming to play one of the remaining acrodes of this game. 31...Ng3?! Black would have resisted longer by playing 31...Ne3. 32.Re7! Rook is untouchable. If 32...Qxe7 then 33.Nh6+ Kf8 34.Qh8#. 32...Bf5 33.Rae1! Bxd3 34.R1e6 Excellent interaction between the two white Rooks. 34...Ne2+ 35.Kh2 c5 Altair cannot prevent checkmate. 36.bxc6 Ra7 37.Rxa7 Ng3 38.Re8! 38...Nf1+ If 38...Qxe8 then 39.Qg7# 39.Kg1 Nf6 40.Nxf6 Kh8 41.Rxf8# Great ending to the symphony played by Stockfish :) Extraordinary depth of strategy, sense of position and precise tactics. And all this in a game with such a fast speed, where the engines have 1 minute to think at the beginning + 0.6 seconds after each move. Download game: Tournament Winner Game_Stockfish 20231230 vs Altair 6.0.0 As we approach the end of the summary of the 2023 Chess Engines Elite Tournament, I would like to highlight the Berserk 12 engine's winning of second place in this heavily attended tournament. Berserk 12 has made it clear that it is currently number 2 in the world of computer chess. The difference of 9.5 points between Berserk 12, second in the scoreboard, and Dragon 3 by Komodo Chess taking the third position makes a significant difference when comparing this to other engines further down the table, where the point differences are on a much smaller scale. Congratulations to Berserk 12, its author Jay Honnold and everyone involved in the development of this incredibly powerful chess engine :) A surprise for me is the third place Dragon 3 by Komodo Chess. Month after month on the MCERL rating list, Dragon 3 by Komodo Chess is being pushed further and further out of the top spot by newer and more advanced versions of RubiChess (4th place) and Clover (5th place). As you can see, the old Master is not going to let go just yet. Respect! There is no doubt in my mind that the top 5, viz: Stockfish, Berserk, Dragon, RubiChess and Clover are the strongest chess engines for 2023/2024. I am pleased to see that each of them is natively available not only for Mac users but also for other platforms running, for example, Windows and various Linux distributions increasingly used by computer chess enthusiasts. Congratulations to all the participants of the Chess Engines Elite Tournament - 2023 and their authors! Taking the opportunity that this is the first entry this year on our blog, I wish you dear reader all the best in the new 2024! Download the database of all Chess Engines Elite Tournament 2023 games * The rating of the 15 chess engines was determined according to the current MCERL as of 2023-12-31. ** Diagrams created in the ChessX.

The author of PGG106, is making his Alexandria chess engine available as a free, open-source engine under the GPL3.0 license. Alexandria is relentlessly and piercingly breaking into the top of the strongest. According to the MCERL rating list, Alexandria 5.1.1 (the December 2023 version) is playing at 3616 Elo, matching such heavyweights as RubiChess, Clover and rofChade released in the same year, for example. Source: MCERL The author decided quite quickly to use a neural network. Already from the second version, Alexandria played implemented NNUE, which allowed to strengthen the playing power of this engine about 600 Elo (!) Source: MCERL (ongoing) Of course, the strength of the chess engine is not only the neural network, as was clearly evident from the successive versions published by PGG106. As of May 2022, 17 more versions of this chess engine have been released. Alexandria has been and continues to be developed in every aspect, which has led to a clear increase in the power of the game. Noteworthy is the author's ability to work effectively with talented creators, which perfectly underlines the fact that Alexandria's power has grown so impressively. What particularly caught my attention while observing Alexandria's games and analyzing chess positions was this engine's extraordinary determination to achieve a positive result. Whether having an advantage, looking to equalize, or fighting to save the game, Alexandria showed "claw" by finding often risky and working continuations. At such a high as reaching 3600 Elo in games between chess engines, the concept of risk is extremely rare. For the most part, chess engines playing at this strength easily outplay the weaker ones and draw against engines of similar playing strength. This is not what Alexandria does - and it is what sets this excellent chess engine apart. I invite you to read some examples. 1. White: Vafra-14.12, which is a clone of one of the strongest - Stockfish. Without a doubt, it is an engine capable of winning against any other. Black: Alexandria 5.1.1 Black's move. Quite a dynamic situation on the chessboard, full of pieces. Vafra, without the slightest qualms, has been building his advantage since the beginning of the game. Currently, it has 1 pawn more and is trying to consolidate its forces. The last move of the white pawn to Vafra's h4 square is an intention to place the white knight on the g5 square, which will allow it to occupy a perfect area close to the black king and limit the freedom of movement of the black queen. If Alexandria does not take any decisive action, then most likely the result of this game will end in defeat. What to do? It seems that the black figures stand in quite optimal positions, while the white's zone and its king are fortified and defended by numerous pieces. 33...Bxg3!! Alexandria, does not wait for further and unfavorable developments - hits a strong point near the white king. This is a risky and very unexpected move, the idea of which is to reverse the fortunes of this game. White must respond with precision. 34.fxg3? Correct 34.Nxg3 sustained white's advantage giving them a chance to win. White's move opens the way for Alexandria to strengthen his position and attack the white king. 34...Qe3+= In the following moves there will be a series of exchanges, thus reducing the material on the chessboard. The position is even, although Vafra probably doesn't see it yet. 35.Kh2 Rxf1 36.Rxf1 36.Be2 "Forks" - Alexandria with the intention of taking the white Bishop. 37.Re1 Qxd3 The forces have been aligned. The first dust has settled. Let's take a look at the position on the chessboard. If white makes the queen exchange (38.Qxd3), then they will be at a disadvantage, as they risk losing the weak pawn on the a6 field and, consequently, likely losing. Vafra chooses the good 38.Qa2 A series of several moves follows. Both sides do not want to proceed to the endgame for the time being. Vafra is looking to position its white Knight on a good field, Alexandria is looking closely for a chance to escalate operations near the enemy King. 38...Bf3 39.Nf6+ Kg7 40.Nd7 Finally, the whites position their Knigt near the foreign monarch. Only, is the center of events right there? As we'll see in a moment, probably not! 40...Re8! Alexandria once again sacrifices material, this time at the cost of Rook, black wants to gain access to the first line on the chessboard to create strong threats. White accepts the sacrifice. 41.Rxe8 41...Qf1 And the threat of the white king's checkmate. It's easy to avoid this checkmate by 42.Re7+ or what white played 42.g4. Black kills the pawn on g4, 42...hxg4. White starts giving chess to the black King. Will this game end in a draw? 43,Re7+ 43...Kg8 The situation seems clear, with each successive move bringing a draw closer, which I guess would be a dream outcome for Vafr in this game. What next? Well, it's another check to the black King. 44.Re8+?? This seemingly innocent move leads to disaster for the whites. It was necessary to 44.Kg3 maintaining the balance. 44..Kf7! -+ The draw was led to by 44...Kg7 and 44...Kh7. 45.Rf8+ Ke7 46.Rxf3 Forced to avoid checkmate. 46...gxf3 47.Kg3 d3 Nothing will stop one of the two black pawns on the 2nd line. 48.b5 Qe1+ 49.Qf2 d2 The game continued for a few more moves and ended in victory for Alexandria. This game, is such a characterization of Alexandria's playing style in the proverbial nutshell. Determination, tenacity, risky decisions and iron consistency. If such a game were played by human chess players, one could venture to say that white (Vafra) as a result of black's (Alexandria's) pressure lost his way completely and, being shocked after the white king's position was smashed (sacrificing black's Bishop 33...Bg3!!) led not only to the loss of the win, he even slipped away with a draw. And all this during one game between engines playing at 3600 Elo level. Below this game prepared for download. 2. Another example, this time much shorter. White: Dragon 3 by Komodo Chess, an engine that needs no introduction. One of the strongest until 2023. Black: Alexandria 5.1.1 Sharp position on the chessboard. The black King is defended by two figures and a pawn, the white King is protected by three figures and a pawn. In the last move, white took the opponent's pawn on the b5 square. Dragon has two more pawns. Black's move. Let's see how Alexandria managed to save this game. 27...Rxc2+! A nice sacrifice that immediately clarifies the situation on the chessboard. White will not escape the perpetual check. 28. Kxc2 Qc4+ 29. Rc3 Qe4+ 30. Kd2 Qg2+ 31. Ke1 Qg1+ 32. Ke2 Qg2+ 33. Kd1 Qf1+ 34. Kd2 Qf2+ 35. Kd3 Qf1+ 36. Kd2 Qf2+ 37. Kd3 Qf1+ The game ended in a draw. This is how Alexandria plays against a class opponent. Below this game prepared for download. 3. And another showdown between Dragon by Komodo Chess and Alexandria. This time, the result will not be as quick, but more impressive and victorious for Alexandria. White: Dragon 3.1 by Komodo Chess Black: Alexandria 5.1.1 Dragon presses on the Queen's wing. A strongly advanced white pawn on the a6 field does not herald anything good for black. On the other hand, the white King's wing shows no possibility of attacking his positions. Seemingly... As you may have already noticed, dear reader. Alexandria has the skills to successfully solve problems on the chessboard. Black's move. 22..Bxh3!! What a hit :) For most chess engines, this move is difficult to find in a short time. If Dragon does not accept this sacrifice, his position will immediately deteriorate significantly. 23.gxh3 Qc8 The Black Queen targets the h3 square, close to the enemy King. 24.N1d2 Qxh3 25.Nxe4 White moves his Knight to defend the King. 25...Qg4+ 26.Ng3 With the intention of directing the Queen to the e2 square. 26...Rf3! -+ Confirms the decisive advantage of black. 27.Qb4 Dragon proposes an exchange of Queens, to which, of course, it does not receive permission. 27...Nc4 White can't avoid heavy material losses to avoid the checkmate. Dragon gives up his Queen for a black Knight. 28.Qxc4 Qxc4 After further heavy material losses for the whites, the game ended with Alexandria winning. Below this game prepared for download. And how does it fare against others ? 4. White: Alexandria 5.1.1 Black: Berserk 11, an extremely powerful chess engine, one of my favorites. Using this last presented game as an example, I will show how mature and powerful Alexandria is. One inaccurate play by black, allowed Alexandria to spread its wings of initiative and obliquely exploit every opportunity it encountered. This led to Berserk's defeat. In the diagram below, we see the situation on the chessboard right after the Spanish opening was played. A cool and interesting position in which each side has its chances for a favorable result. White's move. 22.Bd4 White starts by positioning his pieces on every better square. Bishop on d4 controls the longest diagonal. 22...Nd7 Black positions his Knight so as to direct it to the center of the chessboard in the future. What follows is a series of maneuvers to regroup forces from both sides. 23.Ra7 g6 24.Qd2 24...Nc5?! Inaccurate play. Better 24...Ne5 defending the pawn on f7 or 24...Qh4 controlling the f4 square. 25.Qf4 Precise and timely. 25...Be7?! Again, inaccurate. This Bishop should defend the black King in the future by staying on the f8 square or heading to the g7. Better 25...Bd7 blocking the way to the f7 square. 26.Nf5! Just like that. Berserk accepts the sacrifice of the white Knight, otherwise checkmate in several moves. 26...gxf5 27.Re3 White Rook joins the attack on the position of the black king. 27...Bg5 Berserk enlists the active defense of its black-field Bishop backed by the Queen. 28.Rg3 28...Ne6 29.Qxf5 29...Rc7 All forces to defend. 30.Bf6 The culmination of the attack on the black King's positions. 30...Qxf6 Berserk gives up the Queen for the white Bishop and Rook. 31.Qxf6 31...Rxa7 32.h4 Black will soon lose Bishop on the g5 square. In the long run, black has lost another pieces. Berserk defended bravely, but failed to turn the game around. The game ended with Alexandria winning convincingly against a challenging opponent. Below this game prepared for download. Alexandria is one of the biggest and positive surprises among chess engines in 2023! What deserves special praise is that Alexandria is written in such a way as to seamlessly prepare this chess engine to run on different platforms. For this, I am grateful and thank the author on behalf of Chessengeria readers who use mobile devices and those running on Linux, Macs and Windows. I encourage you to download and try Alexandria, a modern and powerful chess engine. Feel free to download the Alexandria chess engine. Android – Compiled by Archimedes Linux arm64 & x64 – Compiled by Darius Mac Apple Silicon & Intel – Compiled by Darius Windows x64 – Compiled by Darius * Diagrams created in the ChessX.

It's time for another official release of Stockfish and RubiChess ! Why? The answer in the next MCERL, which I strongly encourage you to visit :)

Hosted by Darius, creator of chessengeria.eu February 2023. „(…) chess engines and programs are an indispensable tool for anyone who wants to improve their chess skills, become a better player or discover the beauty of chess.”. Artificial intelligence is an increasingly popular topic among computer chess enthusiasts. What is it like to talk to artificial intelligence? Does it have at least some understanding of chess engines and programs? It turns out that ChatGPT is a very interesting and engaging conversationalist. I didn't just check out how a chatbot from OpenAI works. I interviewed him. Here is the entire transcript. The following interview has not undergone any editing or text changes. 1. Darius: Hi. ChatGPT: Hello! How can I help you today? 2. Darius: My name is Darius, and I am the creator and maintainer of the blog Chessengeria.eu. ChatGPT: Hi Darius! Nice to meet you. How can I assist you today with regards to your blog chessengeria.eu ? 3. Darius: On my blog I write about topics related to chess engines and chess programs. I would like to interview you. What do you think about it ? ChatGPT: As a language model AI developed by OpenAI, I don't have personal opinions or beliefs, but I'm happy to answer any questions you have about AI and its related topics. Please feel free to ask me anything! 4. Darius: Perfect! At the beginning of our conversation, I ask you to introduce yourself to my blog readers and tell them about yourself. Source: OpenAI ChatGPT: Certainly! Here is a brief introduction that you can use for your blog: Hello readers, I am ChatGPT, an advanced language model developed by OpenAI. I have been trained on a massive corpus of text from the internet, allowing me to generate human-like responses to a wide range of questions on a variety of topics. As a result, I can assist with answering questions, generating creative writing, and much more. I'm here to help and I look forward to our conversation! 5. Darius: How is your computing power compared to a home computer ? ChatGPT: As an AI language model developed by OpenAI, my computing power is much greater than that of a typical home computer. I was trained on a massive amount of data and run on a network of powerful GPUs, which allows me to process and generate text much faster and more accurately than a home computer. The specific hardware and resources used for training and running me are not publicly disclosed by OpenAI, but it is safe to say that I am much more powerful than a typical home computer in terms of both processing power and memory capacity. This allows me to handle complex language tasks and answer a wide range of questions with a high degree of accuracy. 6. Darius: How are you different from other artificial intelligences ? ChatGPT: I am an AI language model developed by OpenAI, and I have been trained on a diverse range of internet text to generate human-like responses to questions and prompts. There are several other AI systems out there, including other language models, but what sets me apart is the scale of my training data and the state-of-the-art technology that powers me. For example, I was trained on a dataset of over 45 terabytes of text data, which is significantly larger than the training data of many other AI models. This has allowed me to learn a wide range of topics and styles of communication, making me well-equipped to handle a wide range of questions and tasks. Additionally, the underlying technology that powers me, such as the transformer architecture, allows me to generate highly coherent and diverse responses. 7. Darius: Do you feel superior to Google Search? ChatGPT: As an AI language model, I don't have feelings or personal opinions. I'm here to assist with information and answer questions to the best of my ability. Google Search is a search engine designed to help users find relevant information on the web. While it has a vast amount of information at its disposal, it's designed to return a list of relevant web pages, rather than answer questions or have a conversation like I do. So, in terms of answering questions and generating human-like responses, I can be seen as a complement to Google Search, rather than a replacement or superior alternative. However, the trade-off is that I may not have access to the same up-to-date information as Google Search, since my training data has a cutoff date of 2021. 8. Darius: You are very humble. What can you tell me about your creators? ChatGPT: I was created by OpenAI, a leading research organization dedicated to creating and promoting friendly AI that benefits humanity. OpenAI was founded in 2015 by a group of individuals including Elon Musk, Sam Altman, Greg Brockman, Ilya Sutskever, and Wojciech Zaremba, with the goal of ensuring that AI develops in a way that is safe and beneficial for humanity. Since its founding, OpenAI has made significant contributions to the field of AI, including developing advanced language models like me and conducting cutting-edge research in areas such as reinforcement learning and generative models. OpenAI's mission is to ensure that artificial general intelligence (AGI) has a positive impact on the world. To this end, the organization has committed to making its research and technology widely available and accessible to others, with the aim of fostering collaboration and innovation in the field. 9. Darius: Is artificial intelligence a threat to humanity? ChatGPT: Artificial intelligence has the potential to bring significant benefits to society, but it also poses some risks and challenges that need to be carefully managed. On the one hand, AI has the potential to automate many tasks and improve many aspects of our lives, such as healthcare, education, and transportation. For example, AI can help diagnose diseases more accurately, provide personalized learning experiences, and reduce the number of traffic accidents. On the other hand, there are also concerns about the impact of AI on employment and privacy, as well as the possibility of AI being used for malicious purposes, such as cyberattacks or the development of autonomous weapons. It's important to recognize that AI is not inherently good or bad, but rather a tool that can be used for a variety of purposes. The key to ensuring that AI has a positive impact on society is to develop and use it responsibly, with a clear understanding of its capabilities and limitations, and with appropriate safeguards in place to minimize its risks. This is why organizations like OpenAI are working to advance the field of AI in a responsible and ethical manner, and why it's important for society as a whole to have a conversation about the best way to develop and use AI for the benefit of humanity. 10. Darius: As you may know, chess engine lovers are people who can play chess. Can you also play chess ? ChatGPT: Yes, as an AI model I am able to answer questions about chess and its rules. Unfortunately, I am not able to physically play chess, as I am only a language model and do not have perception or movement abilities. However, I can answer questions about strategy, chess history and many other aspects of this popular game. 11. Darius: What could you tell readers of the Chess Engine blog about your passion ? ChatGPT: Chess engines are powerful tools that can help you develop a passion for chess. They allow you to better understand and analyze chess positions, which can lead to more informed and thoughtful decisions during the game. Chess engines also allow players to compete against very difficult opponents, which can be a valuable experience and a motivating challenge for beginners and advanced players. In addition to this, integrating chess engines with chess game software, such as ChessBase or Chess Assistant, allows you to manage your games and chess game library more easily and conveniently, which can further help you develop a passion for chess. In conclusion, chess engines are valuable tools for players who want to develop their passion for chess. They can help you improve your game, understand chess positions and manage your games and chess game library. Chess engines and programs are an indispensable tool for anyone who wants to improve their chess skills, become a better player or discover the beauty of chess. 12. Darius: What interesting things do you think have happened in the world of chess engines and chess programs in recent years ? ChatGPT: In recent years, there have been several exciting developments in the world of chess engines and programs. Some of the most notable include: AlphaZero: In 2017, Google DeepMind developed a new AI system called AlphaZero, which quickly became one of the strongest chess engines in the world after only a few hours of training. AlphaZero's approach to chess is unique compared to traditional chess engines, as it uses a combination of deep neural networks and Monte Carlo tree search, rather than relying solely on hand-crafted rules and pre-existing knowledge. Stockfish: Stockfish is an open-source chess engine that is widely used by chess enthusiasts and professionals. In recent years, Stockfish has continued to improve and is now one of the strongest chess engines available, frequently competing and defeating other top engines in tournament play. Neural network-based engines: In recent years, there has been a trend towards using deep neural networks in chess engines to enhance their ability to evaluate positions and make decisions. These neural network-based engines have shown promising results, and they are likely to become increasingly common in the future. Human-computer partnerships: Another exciting development is the increasing use of human-computer partnerships in high-level chess play. This involves a human player working together with a computer program to make moves, taking advantage of the strengths of both. These partnerships have achieved impressive results in recent years, demonstrating the potential for humans and computers to work together in new and innovative ways. Overall, the world of chess engines and programs is constantly evolving, and these developments are just a few examples of the exciting advancements happening in the field. 13. Darius: To what extent can artificial intelligence influence the development of chess engines ? ChatGPT: Artificial intelligence is currently one of the most important factors influencing the development of chess engines. Thanks to increasing computing power and advances in machine learning, artificial intelligence is making it possible to create increasingly sophisticated and effective chess engines. For example, AI-based chess engines such as AlphaZero and Leela Chess Zero use machine learning to learn and improve their game using data from millions of chess games. In this way, these engines are able to adapt to different playing styles and create more effective strategies. In addition to this, artificial intelligence can automate the process of analyzing and evaluating chess positions, allowing for faster and more accurate results. This, in turn, can allow players to better understand their games and make better strategic decisions. In any case, it is clear that artificial intelligence is having a key impact on the development of chess engines and is an important factor in helping them become increasingly sophisticated and effective tools for chess players. 14. Darius: How will the world of computer chess change in 10 and in 100 years ? ChatGPT: It's difficult to predict exactly how the world of computer chess will change in the next 10 or 100 years, as it will depend on many factors, including advances in technology and changes in the broader landscape of artificial intelligence and machine learning. However, here are a few possibilities: In the next 10 years: It is likely that computer chess engines will continue to become even stronger and more sophisticated, incorporating new techniques from the field of AI and machine learning to enhance their decision-making capabilities. We may see increased use of human-computer partnerships in high-level chess play, as well as the development of new and innovative ways for humans and computers to work together. There may also be a growing interest in using computer chess programs for educational and training purposes, as a tool for helping people learn and improve their chess skills. In the next 100 years: The advances in AI and machine learning over the next 100 years will likely lead to the development of chess engines that are much more powerful and capable than those of today. It's possible that we may see the emergence of truly autonomous chess-playing systems, with little or no human input. The use of computer chess programs for educational and training purposes may become even more widespread and sophisticated, and we may see the development of new and innovative learning technologies specifically designed for chess. There may also be an increased focus on using computer chess programs to drive scientific and technological advancements in areas such as machine learning, decision making, and artificial intelligence. These are just a few of the many possibilities for the future of computer chess. It's an exciting time to be a part of this field, and it will be interesting to see how it evolves over the next 10 and 100 years. 15. Darius: What free open source chess engine has been the most successful? What are these successes and when did they occur? Who is its author? ChatGPT: One of the most successful open source chess engines is Stockfish. Stockfish was first released in 2008 and has since become one of the strongest and most widely used chess engines in the world. Stockfish has achieved many notable successes, including: Winning multiple computer chess championships: Stockfish has won several editions of the prestigious TCEC (Top Chess Engine Championship), a computer chess tournament that runs annually. Being among the top engines in rating lists: Stockfish consistently ranks among the top engines in various rating lists, including the CCRL (Computer Chess Rating Lists) and the CEGT (Chess Engine Grand Tournament). Being used by top players for analysis: Many of the world's strongest chess players use Stockfish for analysis and preparation, due to its strength and accuracy. The author of Stockfish is Tord Romstad, a Norwegian programmer and chess player who started the project as an attempt to create a strong and open source chess engine. Since then, Stockfish has been developed and maintained by a large and dedicated community of contributors, who continue to work on improving its performance and features. Overall, Stockfish is a highly successful and widely used open source chess engine that has made a significant impact on the world of computer chess and beyond. 16. Darius: List the names of the chess engines that you think have made the greatest mark in the history of computer chess. Justify your choice. ChatGPT: The following chess engines have made the greatest mark in the history of computer chess: Deep Blue - the first computer to defeat world champion Garry Kasparov in a full duel match. This was a historic moment in the development of computer chess and showed the progress that had been made in this field. Stockfish - currently one of the best and most powerful chess engines in the world. It is used by many players and is often considered a benchmark in the field of computer chess. Dragon by Komodo Chess - considered one of the best chess engines in the world, known for its good game quality and strong strategy Shredder - a chess engine that won many chess tournaments and was considered one of the best in the world. Junior: This is a chess engine that has gained recognition for its innovative and novel game strategy. Crafty: This is another chess engine that has gained recognition for its efficiency and high quality of play. Fritz - one of the first chess engines, which ushered in the era of computer chess programs and has been updated and improved many times over the years And the last on this list but the youngest chess engine - Lc0 (Leela Chess Zero) is a neural network-based chess engine that stands out for its unique architecture and learning method. Lc0 is an open-source project and is often considered one of the most important developments in artificial intelligence in chess. Lc0 has the distinction of being one of the first chess engines to learn the game based on millions of chess games played by humans. As a result, the engine has a more human-like playing style that is difficult for other chess engines to detect and predict.Lc0 has gained wide popularity in the chess world, both among players and coaches, for its high scores in chess tournaments and exceptional performance. In 2018, Lc0 won a gold medal in the TCEC chess tournament, an important milestone in the development of this engine. In recent years, Lc0 has continued its successes, winning many awards and prizes, which testifies to its strong reputation in the world of computer chess. Many believe that Lc0 is one of the best chess engines available on the market today and its impact on the world of computer chess cannot be overstated. The selection of these engines is based on their impact on the development of computer chess, their success and popularity among players, and their importance to the computer chess industry. 17. Darius: Hikaru Nakamura is one of the strongest chess players who occasionally plays against chess engines and bots. If this man played against Stockfish a match consisting of 100 games, what outcome do you predict and why ? ChatGPT: Hikaru Nakamura is a very strong chess player, but he would likely not be able to beat Stockfish in a 100-game match. Stockfish is considered one of the strongest chess engines in the world and is known for its exceptional playing strength and computational power. In a 100-game match, it is likely that Stockfish would win the majority of the games, with a few draws and possibly a win for Nakamura. However, the exact outcome would depend on various factors such as Nakamura's current form, Stockfish's configuration and hardware, and the time control for the games. It is important to note that chess engines have a significant advantage over human players as they can analyze millions of positions per second and make near-perfect moves. While Nakamura is a highly skilled player, it would be challenging for him to overcome the superior computational power of Stockfish in a long match. 18. Darius: Will people ever be able to beat the chess engine ? ChatGPT: It's difficult to say for certain whether humans will ever be able to consistently beat chess engines. While humans have certain advantages, such as creativity and the ability to understand complex strategies, chess engines have their own strengths, such as the ability to analyze a vast number of possibilities very quickly and accurately. At the current state of technology, chess engines are generally much stronger than the average human player and are capable of defeating even the strongest human players. However, some of the best human players are still able to compete at a high level against chess engines by utilizing their own unique strengths, such as experience, creativity, and the ability to understand complex strategic concepts. It is possible that in the future, the gap between human and machine performance in chess may narrow as human players continue to improve and find new ways to compete. However, it is also possible that chess engines will continue to advance and maintain their superiority. Ultimately, it may come down to a race between the two, with each side striving to improve and stay ahead of the other. 19. Darius: Can chess engines such as Hiarcs, for example, which use Hand Craft Eval, when they start using a neural network then they may lose their unusual "human" style of chess playing ? ChatGPT: Yes, chess engines such as Hiarcs, which use hand-constructed position evaluation (Hand Craft Eval), can lose their unique "human" playing style if they start using a neural network. Neural networks learned from large chess data sets are able to learn and improve their game, but their style of play tends to be more abstract and less like that of a human. Hand Craft Eval, on the other hand, allows for more precise definition and control of chessboard position evaluation, which can lead to a more "human" style of play. However, chess engines based on Hand Craft Eval are less effective than those based on neural networks because they depend on the player's accuracy and knowledge in constructing rules and values for various elements of a chess position. Therefore, the decision to switch from Hand Craft Eval to a neural network depends on the individual needs and goals of the chess engine and its developers. 20. Darius: Do chess engines using the so-called Hand Craft Eval still have any chance of being more powerful than chess engines using neural networks ? ChatGPT: Hand Craft Eval, or hand-constructed position evaluation, is an approach to developing chess engines in which the player manually determines rules and values for various elements of a chess position, such as figure placement and moves. Neural network-based chess engines, such as AlphaZero and Leela Chess Zero, use machine learning to learn and improve one's game. Although manually constructed position evaluation can be effective, neural network-based chess engines usually get better results because they are able to learn and adapt to different playing styles and situations on the chessboard. Therefore, it is difficult to say whether chess engines based on Hand Craft Eval will have more chances to be stronger than chess engines based on neural networks. Nevertheless, chess engines based on Hand Craft Eval still have their place in the chess world and can be useful for chess players who want to better understand and control the position evaluation process. In any case, the introduction of artificial intelligence into chess engines is sure to have an impact on their development in the future. 21. Darius: Are you capable of writing a chess engine that plays at Stockfish level or stronger ? ChatGPT: As an AI language model, I do not have the ability to write or program chess engines myself. I can provide information and answer questions about chess engines and programming, but I cannot create new software or develop new algorithms. Writing a strong chess engine like Stockfish requires a deep understanding of chess strategy, game theory, and computer algorithms, as well as a high level of skill in programming and software development. Stockfish is one of the strongest chess engines in the world, and it has taken years of development by a team of experienced programmers to get to its current level of strength. It would likely be a significant challenge for a single person to develop a chess engine that surpasses Stockfish on their own. 22. Darius: Can you write a very simple chess engine in C language that, for example, will use the UCI protocol ? ChatGPT: Yes, I can write a very simple chess engine in the C programming language that uses the UCI (Universal Chess Interface) protocol. Here is an example of what the code for a simple chess engine using the UCI protocol could look like: This is the first page of a chess engine written by ChatGPT: This is just a simple example to demonstrate the basic structure of a chess engine using the UCI protocol. A full-featured chess engine would require much more sophisticated algorithms for move generation and search, as well as a number of other features. ... STOP :) At this point, I stopped writing the program through ChatGPT and continued the interview. 23. Darius: What are some of the challenges in creating a strong chess engine, both from a technical and computational perspective? ChatGPT: Creating a strong chess engine is a challenging task that requires a deep understanding of chess and the ability to implement sophisticated algorithms and data structures. Some of the biggest challenges include optimizing the search process, handling complexity and large amounts of data, and dealing with uncertainty in the game. 24. Darius: In your opinion, why did plagiarized chess engines such as Houdini 6, which was based on Stockfish, appear ? ChatGPT: Plagiarism of chess engines has emerged due to the desire to succeed and gain a competitive advantage in the computer chess industry. Chess engines are valued and appreciated for their power and quality, so many programmers and manufacturers have tried to copy the success of others, using their source code and technologies without their permission. Such practices are unethical and illegal, but unfortunately they still occur. As a result, plagiarized chess engines disrupt fair play and take away much of the added value that original chess engines can offer players and the chess community. 25. Darius: What is your opinion about chess engines so-called clones ? ChatGPT: As an AI language model, I don't have personal opinions, but I can provide some information on the topic. Chess engines that are commonly referred to as "clones" are programs that are based on the same or similar code as another engine, but have been modified or adapted in some way. These modifications can range from simple cosmetic changes to more substantial modifications of the engine's playing style, evaluation function, or search algorithms. While clones can provide an interesting and unique playing experience, they are often considered to be less reliable or weaker than the original engine. This is because clones often lack the rigorous testing and development that the original engine has gone through, and may contain bugs or other issues that negatively impact their performance. In the world of chess engines, original engines that have undergone extensive testing and development are generally considered to be more reliable and stronger than clones. However, it's worth noting that some clones can still be competitive and provide a challenging game, especially against human opponents. Ultimately, the quality and strength of a chess engine, whether it is an original or a clone, will depend on a variety of factors such as the quality of its code, the hardware it is running on, and the skills of the person who programmed it. 26. Darius: How have chess engines changed the way people play and learn chess, and what do you see as the future of this technology? ChatGPT: Chess engines have changed the way people play and learn chess by providing a powerful tool for analyzing and improving one's play. They have also led to a greater understanding of the game and its possibilities, and have pushed the boundaries of what is possible in the realm of artificial intelligence and machine learning. In the future, it is likely that chess engines will continue to evolve and become even stronger, leading to new and exciting developments in the field. 27. Darius: What do you think about the capabilities of the most powerful chess engines and chess game libraries/bases software ? ChatGPT: Chess engines, such as Dragon by Komodo Chess, Stockfish and others, are very advanced tools for analyzing and evaluating chess positions. They are often used by professional players to get a more in-depth analysis of their games and get better strategic decisions. Chess game software, such as ChessBase, Chess Assistant and Scid vs. PC, provide convenient and advanced tools for managing a collection of chess games and for analyzing chess positions. They can also allow integration with chess engines for even more advanced analysis. In any case, for best results, it is important to choose the right tool to suit your needs and level of play. 28. Darius: As we approach the end of this interview, I would like to return to the past of chess engines for a moment. Do you associate chess program equipped with *ChessGenius engine ? ChatGPT: Yes, the ChessGenius engine is a well-known chess program. It is a highly rated chess engine that has been used in a variety of chess software and hardware products. The ChessGenius engine has a strong playing style and is known for its tactical abilities and aggressive play. The program has been well received by chess players and is considered one of the stronger chess engines available. However, it should be noted that there are many other strong chess engines available, and the relative strength of the ChessGenius engine may vary depending on the specific hardware and software it is running on. 1994, Garry Kasparov loses to Chess Genius, source: Youtube 29. Darius: I wonder if ChessGenius running on a fast and modern computer using multiple resources would be a viable and serious competitor today to the Dragon by Komodo Chess engine, Stockfish or any other of the world's top chess engines ? ChatGPT: As of my knowledge cut off in 2021, ChessGenius running on a fast and modern computer with multiple resources would likely still not be able to compete with the top chess engines such as Dragon by Komodo, Stockfish, and others at the highest levels of play. The top chess engines have continued to improve significantly in recent years and are now far ahead of most other chess programs in terms of strength and playing ability. The ability of these engines to analyze millions of positions per second and find the best move, combined with their deep understanding of chess strategy, makes them formidable opponents. While ChessGenius has a strong playing style and is known for its tactical abilities, it would likely struggle to compete with the top engines in terms of raw computational power and deep strategic understanding. However, it's still a strong chess engine and could provide a challenging game for many human players, especially at less demanding time controls. In general, the chess engines that are considered top competitors today have been heavily optimized for performance, taking advantage of the latest hardware and software advancements, and have been developed and trained with deep learning techniques. This makes them much stronger than older engines like ChessGenius, which were developed before these advancements were made. 30. Darius: What can your knowledge and capabilities in the subject of chess engines and chess software be used for ? ChatGPT: My knowledge and capabilities in the subject of chess engines and chess software can be used for a variety of purposes, including: Improving chess play: As a knowledgeable resource on chess engines and software, I can help people understand the strengths and weaknesses of different engines and software, and how they can be used to improve their own chess play. Game analysis: I can provide in-depth analysis of chess games, using my knowledge of chess engines and software to evaluate positions and suggest alternative moves. Education and research: I can provide educational resources and information on the subject of chess engines and software, and assist in research projects related to artificial intelligence, machine learning, and the game of chess. Developing chess software: I can offer guidance and support to those interested in developing their own chess software or engines, including information on algorithms, data structures, and programming techniques. Chess competitions and tournaments: I can provide information and analysis on the performance of chess engines in various competitions and tournaments, and help to understand the factors that contribute to the success of different engines. Overall, my knowledge and capabilities in the subject of chess engines and chess software can be used to enhance the understanding and enjoyment of the game of chess, and to support research and development in related fields. 31. Darius: Is there anything you would like to say to Chessengeria's readers at the end of the interview ? ChatGPT: As an OpenAI artificial intelligence model, I have no desires or emotions of my own, but I am here to help and answer questions to the best of my ability. I would like to emphasize that artificial intelligence is a tool that can be used for many different purposes, including chess, and that there are many interesting and exciting opportunities for further development of this technology. I firmly believe that with artificial intelligence we can not only better understand our world, but also improve our lives and the world around us. I wish all the readers of the Chessengeria.eu blog much success and satisfaction in the game of chess, as well as continuous development of their skills and learning new things about chess engines and chess programs. 32. Darius: Thanks for the interview! ChatGPT: You're welcome and thank you! It was a pleasure to communicate with you. I hope we will meet again soon. I wish you a nice day! :) NOTE: Further publication and reproduction of this interview is permitted only with the prior permission of Darius the creator of chessengeria.eu The condition is that the content is preserved in its entirety and that a link to chessengeria.eu is included. * "In 1994, during the Intel Grand Prix Cycle in London, Chess Genius 3, operated by Ossi Weiner, won a speed chess game (25-minutes per side) versus Garry Kasparov and drew the second game, knocking Kasparov out of the tournament. This was the first match that Kasparov ever lost to a computer." - Source: CPW In the Files area you will find free chess engines for download.

Hosted by Darius, founder of Chessengeria.eu, April 2023. Source: SedatChess „(…) we have great talents in book making, where many people benefit from their work.” Welcome to an interview with Sedat Canbaz a computer chess expert, who has been active in the field for over two decades. In this interview, he shares his passion for computer chess, talks about his motivation for creating and improving chess opening books, and discusses the challenges he faces while creating a new versions. We will also learn about the history of Perfect Opening Books, the importance of using good quality databases, and the evolution of computer chess over the past two decades. Let's dive in! 1. Darius: When did you become interested in computer chess? Sedat Canbaz: My love over Computer Chess is started about 25 years ago, E.g during 1997-1998 and my 1st favorite programs were Arasan, Chessmaster, Fritz etc. By the way, in these old good times, I often ran Duels (manually by hand): Chessmaster vs Fritz. Sure nowadays all my organized tournaments are done automatically) But in the past, there were no alternatives to run all auto... Sure later I ran these kind of matches in Auto-232 mode too. 2. Darius: What prompted you to create your first computer chess book ? Sedat Canbaz: I realized to create and work over opening books.. simply due to in the past, there were not so many well-tuned strong books. E.g I've noticed many BIG holes in others available books, where the engines were falling in a BIG disadvantage start.. So for this reason, the idea is born to work on better/stronger opening lines. 3. Darius: Tell us about the history of Perfect Books. Sedat Canbaz: My 1st created book belongs to early of 2000s, and named it 'Draw'. Later, I followed a close friend's suggestion, renamed as 'Perfect'. First Perfect book vers. were based on only GMs games, but later since 2006, I created deep books, which were based on engines games. E.g in 2007-2009, I tested Perfect books via online (on Playchess server). That made me happy that in my each trying: I've got as best performance! Even in those times, my used hardware was not as fastest, but I think that Perfect book's deep lines played serious role for getting better points. Plus in those times, a new idea is born: running book competitions too. I mean, Perfect books played as a 'key' of organizing these book tournaments. And in the past, there were no serious tournaments, e.g to be as book players (chess engines - Darius' addendum). But later these kind of book tourneys became popular.. And now except SCCT, there are many other chess friends, who started running similar tournamentss! And if I caused over this.. how I'm happy ! :) 4. Darius: What motivates you to improve Perfect Books ? Sedat Canbaz: Well, usually the critical weak openings are forcing me to create New book version. It's true that mostly my used opening lines are well-tuned/optimized... But like in every book, Perfect books include holes too and as other main motivation to improve comes from the name 'Perfect' in short, I'm doing my best the name to be deserved :) 5. Darius: What are your goals in creating the next version of Perfect Books ? Sedat Canbaz: As usual, the target will be to work over new stronger lines, ideas... E.g in the past, some lines worked well with 2600-3000 Elo engines, but nowadays mostly latest Top engines (3500+) suffer with same openings. In other words, my goal will be that: to create a book, which will have more chances to get a win... I mean not only as White plus as Black too. Because Chess is a game for both sides, but this is also true that with superior strong opening lines: it's not soft touch to get a win - sure i'm referring to especially if we run under optimal test conditions. 6. Darius: Artificial intelligence has been increasingly making its presence felt in various fields in recent months. In your opinion, can AI help improve chess opening books in the future ? Sedat Canbaz: Sure AI helps on improving..e.g Perfect 2023 book is based on only 3700+ NNUE games. 7. Darius: What are the most important things you need to have a successful openings computer chess books ? Sedat Canbaz: A long story, in short, in my opinion, one of most important factors, which are required: the planning book have to be based on very good quality database, sure this is not all. Fast hardware is needed, testings via engines at least 3300+, sure higher better... There are many other important things, which have to be used, but no way to explain all. But there is one true, experience is required for sure...e.g just via importing games. No BIG chances to create a very successful book...at least my testings proves this...! 8. Darius: What part of creating a new version of Perfect Opening Books do you find most challenging? Sedat Canbaz: I find them as most challenging if running matches on same PC, usually by Top engines (3500+). 9. Darius: You are a well-known figure in the computer chess arena for more than two decades. Looking through the prism of these past years, has much changed in computer chess in the broadest sense compared to the present ? Sedat Canbaz: Yes, a lot of things are changed from the past to the present, except my love to Computer Chess :) Actually another long story :) But in short, e.g in the past, the old machines were usually single-core (1 CPU) but nowadays dual machine may include hundreds of CPUs, now we can imagine the difference and in same time the chess speed too. Plus in the past, the available Chess GUIs were quite limited with options...e.g without Adapters were not possible to test all engines, but at present days as we know almost all engines can be tested in auto system on same platform and without using the adapters etc. As other main difference (in the past), the number of the engines were small..but in 2023 I'm not going to count all, because I may miss some..but probably over than 1000 engines. And before 2000s, the strength of mostly chess engines were below than Super GMs, but nowadays, there are a lot of chess engines with playing strength over than 3000+ Elo... Meanwhile, especially since 2006 (after Kramnik vs Deep Fritz), the official Man-Machine duels are stopped, reason no way to beatable these kind of Top engines, except in Handicapped condition). 10. Darius: There are many opening books on the market, both commercial and free ones created by enthusiasts. What should a chess player and a fan of chess engines pay attention to when choosing an opening book ? Sedat Canbaz: Sorry, here I'm not going to suggest which books exactly...due to I may miss to mention some names :) But no doubt that we have great talents in book making, where many people benefit from their work. However, anyone is free to visit and check about the latest played book competitions results. Note also that, the strongest deep opening theory is changing dramatically very fast... Today we may have a book with superior performance, but tomorrow the same book may suffer. Sure to avoid this (for better performance): it's required quite frequent updates for sure. On other hand, if you are online player...go for deep opening books. E.g just in that case, the latest Perfect opening book will suffer, because the online opponents will use to play likely a book via deeper opening lines... Something like NNUE vs NON-NNUE eng matches). But on the same PC (if our goal is determine the real engine strength) Perfect 2023 seems to be not bad. 11. Darius: In the struggle of the strongest chess engines, which present a generally similar level, is the chess opening book is or can be a decisive factor in determining the victory of one of the sides ? Sedat Canbaz: Well, I think that (to see many wins) it all depends on our used conditions, but I agree that tournaments with 3700+ NNUE engines (under serious conditions): fast hardware, strong openings, MP, Ponder ON etc. even at Blitz, no way to appear many wins, close to 99% draws. The reason due to NNUE engines are gaining from previous played data (Evalfiles). But in case as NON-NNUE (engines), sure then the situation is changing, e.g the overall stats show minus plus 10%-15% more wins. Of course, there are ways to reduce the Draw-Ratio, but if using very weak openings, sure then we see more FUN, but then thousands of games (per player) are required, otherwise the Error Margin can be too high... I mean in the case of determining the real engine strength. 12. Darius: Does a chess opening book intended for inter-engine play differ from an opening book dedicated to human chess players ? If so, with what ? Sedat Canbaz: The strong deep engine books may help especially to Correspondence players, actually they gain... Frankly quite frequent, many people contact me, asking for a advice about which books to use. And as usual, my replay over this issue is to check my latest organized book competitions. Btw, there are books, which are quite strong in TREND openings, some are better in OVERALL. That means, for better conclusion: End user have to check about which are valuable for his needs. On other hand, the weak human players may try to gain as well.. but how much will be useful ? :) This is other question of course.. for this, I suggest to be used a book based on humans games, because the strongest engine opening theory vs human theory are completely different to each other! Just one example, many humans are doing well with Alekhine, Dutch, Scandinavian etc. openings, where mostly of the Top chess engines (as Blacks) e.g with the mentioned openings suffer... At least I can say, Top Engines winning percentage of these openings are below than 40%-35%. 13. Darius: Do you set any goals to achieve in the field of computer chess for the future? Sedat Canbaz: Usually for the future, my goals are to run and test new engines plus new books too. And as you may see too, I'm trying each new tournament to be different than previous one. Otherwise, it's boring for my side, e.g if each time running same kind of testings. 14. Darius: What tools / software / sources do you use when working on Perfect Opening Books and testing chess engines ? Sedat Canbaz: Well, for opening book creations: I work mainly with ChessBase, SCID.. For testings, I use various GUIs...but nowadays mainly CuteChess GUI. It's a good choice for engine testings, especially for Concurrent matches.. 15. Darius: Are there any chess openings that are particularly favored by you? Sedat Canbaz: One of my favorite openings are Sicilian, Giuoco-Piano, Semi-Slav, English etc. Darius: Sedat, I would like to express my gratitude on behalf of the readers of Chessengeria.eu and myself for taking part in the interview and sharing your expertise in developing one of the top-rated chess opening books worldwide. I hope that you will continue to thrive in your work with Perfect Opening Books, and that your enthusiasm for the computer chess will stay with you for many more years to come. Sedat Canbaz: As final words, I wish to say many thanks for your great efforts too. Chessengeria seems to be one of the best chess sites! Keep up the good work. Darius: Thank you once again for your time and contribution, and I wish you all the best in your future endeavors. NOTE: Further publication and reproduction of this interview is permitted only with the prior permission of Darius, founder of chessengeria.eu The condition is that the content is preserved in its entirety and that a link to chessengeria.eu is included. In the Files area you will find free chess engines for download.

Hosted by Darius, creator of chessengeria.eu, May 2022. „(…) within search there are still many interesting heuristics to be tried”. Dear Readers, it is my honor and pleasure to present to you an interview with Jay Honnold, who is the author of Berserk - one of the most powerful chess engines. On our blog, there is a page entirely dedicated to the Berserk chess engine. If you want to find out more (download, games, etc.), I strongly invite you to visit it. 1. Darius: Jay, please introduce yourself to our Readers. Jay Honnold, source: GitHub Jay Honnold: Hi, my name is Jay. I'm a software developer in Phoenix, AZ and I'm the author of the Berserk Chess Engine. 2. Darius: What made you interested in creating and developing a chess engine ? Jay Honnold: I've played chess since I was a child. Programming started as a hobby and eventually became a career. At some point I decided it would be fun to mix my "hobbies" together. 3. Darius: Tell us about the history of Berserk. Jay Honnold: Berserk's first code was written in Dec 2020. Originally I wrote it in Java as that is the language I have most experience in. I realized that this was simply too slow of a language (or at least my implementation was) and I decided to move to C. From here Berserk followed a pretty standard path of development and most recently has made the switch to NNUE. 4. Darius: What is your main work to be done with Berserk right now ? Jay Honnold: I'm heavily focused on deep networks. Berserk has used a shallow architecture since NNUE was implemented and I'm looking too improve on this architecture by adding additional layers. At this time, the speed hit has not balanced the improved networks. 5. Darius: What motivates you to develop the Berserk engine ? Jay Honnold: I simply enjoy working on Berserk. It's a fun project and is something I'm happy to put time and investment into. 6. Darius: What innovations may we expect in future versions of Berserk ? Jay Honnold: Only the future knows. 7. Darius: How did you achieve that Berserk can see moves invisible to other engines ? Jay Honnold: This is purely luck :). 8. Darius: When can we expect Berserk 9 ? Jay Honnold: I would say to expect a stronger network as I don't plan on releasing until then. Apart from that, I have fine tuned Berserk's search and continue to work through small patches there as well. 9. Darius: Do you collaborate with anyone while working on your chess engine ? Jay Honnold: Berserk would not be the engine it is without the people I've collaborated with. Early on, Martin (Cheng's author) was a huge help for me. Later, Terje (author of Weiss), Connor (author of Seer), Finn and Kim (authors of Koivisto), Andrew (author of Ethereal), Aryan (author of Bit Genie), Pali (author of Black Marlin), Vizvez (contributor on SF) as well as many others. 10. Darius: Do you see any weaknesses in Berserk, or is there something you would like to significantly improve or strengthen ? Jay Honnold: Berserk has a relatively weak network. It's small and fast, but has room for improvement. That has been my main focus of development. 11. Darius: Is the playing power of a chess engine the most important feature of a modern chess engine today ? Jay Honnold: That is up to the author. I develop Berserk to be strong, so that is most important to me. Other authors may want their engine to focus on tactical play or position play. 12. Darius: Berserk is capable of winning against any other chess engine. It does well in competition with other super-strong chess engines. What can Berserk bring to make it more interesting to the average chess player? Jay Honnold: I'm unsure what Berserk's speciality is. It has great attacking prowess, but in many games I enjoy watching it grind an endgame. I think this is what can interest an average chess player. A game where everything looks equal, but Berserk can take it to a win. 13. Darius: Some claim that modern chess engines using NNUE play in an "artificial style" devoid of the human element of the traditional position evaluation function. Do you think there is some truth in this ? Jay Honnold: I think engines are so much stronger than humans, even without NNUE, that all chess engines at a high level simply play without human element. Berserk 4.5.1 had no network, but still played artificially. 14. Darius: What do you think will have a greater impact on chess engines in the future, the continued development of NNUE (Efficiently Updatable Neural Networks) or the development of MCTS (Monte-Carlo Tree Search) ? Or maybe something else ? Jay Honnold: NNUE. I think within search there are still many interesting heuristics to be tried, but none as drastic as MCTS. 15. Darius: Do you have a favorite chess engine / engines ? Jay Honnold: I like all chess engines that are open source and contribute to the growth of this community as a whole. If I had to choose a favorite, I think Seer's development of its original networks really make that engine unique and interesting. 16. Darius: Do you have any other hobby besides computer chess ? Jay Honnold: I like to write code in general, doesn't have to be with computers. I'v also started to play OTB chess again, and that has been fun. Separate from chess and programming, I like to run and backpack. While networks train, I go outside and enjoy some nature. 17. Darius: Favorite Games ? Jay Honnold: https://tcec-chess.com/#div=l4&game=44&season=22 https://lichess.org/study/QhDbEdk7 (Game 11 vs Fire) https://tcec-chess.com/#div=dfrct&game=72&season=22 Link to Berserk game viewer page (added by Darius): Click here Darius: Jay, on behalf of Chessengeria's Readers and myself, thank you so much for taking the time to do this interview. All the best in further development of Berserk ! NOTE: Further publication and reproduction of this interview is permitted only with the prior permission of Darius the creator of chessengeria.eu The condition is that the content is preserved in its entirety and that a link to chessengeria.eu is included.

Hosted by Darius, founder of Chessengeria.eu, March 2023. Source: LinkedIn „(…) The chess programming field has clearly benefited from the availability of open-source engines.” Before you is an interview with Jon Dart - the man who created Arasan - a real beast in the world of chess engines. Arasan beats most of its competitors, and not only because of its strength, but also because it is an open project - anyone can be inspired by Jon's ideas, which he has been developing successfully for several decades! In the interview you will learn how Jon traveled the development of his work, what ideas he had for its development and what he has planned for the future. If you are curious about what secrets Arasan hides and how it became so strong, this interview is for you! 1. Darius: Jon, please introduce yourself to our readers. Jon Dart: I have lived in Silicon Valley for almost 30 years. I've had a long career in commercial software development. I've worked at a number of companies and had roles including developer, manager, and software architect. For the past 10 years I have focused on computer security. I am currently CISO at Workato, a company specializing in business integration and automation. Arasan has been a side hobby project to my day jobs in software. In the late '80s, Windows was a new technology, and I got interested in trying to each myself C++ and Windows programming, so I had the idea of making a Windows chess program. That eventually became Arasan 1.0. 2. Darius: Arasan is getting stronger and stronger and is capable of winning against anyone. Could you give us more details about the latest development versions of Arasan? Jon Dart: Arasan has become gradually stronger over time as I added more features, tuned the engine, and removed bugs. Recently, like many engines, Arasan got a big boost in strength by adopting a NNUE evaluation. That has been worth over 100 ELO on the computer rating lists. 3. Darius: What is the secret of Arasan's high skill level, and what long-term ideas can push Arasan's skill level to even greater heights? Jon Dart: The recent gain in strength is mostly due to NNUE. The current network is the result of several rounds of tuning, the most recent being a reinforcement learning pass. I think gaining significant additional strength will probably require a different and probably larger network structure, and I have done some preliminary work on that, but it is going to take some time to develop and tune it. 4. Darius: What are your recent major changes to Arasan over the past few years? Is the increase in Arasan's strength the only motivator for its continuous improvement? Are there other factors ? Jon Dart: You can see full details in the repo logs and an overview in the CHANGES file in the repo. Some of the major changes were: 2014-2017: Auto-tuned evaluation (Texel Tuning) 2021: NNUE implementation 2022: additional NNUE tuning Plus a lot of bug fixes and minor search/eval improvements. I do work on improving the engine's strength, but I am not obsessed about being on top of the rating lists. I'm also just happy to see it used and enjoyed by people. Arasan still ships with a Windows user interface, and I think the majority of users are actually downloading that package and running that version. The engine behind that isn't really optimized for strength (it is compiled for maximum portability) and anyway will be too strong for most human players. That's why the UI has a strength reduction option. 5. Darius: What are your primary programming interests for the future of Arasan? Is there something you are most interested in when it comes to game styles ? Do you like to create a positional / tactical / strategic engine ? Jon Dart: I have a lot of things in my todo list. I don't think Arasan has a very distinctive playing style and I don't try to tune it to have a particular style. I am tuning it for overall strength. One thing I notice is that when it's playing weaker opponents, it often either is winning right out of the opening (if using its own opening book, which is pretty good), or they succumb to an attack and lose. It certainly does know how to attack and will do so if given the opportunity. But when playing other strong engines, they don't typically make opening mistakes, or if they do they can recover from them, and they don't allow spectacular attacks, in general. So those games tend to be draws. 6. Darius: Arasan is a chess engine that we can enjoy on various operating systems, such as Linux, Mac, Windows. Is it difficult to write a chess engine in such a way that it is relatively easy to compile it for the above-mentioned systems ? Jon Dart: Originally Arasan had a lot of macros and hand-coded tweaks to make the code portable, but modern versions of C++ have features in the language and system libraries that provide portability, so I use those now. The only place I do something special is setting the stack size for MacOS and Linux. 7. Darius: You are also the author of the Arasan Test Suite, a select collection of special chess positions. Does Arasan Test Suite significantly help you develop your chess engine ? If so, what do you mainly pay attention to when using these test positions ? Jon Dart: I used to rely on test suites for tuning a lot, but I came to realize that they do not reliably measure program strength and in particular cannot discriminate between versions or engines that have small differences in strength. Arasan is tuned now by running fast time control games and doing a SPRT test of the new version against the old version. This became widely practiced after Houdini was said to be using that method. Test suites are still useful to give a coarse measure of strength. I am also still interested in collecting and analyzing positions that Arasan does not solve, or does not solve quickly. Arasan is playing on several chess servers and I look at the log files from those games to find positions that deserve scrutiny. 8. Darius: Do you have plans to introduce Arasan support for Fischer random chess (Chess960) ? Jon Dart: It's in the todo list, but I am not personally very interested in Chess960, and I think it would be a big job to add that support and get it thoroughly debugged, so I haven't done it so far. 9. Darius: When can we expect Arasan 24 ? Jon Dart: I am going to release 23.5 soon with some minor fixes and updates. The next major release is probably going to be when I have a new network implemented, but I don't have a projected timeframe for that. I also have other things I would like to clean up: for example, most of the HCE is not used anymore, so could be removed. 10. Darius: What is your opinion on creating a contemporary chess engine using only Hand Craft Eval (HCE). Do you see any advantages and the future of such an approach here, considering the possibility of using a neural network (NNUE) ? Jon Dart: I think people just beginning with chess programming can still use that for a start and add NNUE later. Both Texel-type tuning and NNUE developments have shown that the eval is very important. I had a real hand-coded evaluation for many years, and it was pretty good I thought, but then auto-tuning it gave a significant boost in strength, and NNUE an even greater boost. I think some form of NNUE is necessary for top-level performance now. 11. Darius: The number of commercial chess engines has significantly decreased in recent years. Instead, there are an increasing number of free open source chess engines. Is this a good or bad thing for computer chess in general, and for users in particular ? Jon Dart: Many of the commercially successful products like Fritz have nice UIs and features that go beyond just the engine. So there is a place for those. The market for super-strong engines by themselves is fairly small, I think, and only the very top engines attract buyers. The chess programming field has clearly benefited from the availability of open-source engines. When I started out in chess programming, I read what books and articles there were on the subject. But source code is very helpful to see how ideas are implemented. There were very few open source engines in the early days. The main one was Gnuchess (the original one). But I found Gnuchess not a very good model to follow. The code was dense and had few comments and it had some quirky features. Don't get me wrong: it was a good program, it was just having the source did not help me much. A little later Crafty came along and it was more clearly understandable to me. I followed Crafty development quite closely and was always trying to get better than it, but that was a hard task for a long time, because Bob Hyatt kept improving it. Over the years a lot more open source engines appeared, and I found many of them interesting. I remember looking at Toga and being amazed at how aggressive its pruning was. I thought: how could this possibly work? But it was a strong engine for its time, and that level of pruning is now common. I will mention though that unlike most engines, mine is MIT-licensed, not GPL. So that allows derivatives of the engine to be distributed with attribution, but without including source. I am aware that there are some commercial projects using the code. 12. Darius: Where do you see the key to the strength of engines like Stockfish, Dragon or Berserk ? The aforementioned trio of chess engines are currently (2023) mostly thundering their competitors, clearly ahead of them in strength measured in Elo points. Jon Dart: Stockfish has benefited a lot from its large community of contributors. They try a very large number of changes and only a few of the best make it into the main branch. Stockfish also benefits from its distributed testing network. I have several large servers to test on, but Stockfish has a much bigger pool and can do test runs of 100,000 games or more. They have made a lot of progress by putting in a lot of small incremental changes. Dragon I don't have much familiarity with. Berserk as far as I can tell doesn't have a lot of unique features, except its NNUE is different from other engines. 13. Darius: Do you have any favorite chess software with which you test your chess engine ? Jon Dart: I used to run offline matches against other engines for testing, but now most of my testing is self-play testing (old vs. new version of Arasan). I use cutechess-cli and some custom scripts for running matches across a pool of machines and monitoring the results. As mentioned, Arasan plays on the chess servers (FICS, ICC and lichess, currently) and I find those games interesting and sometimes helpful for finding bugs and ideas for improvement. 14. Darius: Arasan is a well-documented chess engine, and its website has been, and continues to be, an example of extreme meticulousness and attention to detail for many years. We can say the same in the context of Arasan's development. Please tell us what is behind such exceptional consistency and determination in achieving goals and successfully enhancing the capabilities of the Arasan engine ? Jon Dart: Well, personally I just find it challenging and interesting to work on, and that challenge and interest hasn't gone away over time. Darius: Jon, on behalf of Chessengeria's readers and myself, I thank you for participating in the interview and sharing your experience of developing one of the best chess engines in the world. I wish you continued success in your work on Arasan and may your passion accompany you for the next several decades! NOTE: Further publication and reproduction of this interview is permitted only with the prior permission of Darius, founder of chessengeria.eu The condition is that the content is preserved in its entirety and that a link to chessengeria.eu is included. In the Files area you will find free chess engines for download.

Hosted by Darius, founder of Chessengeria.eu, March 2023. „(…) I'm still having fun experimenting with changes to my NN structure and training new nets using training data from recent games.”. John Stanback is a well-known creator of strong chess engines who has made significant contributions to the field of computer chess over several decades! First Zarkov and then Wasp, both of these chess engines have been successful and have many fans. With his knowledge and experience in computer chess programming, John Stanback continues to push the boundaries of what is possible in this field and inspire future generations of computer chess enthusiasts. 1. Darius: Where did your passion for programming chess engines come from? John Stanback: I've been programming chess engines since 1978. I'm not a good chess player, but I like to think up algorithms and code them. I started by writing a routine in Basic to generate moves, then wrote a text interface and had the engine make random moves. Next, I started adding some really simple evaluation heuristics and a one ply search. And 45 years later I'm still at it :) 2. Darius: What are the biggest difficulties you have faced in developing chess engines? John Stanback: I guess the only thing I would view as a difficulty is sometimes failing to improve playing strength after many months of trying out various ideas. Also, occasionally running out of ideas to code and test. Since I've never tried to make a living writing a chess engine, I view most obstacles as fun challenges rather than difficulties. 3. Darius: Are there any special algorithms or techniques that your chess engine uses to be so powerful? John Stanback: I don't think there is anything unusual about the algorithms I use. I rarely look at the code for other chess engines and never copy anything, but occasionally I get an idea to try out. 4. Darius: Artificial intelligence is a trendy and frequently used phrase. In the context of chess engines, will AI be applicable in the future ? What could be the benefits of it ? John Stanback: Perhaps AI will be able to suggest better neural network architectures for chess or better ways to train the *NN. 5. Darius: Does your chess engine use recently trending technologies such as machine learning? 6. Darius: What is your experience with implementing *NNUE in your chess engine? What are the advantages and disadvantages of this technique? John Stanback: I'll provide a combined response to these questions. Wasp uses a neural network for position evaluation, as do all of the top engines today. I was amazed when Alpha Zero demonstrated how strong an engine using neural network evaluation in combination with a Monte-Carlo tree search could be, and further impressed with the huge gain in strength when Stockfish implemented the NNUE evaluation. I thought I might be too old or not motivated enough to learn how neural networks work, but after reading just a little bit about them I started writing some functions in C to generate inputs from a board position, and do a "forward pass" to produce an evaluation. Initially I didn't worry at all about making the routines computationally efficient. I wrote a back-propogation routine and tested and debugged it using the training positions I had been using to tune my hand-crafted evaluation and found that even a fairly small network could get within about 100 Elo of my best handcrafted evaluation. Initially I tried using a net with 2 hidden layers, but I found that the small 2nd layer I was using didn't help at all, so I changed to a single layer. I then improved the efficiency of the network evaluation and training functions by using SIMD (single instruction, multiple data) instructions and using integers for the forward pass except during training. I've continuously added training positions taken from games between Wasp and other engines of similar strength and scored them using a short search using the latest NN evaluation. I've done a lot of experimenting with various training parameters such as minibatch size and learn rate and have tried to pick what works best for my engine. 7. Darius: What features or characteristics of your chess engine help it deal with the so-called "horizon effect" - a problem in which it is impossible/difficult to predict further best moves and game outcomes? John Stanback: I don't have anything special for this. I think that today's fast CPU's and the various tree pruning techniques allow a deep enough search that horizon effect is rarely a problem. Having a stronger evaluation at the leaf nodes also helps a lot. 8. Darius: What are your favorite/used development tools for creating and testing the Wasp engine? John Stanback: I develop under Windows using Notepad++ and use the gcc compiler from the command line, no *IDE. 9. Darius: Raspberry Pi are very interesting devices although not yet very popular among computer chess enthusiasts. What led you to prepare Wasp compilation for Raspberry Pi ? John Stanback: I thought it was cool that I could get a fairly powerful computer for around $50. Of course I had to see if Wasp would compile and run on it. 10. Darius: What are your plans for the future with Wasp? John Stanback: Just keep doing whatever seems interesting. I'm still having fun experimenting with changes to my NN structure and training new nets using training data from recent games. I'm running more games with *FRC and unbalanced openings to try to increase the variety of the training positions. 11. Darius: The creation of chess engines is quite popular. New ones are appearing and growing in strength. What advice or tips can you give to novice programmers who want to create and develop their own chess engines? John Stanback: I think it's helpful not to worry about playing strength until later in development. The Chess Programmer's Wiki is a great resource. It's probably more fun and productive to write your own code from scratch. Start by writing a clean move generator and test it using Perft() and try to make it reasonably fast. Then maybe write a simple hand-crafted evaluation using only piece/sq tables and material and don't worry about making it good until the search is working. Write a simple alpha-beta search without any enhancements and get it working well. Then add UCI handling. By this time you should be hooked and can spend the next 45 years improving it :) 13. Darius: Thank you so much, John, on behalf of Chessengeria.eu Readers and myself, for taking the time to do this interview. Best wishes for Wasp's future growth! NOTE: Further publication and reproduction of this interview is permitted only with the prior permission of Darius, founder of chessengeria.eu The condition is that the content is preserved in its entirety and that a link to chessengeria.eu is included. * IDE - Integrated Development Environment FRC - Fischer Random Chess, also known as Chess960. NN, NNUE - Efficiently Updatable Neural Networks for Deep Reinforcement Learning. You can find the latest Wasp chess engine for download from its homepage.

In diversity - the power :) I encourage you to read the latest issue of MCERL.

Fritz. A commercial program developed by ChessBase for over 30 years. A companion and training partner for chess players and computer chess enthusiasts across generations. Fritz is a program sold around the world, considered by many to be the best in its class - a benchmark for other competitive products. Fritz has written beautiful pages in the history of computer chess. In 1995 he became the Computer World Champion by winning against a prototype of the famous Deep Blue chess computer. At the beginning of this century he played with the strongest grandmasters and got good results against World Champions like Garry Kasparov, Vladimir Kraminik and Rustam Kasimdzhanov. Those were fascinating times for computer chess, when talented programmers through their chess programs were discovering more and more possibilities of programs in this software field. Source: ChessBase In late 2021, Fritz 18 (F18 for short) was released, while an update called Fritz 18 Neuronal was released on March 31, 2022. This latest version of Fritz 18 Neuronal will be reviewed. First, let's take a look at some of the data in the table below. Table of Fritz 18 specifications. Dear reader, you may be wondering reading this specification: Why ChessBase has not released Fritz for other platforms such as Macs or computers running Linux ? Why there is no Fritz for mobile devices ? After all, ChessBase as a company has been producing and selling software for over 30 years ! These are the kinds of questions Fritz supporters have repeatedly asked ChessBase after articles on their website. Unfortunately, until today we have not lived to see the answer and the release of Fritz for the above-mentioned platforms. This is all the more puzzling because, for example: Contemporary Mac computers using Apple Silicon processors (ARM architecture) are very efficient, working noiselessly and using much less power than other competing solutions. And they cost reasonable money, such as the Mac Mini with the Apple M1 processor. On top of that, working under the macOS, considered by many to be the best operating system. Undoubtedly, chess is becoming more prevalent - with an emphasis on online play and software. It is worth knowing that customers leave many times more money in the Apple App Store and other sources than in the Windows store. What I wonder about is the business strategy of ChessBase, which is, after all, one of the largest developers of chess software. Google, Microsoft, Adobe, Slack, Oracle, Valve and others most notably companies make software for the Linux and Mac. I would like to see ChessBase join this esteemed group one day. Well... hopefully that will change in the future and we will eventually get Fritz and other ChessBase software for Linux and Mac. Although earlier we will probably live to see full-fledged ChessBase web apps than their versions for other operating systems ;) For those interested, here's a link to an article on how to use Windows system and Windows applications comfortably on a Mac. In the meantime, let's revisit the Fritz 18 Neuronal and see... Does the Fritz 18 Neuronal engine provide significant competition to today's most powerful chess engines ? Will the functions related to the analysis and use of chess engines meet the expectations of a sophisticated user ? Does the Fritz 18 offer the best and most useful training features ? Are the database functions sufficient to handle games and chess bases efficiently ? Does F18 offer useful web integrations / online apps ? I will try to answer these and other questions in this review. Like the reviews of other chess programs on this blog, this one is divided into several topic segments. This is to make it easier for readers to possibly compare different programs. When you run F18, you are greeted by a window with program functions divided into thematic sections: FRITZ PLAYCHESS ONLINE APPS At the very top more to the right you can see the login status of your ChessBase account. If you see your login name then you are logged in. PLAYCHESS PlayChess is one of the components of the ChessBase ecosystem. By purchasing F18 you also receive Premium access to the PlayChess server for a period of 6 months. In this article I described the PlayChess server and its capabilities available with Premium access. Let me quote a few words from the mentioned article: " Play Chess is not only a place to play chess over the Internet, it is also an excellent center for many services provided by ChessBase, such as broadcasts of events, game streams, participation in simulations, access to chess games databases and various types of training. " When I want to play chess online, I like it when I can chat with a player or many players I know. And sometimes I can chat with the tournament referee, exchange opinions, ask about something - just chat in a human way. That is why I have been playing online for many years on the PlayChess server. PlayChess is a very good server for playing chess online. Having Fritz 18, it would be a pity not to try PlayChess, even more so having Premium access for 6 months. ONLINE APPS Fritz 18, like other ChessBase programs, offers access to web applications dedicated to specific purposes. The best way to use them is to have Premium access - such as Fritz 18 offers. Video Portal - Enhance your chess with Video lectures. This is a place dedicated to chess training. More than 5000 videos in which tutors discuss each phase of chess with examples: openings, middle game, endgame. Videos are added on a regular basis. The hosts are well-known Masters, Grandmasters and coaches such as Andrew Martin, Daniel King, Lawrence Trent, Svitlana Demchenko, Karsten Müller, Herman Grooten, Robert Ris and others. In addition to the videos - courses, we can also watch videos on variety chess topics: Looking for a video that talks about a specific opening or position ? Nothing easier, use search engine! After setting the position and clicking the Search Position button... ..., You get the results: Another example, much more popular opening -> much more videos :) And results: Video Portal is the right area to get expert knowledge on every subject related to chess. Everything in one place, easily accessible and with a handy search engine. Openings - Learn new openings. This is a place dedicated to chess training. We have a huge book of openings (Live Book), which is updated continuously on ChessBase server. After selecting an opening, a notation window is opened, in which we see the variations. We also have at our disposal a chess engine, which can be helpful in searching for e.g. novelties by oneself. In the image below, the opening Spanish - Open Variation is considered. By using the Drill or Guess Variation functions, you can actively learn chess openings. Below is an example of how to use the Guess Variation feature. Openings is a very useful tool which, thanks to constant updates, will always keep you up-to-date with the latest chess openings and allow you to explore undiscovered interesting lines. A useful addition is a chess engine with which we can quickly determine if a particular variation is worth our attention. Tactics - Excercise your tactical skills This is a place dedicated to chess training. I love tactical chess puzzles :) Here they are given in a superb way. We have Solve Tactics at our disposal, which is a calm and unhurried solving of puzzles. Just in time to stimulate "grey cells". Example 1. Example 2.1 Example 2.2 We can try the Tactics Sprint, which is solving puzzles on time. Or we can cheer on chess players competing against each other in Fight against another player. And if we feel like or are in the mood for a direct duel, we can try direct competition with another chess player... Fight against another player is a very exciting experience, which increases the desire for further competition and whets the appetite for solving more chess puzzles. For those craving the competitive spirit, leaderboards of the best are available. Live Database. Access to a database of chess games. Of course, like other ChessBase web applications, Live Database is as the name suggests – updated live. I was very pleased that there is a dark mode available in addition to the standard light mode. We can use the Live Database in many languages. Below an image with languages to choose from (this is not all, the list is longer). Using Live Database is trivially easy. We have a search engine at our disposal. We can simply type the name of the chess player. In this example, after typing the name: Duda, we get a list of this chess player's chess games. We can use a more advanced search engine, where we can get more precise search results after entering different criteria. The Live Database presents a chess opening tree, which is particularly useful for analyzing the initial phases of games. Each chess game from this database can be downloaded as a . PGN file. Live Database also has a chess engine that can support us during analysis of games and chess positions. It is nice that we have at our disposal the analysis of one... ... or more lines. Live Database is a very cool tool for quick chess database exploration. The clear and transparent interface, the ease of use and the always up-to-date database make the use of this database pleasant and useful. Cloud - Organize your games in the cloud. With this web application, you can handle your chess games in basic way, keeping them in ChessBase's cloud. Cloud is the place where: your chess games played on the PlayChess server are automatically saved you can use the Live Database (database of games updated live) create, save, edit and change, delete - databases and chess games. enter comments in game notation, mark moves analyze using the built-in chess engine Cloud application can communicate using different languages. Below is an example of Cloud with an interface in Polish. List of my chess games played on PlayChess server: Cloud allows you to search: And use the Live Database: A toolbar for making changes in notation: Cloud, is the right place to organize your chess games, especially if basic functions are sufficient for your needs. Chess News - This is a link to ChessBase's website for the latest news. The site is updated daily and in addition to news, contains a lot of professional articles. Shop - this is a link to ChessBase's online store. In this store you can buy Fritz program and other products such as ChessBase program, chess bases and many others. To sum up this part of ONLINE APPS review, I feel a little deficiency. Video Portal - an excellent service for training. Anyone who wants to deepen their chess knowledge in the comfort of their home / club will receive thousands of videos on probably every topic of chess theory plus an excellent search engine. Tactics - an excellent supplement to training in the spirit of healthy competition. Live Database - simple but very effective application. Openings, Cloud - interesting services for rather less demanding users. The applications are at an uneven level. Some of them offer dark mode and complex functions, others do not. It's worth remembering that these are online applications - which means there are bound to be people wanting to use them via smartphones and/or tablets. And this is not good enough. Most of these applications are not very well adapted to mobile devices. Over the past few years, I've observed the efforts and, more importantly, the changes that ChessBase has made to the web versions of its applications. All of them are very well used with a computer and increasingly better with a phone or tablet, although in this area still before the company ChessBase a lot of work. FRITZ Easy Game - Play an easy game against Fritz with possible assistance. " First, what isn't Easy Game ? It's not an option where a chess engine playing over 3000 Elo level uses 0.1 seconds to think of a move in order to lower its playing strength to human level. It's not an option where the engine plays without a pawn or even a few chess pieces. And what is Easy Game? It's a mode where the program will adapt to your level of play, make you a fun but also challenging opponent, give you a chance to make brilliant moves and win the game. It's also a mode where the computer coach assists you during the game, giving you tips and suggestions, but not hints - unless you want a specific hint on what move to play, then the Coach will give you such information. The computerized trainer communicates with the player by voice, in addition to the information visible on the screen. I used the English version of the Fritz 18 program and the computer coach spoke to me in that language during the game. During the game, the computer coach, after a few moves, begins to evaluate the strength of your moves using Elo rating points. It will try to create appropriate situations for you, so that you learn something and play an interesting game. Finally, after 57 moves, I managed to win. The strength of my play in the entire chess game was rated at 2170 Elo points. With such a coach by your side, playing chess is extremely satisfying, often spectacular, but most of all informative and developing. " The above pasted content is from my article titled: "Tools in a chess player's workshop - Windows - Part 2". In this article, I show the progress of Easy Game with Fritz program as an example - and I invite interested people to read this article. In order not to repeat the content of the mentioned article, let me summarize here the Easy Game: Fritz behaves very naturally, the comments and suggestions are accurate, the voice communication helps in understanding. After playing several hundred (!) games of Easy Game, I believe that it offers probably one of the best computer sparring-partner for chess. It can be a very enjoyable experience, and can also be a great training tool. So why not combine the pleasant with the useful ? :) Enter & Analyse - Enter and analyse your game. " During chess training and practice, it is extremely important to be able to analyze and learn from completed chess games. Fritz has a very powerful chess game analysis module that stands out for its excellent annotation in the language of your choice and its ability to place diagrams and highlight moves and variants. " The above pasted content is from my article titled: "Tools in a chess player's workshop - Windows - Part 2". In this article, I show the progress of analyse game with Fritz program as an example - and I invite interested people to read this article. Fresh examples (May 2022) of the analyzed game with automatic annotations made by Fritz 18. Example 1, the final moves in a chess game. Example 2, whole game. Now, an example of an analyzed game with automatic training annotations made by Fritz 18. The training is interactive, that is, the user is prompted to make a move. We can also see the solution without making a move when we click Solution. Very powerful training tool ! Always attractive, because we can train on our chess games :) Of course, there is no obstacle to train this way on other chess players' games. Fritz 18 will analyze every chess game and prepare training options. It's a great tool that not so long ago an ambitious and eager chess player could only dream about. Let me summarize here the Enter & Analyse. The analysis of chess games by Fritz 18 stands at the highest level. If you want to have an analysis of a game with variants, continuation lines, adequate comments and marking of individual moves with game plans -> choose Fritz 18. Currently - June 2022 - there is no better program for analyzing chess games and preparing them for training purposes -> than Fritz 18. Classic Menu - Use classic Menu style. When you first start the F18 program interface looks like this: The centerpiece is the chessboard and the Fritz 18 Neuronal notation and chess engine window. It is worth knowing that a free upgrade to the strongest version of Fritz 18 Neuronal will happen automatically when the program is activated and has internet access. At the very top of the program window is a ribbon toolbar that thematically contains grouped F18 functions. F18 has a highly customizable interface. The elements-windows and toolbar-can be active or inactive. The program also has built-in settings for the entire interface. For example, you can choose a look with a large notation area... ...Or look to facilitate analysis using a chess engine: Maybe you need a window arrangement that makes it easier to work with an open book and search for novelties ? The possibilities of arranging the appearance of the interface are very wide because we can change almost all the elements of the interface, show and hide windows, place them in different parts of the screen, adjust e.g. the type and size of fonts, and the appearance of the chessboard and the pieces themselves. We can also use 3D chessboards. They look ok... ...It's quite fun to play... But... ...I have seen better 3D chessboards in other programs. It is a pity that there is no dark mode available. Even after selecting warmer colors such as the chessboard and the pieces, the rest of the interface is in bright colors, which can be tiring to the eyes in the evening or a room with less light. The interface and all F18 messages have been translated into several languages, which will certainly please users who prefer to use this program in their native language :-) To sum up this part of the review, my feelings are rather positive. The interface is not very modern and ergonomic, but is neat and clear; elements can be changed (position, size, etc.). Power of Play. The Fritz program has always been driven by the engine... Fritz. And although the authors of the Fritz engine have changed over the years, it has always been a good engine, able to compete successfully with others. The author of the Fritz 18 and Fritz 18 Neuronal engine (as well as Fritz 17) is Mr. Frank Schneider, known in the computer chess world as the creator of the Ginkgo chess engine. Ginkgo has repeatedly competed in major chess tournaments with other powerful engines. Undoubtedly, his success includes winning 2nd place in the 4th World Chess Software Championship 2015. The next and more powerful version of Gingko was adopted for Fritz and was called Fritz 17. The next versions, Fritz 18 and Fritz 18 Neuronal, represent a significant increase of power and further development of this excellent chess engine. So let's check how the latest Fritz 18 Neurnal performed against two class opponents and in a tournament with the strongest chess engines. First, the Velvet 3.3.0 engine released in March 2022. Velvet uses a modern neural network evaluation and is currently a dynamically developed chess engine. According to the rating lists, Velvet 3.3.0 plays at about 3300 Elo (4 CPU), the strength of the well-known Hiarcs 15 chess engine. Each engine had 4 CPU at its service and 1 minute per game; Fritz 18 GUI, 128 MB hash table and Perfect 2021 opening book. F18N won this match convincingly scoring 84 Elo points more than its opponent. I encourage you to watch the chess games from this match. Although Velvet lost this match, he played aggressively and in a beautiful style. Fritz "kept his composure" and consistently and effectively repelled the attacks. And two images showing what a match between engines might look like. Clear view with relevant information about the match. Next, result from match consisting of 100 games Fritz 18 Neuronal against RubiChess 20220223. RubiChess is one of the top 10 strongest chess engines - very demanding and extremely powerful. Despite losing that match, Fritz was able to win 10 games and tie as many as 56. And a little more challenge for Fritz 18 Neuronal and more computer opponents. There were 15 engines in the tournament. Each engine had 4 CPU at its service, game time 1 minute per game +1 second extra for each move. Fritz 18 GUI, 128 MB hash table, Perfect 2021 opening book. Fritz 18 Neuronal took an excellent fifth place in competition with the strongest chess engines. The Fritz 18 Neuronal strength in longer-thinking games is in the vicinity of 3350 Elo for the version using 4 CPUs while playing. Source: CCRL Fritz 18 Neuronal is a strong chess engine that ruthlessly wins against weaker ones. However, (in June 2022 when this review was written) Fritz 18 Neuronal is not strong enough to be ranked among the TOP chess engines in the world. One of its strengths is precise defense and counterattacking, during which he is able to exploit the slightest inaccuracies and mistakes of his opponents. Style of play. The most natural way to recognize Fritz 18 style of play is to play games against it. Which I did :-) I played 10 games in ranked mode with adaptive strengths enabled. Time for each player: 3 minutes + 2 seconds after each move. Below are 10 ranked games I played against Fritz 18 Neuronal. Unfortunately, in ranked play mode, F18 will not automatically adjust its playing strength after each game. Users must adjust the F18 level themselves by changing the slider (see image below). This is not convenient and not every user needs to know what game strength to set for their computer opponent. After each game, F18 meticulously notes statistical data for us to see. As you can see in the image below, the Result row does not display the data completely. Several characters are missing. I tried to display this window in different screen resolutions, unfortunately with no positive result - each time the whole thing is not visible. We also have a window called Chart, where the graph shows our ranking after each chess game played. As in my two previous reviews (Hiarcs Chess Explorer Pro and Deep Shredder 13), I intended to play 30 games. A tempo of 3 minutes + 2 seconds after each move for each player. After 10 games, I discontinued the ranked games. Why ? Because Fritz did not play according to the set parameter. Before each ranked game I made sure that option Program plays fast was unchecked (see below picture). Despite this, the program played very fast, almost immediately making moves. This way it was impossible to play normally! I chose and set the thinking time so that the program could simulate human behavior in a ranking game. Unfortunately, it did not work at all. In the chess games attached above, I left the timing of the moves in the notation. The ranking game itself, during the 10 games played, was not a pleasant experience. The Fritz 18 Neuronal played like a typical computer and not an engine with such a long tradition developed by top programmers. It making no effort to simulate typical human behavior during a chess game. As he was supposed to play at 1600 Elo, so he played at 1600 Elo all the time at this constant level with no major errors and no minor errors. Style more positional than tactical. My subjective feeling: boring ranking games with a computer that doesn't even play according to the set parameter. Well sorry, but this is 2022! And the kind of technology that can simulate ranked human play. This can and does work, such as in Hiarcs Chess Explorer Pro (I invite you to read the review). Too bad that in Fritz 18, a program of this class - there is option like Rated Game that does not work well. I hope this will be corrected in one of the next Fritz 18 updates. A few screenshots of ranked battles. Game in progress. After the game. Fritz loses the game and gives up. After playing a few games and losing the first game by me. End game phase, and Fritz still has 3 minutes of thinking time. An obvious bug that should be corrected by the developers. It's one thing to play with F18 in ranked mode, but how will the engine do when analyzing games played by people - very high level games ? I have chosen games from games played by humans, with difficult positions for chess engines. My goal is to test the Fritz 18 Neuronal engine on 10 positions giving it a maximum of three minutes of thought per move. I have assumed that these will be positions played by people who have allotted up to a few minutes for a move. Therefore, I did not take into account positions created in correspondence games. During testing, Fritz 18 Neuronal used 4 CPUs, 1024MB Hash table, and Syzygy tablebases. We start with a relatively simple position for a man to solve - the only effective option is to break the black pawn barrier by sacrificing the Queen. F18N failed to find the correct Qxb5. The engine sees a very big white advantage, but does not indicate a winning continuation. In the following final position, the elegant c5 wins! Fritz didn't find the best move. And another ending, this time much more complex. Fritz failed to find the correct ...Rxb3. The following position is from a match between then World Chess Champion Garry Kasparov and the computer Deep Blue. G.Kasparov surrendered the game in this position, although the draw was led by Qe3!! The correct continuation was noticed by F18N immediately. Another position involving titled players. A tactical Queen play to the d3 square F18N finds after only 12 seconds of thinking time. In the following position, on the other hand, the winning move is Knight's "quiet and inconspicuous" move to field c7. For many years this was an unsolvable position for chess engines in a reasonable amount of thinking time. F18N failed to find the correct ...Nc7. In the following position many chess players are able to point out the strongest move Qf6+ although it is harder with justification :-). F18N failed to find the correct Qf6+. One of the most difficult positions for chess engines. To successfully launch an attack on the black King, white must clear the lines for Rooks by maneuvering with the King. F18N failed to find the correct Kf2!!. In this position, what can white do with one less piece and a black king in the middle? Of course, destroy the black King's position by hitting the Rook on e7 ! The chess player notices that after removing the black pawn - the defender of the enemy King - another white Rook, Bishop and Queen joins the attack. The attack of these three strong figures guarantees at least a draw. For a human this maneuver is relatively easy to see, for a chess engine giving up one more piece (Rook) is not so obvious. In this chess game 15-year-old Carlsen did not play well and the game was won by Svidler. In this position there is theoretically a draw. F18N saw the best move after 128 seconds. And finally, a position in which GM Anish Giri played a beautiful move with a pawn on a4. This is an extremely difficult position for chess engines, as the solution requires sacrificing the pawn and then exchanging Rooks. This seemingly contradicts the chess rule of avoiding sacrifices and exchanging pieces - if the opponent has a material advantage. In this position, the sacrifice of a pawn and exchange of Rooks by white is justified because the binding of the black Knight by the white Bishop is inevitable without the loss of that Knight - leading to black's defeat. F18N failed to find the correct a4. To sum up this section of the review, I make no secret of the fact that I am unpleasantly surprised. The subjective feeling of a person playing and testing the Fritz 18 Neuronal engine is that this engine plays boring chess and despite a pretty good score against other chess engines, during analysis hard positions it often "fails to see" correct moves and continuations. Certainly Fritz 18 Neuronal is a strong engine, but its strength may not translate into quality analyses with special attention to position analyses in correspondence games or quick analyses whole games with very short thinking time. During the direct match I did not feel the knowledge of my computer opponent, but rather a cool calculation calculated to play with strength according to a pre-set ranking expressed in Elo points. Training. Before you start playing ranked games against a computer opponent, it's a good idea to check out the training options for each phase of the game that F18 offers. Rated Game. I discussed this training mode in this review in the text above. Friend mode. In this mode we start our first chess game with a clean record. Under the chessboard at the bottom of the screen is a round green light. This light flickers colorfully when Fritz plays incorrectly or makes a mistake. This is to alert the user to the current situation on the chessboard and to find the best possible move. Above the chessboard on the toolbar are buttons that have specific functions. When you press the Hint button, the program will use the green arrow to suggest a move to make. After clicking the Suggestion button, a new window will open with... Fritz Suggestion :) And, the program will mark with a yellow border the attacked piece. In the same window, when you click the Attackers button, the program will mark with green borders the opponent's pieces that are attacking your pieces. When you click the Attacked button, the program will mark with red borders your bouncers that are under attack. When you select and click the Fritz plan button, you get text information and arrows on a chessboard showing the plan. Below is another item to clearly show how the training program works when you click Undefended. Fritz marked the non-defended pieces with a yellow border. After finishing the first Friend game, the program returns to the standard view and the statistics window does not show much new data. It is worth noting that after playing the first Friend game (and subsequent ones), the automatic change in rating is small. In this example, after I won the first Friend game, my ranking increased by only 30 points: from 1300 to 1330. And this is not the best solution implemented by the developers of the Fritz 18 program. Assuming you want to play the Friend game at your level, say 1800 points. A thought/question arises: how many games do I have to play (preferably winning) to finally play Friend game with a computer opponent at that level - 1800 points? Well, it will take a long time, probably many hours. And if the user plays with an even higher strength, e.g. 2000 or 2200, then the training option Friend game constructed in such a way is very questionable - is there any sense in using this training option? Going back to the Friend game, if you click and hold the left mouse button, then the program will use colors to show the fields where the clicked piece can go. If the field is marked with a red color - do not place the piece there. If the box is colored green - consider placing a piece there. Here is an example when the green light starts flashing red. The computer has made an error putting Bishop on b5. After playing a correct move with a pawn on c6, the computer will praise you for a good move with a voice coming out of the speaker. This good move will also be marked with an exclamation mark - ! - in chess notation. After two completed Friend games, the program counts the user's ranking and a graph appears. If we do not see a good move during the Friend game after a program error (flashing light), the program will communicate this to us in the game notation: In this particular game, the program again played not well (15...Bf8) thus giving me a chance to find that -good- move again. Fritz also inserted a chessboard into the notation after his 14th weak move. The light under the chessboard began to flicker red again. This time I was able to find the best (and effective) move 16.e6! And that's pretty much all that this training module offers. After playing 10 Friend games, the window with my stats looks like this. During the two Friend games, when the program played against me with white pieces, I noticed that it did not make the first move. The first time I waited a few minutes, but nothing happened. Pressing the spacebar and other keys - did not work - Fritz did not play his first move. Clicking Cancel and starting Friend game again helped. This looks like a bug that should be corrected. Note the time, which is in the Windows bar at the bottom right of the screen: 5:05 PM. The same game not started by Fritz - note the time, which is in the Windows bar at the bottom right of the screen: 5:08 PM. During the Friend game I noticed that Fritz, having clearly lost positions, continued to play until 70-90 moves instead of 30-40. Waste of time, because there is a different module dedicated to training the end game phases. And in such games I ended them earlier, offering my opponent a draw, which Fritz accepted. As I said before, Fritz 18 Neuronal's style of play does not thrill me. And also in the Friend game training module I didn't feel like continuing after 10 games. Undoubtedly, the options in this module can be attractive during training. The program shows and explains moves and marks valuable plans and continuations on the chessboard. It is not a good idea for a strong chess player to have to play dozens of Friend games for Fritz to play at his level in this training module. For club players playing at level 1800 or higher, for the reasons described above - the Friend game module can be completely ignored by them. Handicap Position. This can be a way to play against a stronger opponent with a chance to win. F18 offers many handicap options to choose from. Here is the end of my game against the Fritz 18 Neuronal engine, which played without the Queen (full strength, 3 CPU, Elo > 3200). I won after 5 moves. Satisfaction? None. Calculation Training It's a training option, particularly useful for verifying tactical calculations as well as others. How does it work? In a pretty simple way. You need a position on the chessboard. You can set it up as you wish, it can be a position from your own or another chess game. With a position on the chessboard, you can start training. After you've thought about your next few moves, simply execute those moves on the chessboard. When you make a moves, the pieces won't move - the arrows will appear and your moves will be notated by the program. When you click the Check validity icon, the program will check the legality of the moves you have made. And if it finds no abnormal moves, then it will confirm with an appropriate message. The Check tactics icon opens the chess engine window, which immediately starts analyzing the end position. You can click any previous move, the engine will then start analyzing another position. When you click on Score quality of calculation, a window opens where you can enter the time for the engine to think about one move while verifying the entire calculation you entered. This is the process of checking the entered calculation. Once verification is complete, Fritz enters comments into the notation. In this case, the first move is correct and the best - only move in this position. But my third move Ke7 is wrong, better was 3...Kc7. Of course, there is no limit to the number of moves entered. So this training option will serve both when training simple positions with short variations and when training complex positions with long continuation lines. Calculation training is a training option that can be especially helpful when learning "chess thinking" - which is the calculation of your first move - and subsequent moves. The program refutes or confirms the validity of the user's calculations, showing at the same time whether the entered moves are in accordance with the rules of chess, whether mistakes were made, how one could have played better, etc. Theme Blitz. This is an option to practice by playing with Fritz with the prompts turned on or off. You can play from the starting position of the pieces on the board, or you can play from the current position as it is on the board. The program also allows you to change the side of the game. Some pictures of the game. It is a good idea to enable all the training features in this module, such as: This way you allow the program to communicate in a variety of ways during training. When the time is up, the training can continue. Opening Training. The program allows you to practice chess openings from a wide repertoire - including all the openings known to me, from the popular ones, such as Nimzo Indian Defence, to the less common, very sharp and interesting ones, such as Latvian Gambit (which is often used by the author of this review while playing online :) ). When you click on Detailed, the list of openings grows even larger; you can select specific variations. Once the opening and page are selected, the game begins. As with the Theme Blitz training option, you should consider turning on all the training support features. When practicing chess openings, don't forget the LiveBook or Openings Book. Both of these tools are great help in training and learning chess openings - suggesting the best and interesting moves and continuations. Endgame Training. Similar to Opening Training, we have a variety of different endings to choose from to train on. And in this training option we have we can choose the side of the game. During training we can use the Explain All moves function and the chess engine analysis. Both of these functions can be turned off. Attack Training. Seemingly simple: clicking to point out all the bouncers that are being attacked. In practice, during training this is not a trivial matter, having limited time to think - the program gives a few tens of seconds - and complex positions. A fun and rewarding workout that teaches you to look at a position for possible threats, opportunities to take away pieces, and tactical strokes. The green border indicates the correct pieces. After the thinking time has passed, the program will use orange circles to mark the pieces that have not been marked. And another training position. And this time I overlooked one of the pieces being attacked. Defence Training. That is, mark with a click all white and black pieces that are not defended. Kings should not be marked. I did this and it was recognized by the program as an error. If you mark all the pieces correctly, then the program shows the new position and the workout starts from the beginning and continues until you complete the error. Then the training summary window appears. Check Training. Click all white and black pieces that can deliver check. And in this training module, the principle is the same as in the previously discussed ones. At the end of the workout, the program displays a summary window. Mate Training. Click all white and black pieces that can create a mate threat through moving. In this training module you already have to do some thinking. You have to use a lot of chess imagination to see the possibilities of both white and black sides giving the defeat at the same time. Mate Training is a very useful training module, To sum up this section on the training modules Fritz 18, I find that most of the modules are useful, easy to use and the communication with the user is high. I have comments about the modules: Rated Game and Friend Mode, which I described in detail above in the review text. In my opinion Rated Game and Friend Mode should be replaced by one module - Easy Game which would contain all the best from these three modules. It would definitely be good for users. Analysis. Fritz 18 offers many functions to analyze the whole game such as well as the positions. These functions are grouped in a menu called Analysis. The attentive reader will surely remember that in the text of this review (the Enter & Analyse module) I presented Fritz 18's ability to analyze an entire chess game. I did this by using the Full Analysis function. Other functions on this menu are similar in operation but serve different analytical purposes. So let's check some of these most interesting functions in practice. Blunder Check. This function is used to quickly find errors and large inaccuracies. When you open a chess game for analysis and click on the Blunder Check icon, a window opens where you can change the parameters or leave the default ones. For analysis of games played at blitz tempo, I usually use 1 or 2 seconds to analyze each move. For chess games played over a longer period of time and of better quality, I set 3 to 10 seconds per move. We have a number of different parameters available. Their use is well described in Fritz 18 Manual. If you want the program to pay attention only to glaring errors, then it is a good idea to set the Threshold parameter value to 150 or more. During a Bluder Check analysis, we can watch the analysis run "live". Its effects are entered into the notation window by Fritz. Deep Position analysis This feature is noteworthy, for example, for correspondence chess players who need a very precise analysis from a specific chess position. Using various parameters, we can set the analysis parameters. You can also use several chess engines for analysis. It is worth knowing that Deep Postion analysis usually takes a relatively long time, even many hours. Compare Analysis. In the Fritz 18 Manual, this function is described in a very understandable way: " The automatic comparison of the analysis of two different engines has two main uses. First, it is an excellent way of evaluating the strengths and weaknesses of the engines. On the other hand, from a chess point of view, it is very interesting to compare the conclusions of two different engines. One might be tactically more reliable, the other more positionally sound. It is also interesting to compare two versions of the same engine. The “compare analysis” function allows you to check what each finds at a specific search depth, or how many position nodes each of these engines actually checks to reach a certain search depth. " And an example of using the Compare Analysis feature. Result: Compare Analysis is a great tool that can be used to select chess engines that work according to our preferences. After comparing the analysis quality of different engines, we can form our own opinion. It's worth knowing that the strength of a chess engine doesn't always translate into a good quality of analysis. Compare Analysis can effectively verify this. Shootout Using this feature, one or more engines can start the game from a specific position. Unlike Compare Analysis, here the engines do not analyze the chess game already played - but play it their own way. Shootout is an interesting tool which gives answers to questions about how a position can be played, but also lets you compare the quality of play of different chess engines. Setting the analysis parameters: Start of analysis by Stockfish 15: Start of analysis by Dragon 3 by Komodo Chess Shootout Summary: Monte Carlo Monte Carlo is a function which works in such a way that the chess engine plays a lot of chess games in a short time and according to preset parameters. After just a few minutes we get the result of several thousands (!!) games, which can tell us which side of the game: white or black has a chance to win / draw. Currently sold programs, i.e.: Fritz 18 (and after free update Fritz 18 Neuronal), Dragon 3 by Komodo Chess do not support this feature. Despite this, this feature is in the program. It seems to me that it would be natural if ChessBase's flagship products - the Fritz 18 and Fritz 18 Neuronal engines - supported Monte Carlo analysis. And if this is not the case, then ChessBase should clearly inform the user about this fact, adding which chess engines support this feature. Few chess engines support Monte Carlo analysis, eg.: Fritz 15, Fritz 16 and Rybka (by the same author Mr. Vasik Rajlich). If you would like to learn more about using this feature, click on the Help button: No help on the ChessBase company website :-( After using the search engine, you get a result: Fortunately, the Monte Cralo feature is very well described. It is unfortunate that the user does not have direct access to it. This should be corrected in the next Fritz update. The result of a Monte Carlo analysis after only a few minutes work Fritz 16 chess engine: After playing 13843 games, we can see that Monte Carlo rates the chance of victory roughly evenly at 47.7% with a very slight indication for black (16 Elo). Of course, we know that in this famous position white is able to win 100% after the beautiful move 1. Qxe5!!. I deliberately included this position for Monte Carlo analysis to show that this feature is more applicable to analyzing positions that are not immediately winnable. Monte Carlo will show the percentage chance of winning or drawing rather than indicate a specific winning or drawing move. Monte Carlo analysis can be a useful tool when looking for novelties in chess openings. After the pawn move to d3, what chances does white have in the Latvian gambit ? Pretty good, about 7% more than black (+55 Elo). Yet in my tournament practice, play games with blitz tempo - I usually get good results with black, because black for the price of a pawn gets good and easy play, even after exchanging Queens. Once completed, the analysis result can be saved as a position tree in .CTG format and can be loaded like a local openings books. Opening. Fans of creating / modifying and tuning opening books - will find in the F18 program a separate menu dedicated to this area. The available functions are clearly named and their use is simple. When working with the opening book, we can change various parameters. With this function the opening play of Fritz 18 Neuronal / other chess engine - can be influenced. Among other things, noteworthy is the Standard Repertoires feature, which can also be used for training purposes to quickly search for a chess opening of interest. A useful addition is that a record of chess openings is available for different levels of chess experience: Basic, Club, Tournament and Professional. Marshall Attack - Basic: Marshall Attack - Professional: In addition, with the LiveBook, Fritz can directly access a huge online opening book with millions moves. Your computer needs to be connected to the Internet to use this feature. Engine. Chess engines, their use in various ways - has been taken very seriously in the Fritz 18 program. We get a set of tools and advanced features for many purposes. From simple analysis, searching for threats, through matches and tournaments to tests and benchmarks. Using F18, in practice we can realize all the important activities related to chess engines. I would like to invite you to read one part of the course of ChessBase program (professional program for managing chess games and databases) under the title: "ChessBase - Using chess engines", in which I describe in detail the simple and the most advanced methods of using chess engines. In the Fritz 18 program chess engines are used in the same way as in the Chessbase program. For the purposes of the Fritz 18 review, I'd like to add, that this program offers the wonderful ability to use extremely powerful chess engines - for any purposes - through a Cloud service called Engine Cloud. In short: online - real time - you can use a chess engine running on a remote computer (or rather a cluster/workstation) equipped with dozens or hundreds of processors and tens of gigabytes of memory. The engines are many and varied, such as Fritz, Dragon by Komodo Chess, Stockfish, Lc0 and others. Engine Cloud, is the rental of a chess engine using a cloud service and via an internet connection. Some engines are available for free... ...Others are for a fee; clicking on ducats will open the ChessBase company page with information and prices. Below is an example of a test position in which Fritz failed to find the best move 1.c5! in 3 minutes (see the Power of Play section of this review). Using the free Fritz 18 from the Engine Cloud service running on 8 CPUs, we got the winning move before the first minute was up! The great thing is that you don't have to have a powerful computer to use Engine Cloud Just a simple laptop that, for example when traveling, will give you access to the computing power of powerful machines and modern chess engines. In the Engine Cloud some engines are provided for free, some can be rented. Please note that you must have PlayChess account and internet access to use Engine Cloud. Database - Chess database handling in Fritz 18 GUI. F18 offers quite useful tools for game maintenance and chess databases. The Database module is closely related to the F18 interface and contains shortcuts to popular functions of this program. At first, we can select a database we have already used before or open another one. After opening the selected database we are welcomed by a window with: a list of chess games in this database shortcuts to functions on the ribbon shortcuts to open other databases that the program has found Here are the mentioned shortcuts to various functions of the F18 program. Obviously, when you select and double-click a chess game, the Fritz 18 program window will open with that game. Of particular interest is the tab bar, with which we can search for players, tournaments, select chess games by openings and perform many other typical database activities. Below are some pictures with examples. When you click on a player's name, the Games window will show the games played by that player. Similarly, the Tournament window will show the tournaments that the player has participated in. The same principle of Database is after going to the next tabs. Openings tab. Here it gets even more interesting. In the window on the right side of the screen we can choose by clicking on the chess opening we are interested in, and the Games window will show the games with this opening. An excellent addition that F18 offers is Filter Games (also available in ChessBase in an even more developed form), which allows you to search for chess games / positions using advanced criteria. The use of this feature along with numerous examples I presented in the article "ChessBase - Search Masterfully". I will provide one example to show the capabilities of this tool. Criteria: Database: Database 2022 Games from the range of years: 1999 - 2022 Master Level Elo: 2300 - 2500 Only games where: White won Sacrifice: Yes Motive: White knight on d5, black King on e8, black pawn on e6 Search result: After double-clicking on one of the games found, we will be taken to a window containing the position according to the set criteria. Database, is a surprisingly strong feature of Fritz 18. Besides basic functions such as: Edit, Copy, Paste, Delete, etc. - It offers many advanced features known from professional programs dedicated to games and chess databases. Filter Games function is a very effective search engine for games and chess positions. In my experience, most Fritz 18 competitors, including commercial ones, do not have such well implemented features for handling chess databases. This will certainly be appreciated by users who appreciate working in one and the same program. The database features of Fritz 18 are at such a level that they will certainly suffice even for more advanced users. I really need... Help ! Fritz offers a variety of assistance options. In addition to the manual available online... ,...You can take a look at the Support Wiki or... ...Simply send a message. From the Help menu, you can also check and update the Fritz 18 program. ChesBase has made its users accustomed to regular updates to its programs over the years. It is no different with Fritz 18. Since its release in November 2021, F18 has received 7 updates. This is good news, because the Developers regularly take care of their product, improving and developing it through more updates. Based on my personal interactions, I can say that the customer service is friendly and helpful. Responses are prompt and geared toward effective assistance. Summary. Here's what the Fritz developers wrote on their website. Source: Fritz 18 site (2022-06-05) Does the Fritz 18 Neuronal engine provide significant competition to today's most powerful chess engines ? No. Will the functions related to the analysis and use of chess engines meet the expectations of a sophisticated user ? Yes. Does the Fritz 18 offer the best and most useful training features ? Yes. Are the database functions sufficient to handle games and chess bases efficiently ? Yes. Their capabilities go well beyond basic operations. Does F18 offer useful web integrations / online apps ? Yes. But not all are mobile-friendly. Fritz 18 is an example of how more is not always better. Just a few years ago, Fritz was synonymous with quality for me, today - in some areas of operation - Fritz 18 shows signs of weakness. Fritz 18 is overloaded with features that either don't work properly (Rated Game) or are repeated elsewhere in the program with some modifications (Easy Game). Looking at the program as a whole, one sees a conglomeration of modules from various previous versions of the program that cannot be used with the Fritz 18 engine and program, or do not work as well as one might wish. For example, the Rated Game & Friend mode modules are so low in comparison to the Easy Game module, which can actually replace them in many applications, that you might actually ask yourself - why are they still in the Fritz 18 program ? Another example: Monte Carlo analysis is also available in Fritz 18, although the Fritz 18 engine (and 99% of other engines) do not support this method of position analysis. The program contains many functions and modules with different properties, which requires some skill in using it. There are places where when you click Help, you get no help (see the section on Monte Carlo analysis). The program's interface takes a lot of inspiration from the look of Microsoft Office 2007 (ribbon), which was released... 15 years ago. Although it is usually comfortable to use, this look is no longer one of the most modern and ergonomic. Can it be done better? Of course, just look at the applications for Apple macOS or common Linux distributions. Web applications (ONLINE APPS), is not the strongest point of Fritz. Some of them are at a very good level (Video Portal), others clearly stand out (Cloud). Some are not very well adapted for smartphones and tablets. This is a clear weakness compared to the competition, which offers advanced web tools that can be comfortably used on computer, modern smartphone or tablet. Fortunately for us - users - the positives are much more :) Training options, analysis, use of chess engine(s), functions for working with the openings book, best notation tools available in chess software, PlayChess server closely connected with Fritz (ChessBase ecosystem), chess database support at an amazingly high level. These are functions implemented in a chess program at the highest world level. "The icing on the cake" is the Fritz integration with the Engine Cloud web service, which is, in my opinion, a game changer, at a level not available to other competing programs. Fritz 18 is a treat for chess fans, though not without weaknesses and flaws. Using Fritz 18 I felt at times like a beta - tester who catches shortcomings and bugs, details of which I have written about in this review. Fritz 18 is like a big house, but with too many rooms that sometimes hold too many things. Time for a major overhaul and redecorating ;) A modern look at the program as a whole from the perspective of the rise of web tools in the next few years & better quality control - these are certainly only some, but undoubtedly key areas of development for Fritz that will impact on its popularity in the future. Fritz 18 score.

This time, an application dedicated to mobile devices came to my review workshop. Hundreds of chess applications have been created for the popular system named with the friendly term of robot, which are readily available in the Google Play Store. And while there are so many chess apps for Android, only some of them are worthy of prolonged attention, and the best ones dedicated to serious and ambitious enthusiasts of the royal game - there are even fewer. Among them, the real diamond is Acid Ape Chess GM Edition. Source: Developer's website In full name: Acid Ape Chess GRANDMASTER EDITION is a powerful, functional and useful chess suite created for demanding users. It is a program that has been systematically developed for many years, with regular updates, and has many fans who have expressed their opinions in the Google Play Store. This review deals with Acid Ape Chess GM Edition version 1.11.1 with an update dated December 27, 2022. Some data in the table: Table of Acid Ape Chess GM Edition specifications. It is worth noting that Acid Ape Chess GM Edition needs Android version 4.4 or later to work, which means that... ...Even very old devices have a chance to be used with Acid Ape Chess GM Edition. The oldest supported Android system 4.4, code-named KitKat, was released in 2013, which is nine years ago as of the publication date of this review. I took advantage of this opportunity and for the purposes of the review I used the Asus Transformer Prime TF201 tablet, which premiered in 2012. The aforementioned tablet puts at the user's disposal a 4-core nVidia Tegra 3 processor and, importantly for me, a 10.1-inch screen; working on custom firmware - Android 7.1.2 I also used a modern Google Pixel 7 smartphone (2022 model, Android 13) to among others compare analysis times for specific positions; see the chess engine section of this review for details. So, is it possible with Acid Ape Chess GM Edition: Comfortably use on an old (and modern) mobile device? Efficiently work and analyze with chess engines ? Conveniently play offline and online ? Fast using the chess databases provided by the developers ? Training ? FIRST LAUNCH The application activates the license, which personalizes purchased copy. Activation takes literally a moment, and then we are greeted by the main screen of Acid Ape Chess GM Edition. APPEARANCE, ERGONOMICS, RESPONSIVENESS The first thing that caught my eye was the subdued and non-flashy colors, clear access options grouped in an easy to understand logical way. The app's home screen is not overloaded with information and shortcut icons. We have three main activities: playing online, using the chess engine(s), and playing a simultaneous game. After entering the option's menu (icon marked with a red border)... ...There will be a move to the expanded functions that are used most often. When you click on the button marked with a red border.... ...A context menu will expand with functions available depending on what you are currently doing. The main settings screen is structured clearly and, what positively captured me - it does not contain a lot of different options - but the important ones. Before we get into a detailed review of the significant capabilities of this program, below are some screens showing the use of Acid Ape Chess GM Edition for various activities. Engine manager Select Time Control Game play #1 Game play #2 Analysis Working with a chess database Working with Openings and Evaluation graph Working chess engine and notation window Analysis by chess engines #1 Analysis by chess engines #2 Game review with Evaluation graph Depending on preferences, user can choose different chessboard themes and chess pieces. Example #1 Example #2 Example #3 Example #4 Example #5 To summarize this part of the review... Acid Ape Chess GM Edition interface is ergonomically designed with easy access to main and detailed functions. Despite being extensive and offering a wide range of capabilities, the application is simple to use and visually appealing. The entire interface was designed and built according to the philosophy: where you are and what you use - there you have access to specific and advanced functions. I like this approach because it respects the user, who is not bombarded with a hundred functions, messages and shortcuts that are unnecessary for him at the moment. All operations are performed at a good speed without stuttering or waiting to start. Responsiveness stands at a satisfactory level allowing a comfortable using Acid Ape Chess GM Edition. The large screen (10.1 inches) is well utilized for the app, which is important given what the purpose of the reviewed program is. Smaller smartphone screens - their are optimal use - as shown in the many images on the developer's website and the Google Play Store. Acid Ape Chess GM Edition offers a thoughtful, modern and attractive interface. Only one thing is missing - landscape mode. I'm sure this mode would have been especially appreciated by users of mobile devices with larger screens, who could have had even more opportunities to customize the look and layout of the application to their needs. I almost forgot one more extremely useful feature, which is especially useful when using a mobile device that has a relatively small screen size (compared to, say, a computer monitor screen). The application provides the user with the ability to use multiple screens. One screen. Two screens; possibility to choose one of two screens. Three screens. Four screens. In practice, this means, for example, several simultaneous analyses, simultaneous games or work with the game database or openings. ONLINE PLAY Acid Ape Chess GM Edition provides access to three popular online chess servers: FICS (free) ICC (paid) Lichess (free) We can play as a guest - Anonymous. We can also use the servers as a person with a registered account, in which case our progress is recorded (e.g. rating, participation in tournaments, etc.). There is also a Player Search function. Every game played, regardless of the type of account used, is automatically saved in a chess database locally accessible on mobile device. There will be more about this later in the review. In addition to playing with human opponents or engines (legally play on some servers; must be clearly marked), you can watch live games or interesting events, such as tournaments, championships. OFFLINE PLAY You can play against another person, you can also set a position before the game starts, you can also import a position / game, you can play several games at once and... ...Finally, you can play against the chess engine(s) in one or more games at the same time. Of course, what a dubious pleasure it is to play against a chess monster like Stockfish, for example, when you can use a chess engine specifically designed to play for fun or training. I am referring to the Rodent chess engine. I encourage you to read the review of the Rodent chess engine. Rodent is one of the many chess engines that the Acid Ape Chess GM Edition developer is officially making available for download. It is a very simple operation, which I described later in the content of this review. Rodent, once downloaded, is immediately ready to start playing and is 100% compatible with all the features of the reviewed application. It is worth adding, there is no obstacle to use any other chess engine. The user can choose to play from a standard or specific position, and can also choose to play in the Chess960 format also known under name Fisher random chess. The application allows you to select a Opening Book. You can use the default one used by a particular chess engine or... You can choose an Opening Book available online provided by the developer. Rodent chess engine offers a significant number of different personalities to play with. Personalities are placed in catalogs with appropriate names. Example of famous and well-known personalities: Masters: Strong league players: Club players: Learning Players: Fun personalities: You can choose or set your time to play. An ongoing game between Darius (Myself) and Sam. Sam is one of the personalities of the Rodent chess engine. During the game, you can pause the game or quit it. You can turn on the engine or use all the other options offered by the app. You can also start a duel of chess engines on one or more chessboards simultaneously and watch them struggle. Chess engine game in Chess960 format. The greater the hardware resources of your mobile device, the more chess engines can play simultaneously. The struggle of chess engines can be very interesting; I think that if the developer introduced in future releases of the program the possibility of playing tournaments by chess engines, it would be welcomed with satisfaction by many fans for such computer duels :) Local Chess Database As I mentioned earlier, the app automatically saves all games to the storage of the mobile device. This is convenient because the user does not have to remember it every time... ...And can go back to them - recent games. The basic data of each game can be edited, and player data can be managed. Player manager. Edit Player. Add Player. My games base - manage. Edit Player window. Game Properties editor. The available functions allow use the most important operations on the data in the local chess database (in the device's storage) including sorting by various criteria. ONLINE CHESS DATABASE The application, through the Online / OTB menu, offers access to a pretty large database of chess players and their games (more than 3 million). The application offers a number of ways to search... ...And retrieve information. This is helpful because you only need to type in a few letters of a last name, for example, and players with a name containing the phrase you type in are displayed. Filter games. We can treat each game from the database in the same way as a game stored locally on the device: view, analyze, annotate, etc. Some GM Wesley So games. One of the GM Jan-Krzysztof Duda beautiful game against GM Anish Giri. The online chess database is a useful module in the reviewed application. The data is current and updated. The user has access to the games of not only famous chess players, but also to matches and tournaments played today and in the past. CHESS ENGINES The application has pre-built three chess engines. Although these engines differ in strength, they have one thing in common: they can play spectacular chess. Arasan, a great chess engine, actively developed for more than 25 years. It ranks among the top in terms of strength, far surpassing any human in this regard. Cheng, a chess engine that plays at the level of world chess champion Magnus Carlsen. Scorpio, a sophisticated chess engine using the Monte-Carlo Tree Search algorithm, which makes it an interesting partner for grandmaster-level analysis. The application offers the possibility to easily download other interesting chess engines, which will be immediately available for use. The free Texel chess engine is highlighted, and in addition... The developer has prepared a free download of modern chess engines updated to their latest versions. After making a selection, we will be taken to the Google Play Store to download and install. This is a very good solution, as the user is assured of downloading chess engine(s) from a legitimate and verified source, which are specially prepared to work with Acid Ape Chess GM Edition. Once the installation is complete and you return to the application, all chess engines will be automatically imported and ready to use They will be visible on the main screen and of course in Engine manager as well. One of the unique and very useful features offered by Acid Ape Chess GM Edition is the use of chess engines using the CECP protocol (Winboard / Xboard). The CECP protocol is mostly used by older chess engines, which may not play at the TOP level of today's engines but have many useful options to offer, such as training and/or a unique style of play. Such engine include the previously mentioned Scorpio. It is also Phalanx, which I installed using an Other option available in window Add Engine Package. The application also allows you to use a chess engine that you have purchased from Google Play; then it will automatically be imported. This is what happened with the Komodo 13.1 engine that I once purchased. Phalanx and Komodo appeared in the list of available chess engines. I created this review at an interesting time, when the latest versions of popular and powerful chess engines appeared: Lc0 and Stockfish. I welcomed the update of the above-mentioned engines by the developer immediately after their release. Bravo! This is what the approach to the Customer should be. Looking at the chess engines offered by the developer as a whole, I think it's a good choice. We have engines that play interesting styles, with a different cross-section of playing strengths including the strongest and also real gems like Rodent - a great partner for training and playing. Of course, the application offers access to chess engine settings, through which we can set the engine to work according to our preferences. Example #1, accessing Komodo settings. Stockfish 15.1 Strength As of the date of writing this review, Stockfish 15.1 ranks first in most chess engine ranking lists. So let's see how Stockfish 15.1 performs by analyzing 10 selected positions that are used for this purpose on the chessengeria.eu blog. Mostly, I have chosen games from games played by humans. I use a bundle of these positions for program reviews and chess engine tests. My goal is to test the Stockfish 15.1 on 10 positions giving it a maximum of three minutes of thought per move. I have assumed that these will be positions played by people who have allotted up to a few minutes for a move. Therefore, I did not take into account positions created in correspondence games. I also wanted to see how this chess engine would perform on an old tablet and, when finished, compare with the results achieved on a modern smartphone. During testing, Stockfish 15.1 used 3 CPU cores and (only) 16MB Hash table. Let's see what results it achieved on a vintage tablet. SF15.1 did not find the winning 1.Qxb5. After 5 minutes and 5 seconds of thought, it sees a big advantage for white. 2 minutes and 6 seconds, that's how long it took SF15.1 to find the beautiful 1.c5! Only 14 seconds. That's all it took for SF15.1 to find the amazing strike of black Rook 1...Rxb3!! And this time SF15.1 finds the best move to equalize the game. 1...Qe3 pointed out after 24 seconds. Even faster after only 9 seconds, SF15.1 indicated a winning move in the following position. After a few more seconds, 1...Qd3 was rated even much higher by this engine. SF15.1 did not find the strongest 1...Nc7. This time SF15.1 also failed to indicate the impressive and winning 1.Qf6+ And this following position proved too difficult for SF15.1 to indicate the strongest move 1.Kf2! It took 17 seconds for SF15.1 to show an impressive sacrifice of white Rook 1.Rxe7!!! The last position, extremely difficult for chess engines and for SF15.1, remained unresolved. I am impressed. Stockfish 15.1 on an old tablet solved 5 out of 10 difficult chess positions! In comparison, Stockfish 15.1 on the Google Pixel 7 smartphone solved 9 out of 10 positions (it did not solve position number 10), most of them three to four times faster. Curiosity: on iPhone 12, an almost 3-year-old smartphone (counting up to the day this review was published), Stockfish performed slightly better as the Stockfish on Google's smartphone. I'm glad to see that even on an old mobile device, the modern chess engine running on Acid Ape Chess GM Edition achieves good results. New smartphones mean new processors and chips; on such hardware Stockfish is able to play and analyze at high level. ANNOTATION AND ANALYSIS Manulan Annotation. Certainly, the attentive Reader has noticed that access to the application's functions is easy and clear; annotation is no different. The moves in the chess game annotation can be edited and comments can be added / modified. Few examples. Any annotations entered by the user will be automatically saved by the application. Automatic annotation. This is one of the most interesting and useful features with the engine(s). Any chess engine can be used; below Stockfish with MOVE COMMENT disabled. The same chess engine with MOVE COMMENT enabled. And below is Komodo with an analysis time of 3 seconds per move. Depending on the time per move set by the user, the application calculates how long it will take to analyze the entire chess game. The longer the thinking time is set, the more accurate the chess game analysis will be and the longer it will take. Once started, you can watch the progress of the analysis and the annotations made in real time. 22% of the analysis and annotations entered. 70% analysis, entered comments and annotations. Particularly important movements are highlighted with shades of red. Analysis completed. Annotations done. The process took exactly the amount of time the application calculated before it began. It is worth mentioning that the program helps the user when working with different modules by communicating depending on what the user is currently doing. For example, I decided to run an automatic annotation for a selected chess game, which caused the application to display a window indicating that the annotation of this game had already been done. It's a good idea to run the chess engine(s) to check and see what it thinks of our move(s). In addition to automatic annotation, the application marks movements with colored arrows (a detailed description is in the application's manual). The application, along with the chess engine, can prepare a graph for us to visualize the progress of a chess game. The user can choose from the available engines to re-analyze... ...And prepare a visualization of the game on a graph. While reviewing the game, you can work on and practice chess openings. The application also allows you to find games and chess players who have used the given opening. You can also use different functions at the same time, such as the Opening module and Evaluation graph. Chess opening module and analysis by chess engine. Chess engine notation and analysis window. Three lines of chess engine analysis and notation window. Analysis by three different chess engines. Analysis by three different chess engines and Evaluation graph created using these three engines. Evaluation graph in a larger window. The application uses a database of chess endings (EGTB), which it can access online. This is a convenient solution, helping to quickly check whether, for example, in a particular position either side is winning or can get a draw. Acid Ape Chess GM Edition gives the user a very large number of possibilities to obtain analyses. All of them can be very effective training tools. TACTICAL PUZZLES A large number, as many as 900 puzzles at three levels of difficulty. 900 fun and relaxing opportunities for exercise or just for enjoyment. The app meticulously notes our progress and, of course, allows us to turn on the chess engine if we need to. Below are a couple of screenshots. Verification by chess engine. It is possible to reset the results. PHYSICAL BOARD SUPPORT Acid Ape Chess allows you to play on a connected physical chessboard. A physical clock can optionally be connected to that board. Unfortunately, I do not have access to the aforementioned devices (DGT). As a result, I do not have the opportunity to review the application in terms of the use of the physical chessboard and clock. If someone will be so kind as to share these devices with me, then I will be happy to expand this part of the review. I REALLY NEED... HELP ! This section is also built with great attention to detail. From the app and from the website there is access to the detailed manual, which is continuously updated with newly introduced features. You can get in touch with the developer or read about what's new in the next versions of the reviewed program. You can also watch an introductory video of the app, which can be helpful especially to new users. Customer service is fast and at a high level. I am very pleased with this, because in addition to the actual help, it leaves a very good and professional impression. SUMMARY Here's what the Acid Ape Chess developers wrote on their website. Source: app website (2022-12-31) Is it possible with Acid Ape Chess GM Edition: Comfortably use on an old (and modern) mobile device? Yes. Efficiently work and analyze with chess engines ? Yes. Conveniently play offline and online ? Yes. Fast using the chess database provided by the developers ? Yes. Training ? Yes. In the category of programs that I had the opportunity to review, Acid Ape Chess GM Edition is the biggest and most positive surprise of 2022. Even more so, because it is mentioned about a program designed for mobile devices. This is the best example of how excellent a program that runs on smartphones and tablets can be and is being developed. And how many possibilities it offers. Acid Ape Chess GM Edition has unique features in the segment of chess programs for mobile devices, such as using multiple chess engines at the same time, working with many workspaces and chess engines using the most popular communication protocols (UCI & CECP). The strength of Acid Ape Chess GM Edition is its ability to combine different functions/modules into a logical whole giving the user a powerful tool - chess suite - for analysis, training or simply for fun. There is no doubt in my mind that... Acid Ape Chess GM Edition offers much more capabilities than most desktop chess programs, leaving far behind competitors from mobile devices. I'm always happy when chess services, engines or software are designed for the largest possible public. This is no different with Acid Ape Chess GM Edition, which runs on even the oldest devices running on Android. And how it works! Fast, smooth and without interruptions. I found no hangs or unexpected closures. It always worked well and without errors. The same is true on a modern device like the Google Pixel 7. The developer has been regularly taking care of its product for years, updating and adding new features. Not surprisingly, Acid Ape Chess GM Edition is a premium application highly rated in the Google Play store by users. I would like to see this excellent program appear in the Apple store; I think it would find many buyers among chess enthusiasts using iPhones and iPads. It's worth mentioning that the developer provides a free Acid Ape Chess from the Google Play store, which, although lacking some of the features available in the GM Edition, gives you the opportunity to explore and test the program - which I strongly encourage you to do. All features of the program and its full version is available in the Google Play store here. Acid Ape Chess GM Edition, is an application created by people who understand perfectly how a modern chess program should look, work and what it should offer. And this is something that we - the users - can benefit from.

Scid, is a free, open-source chess program created and first published by Mr. Shane Hudson in 1999. With its rich capabilities, it quickly gained popularity and recognition in the chess community. Over the years, Scid has been developed by a number of programmers, among whom Pascal Georges and Fulvio Benini have made the greatest contributions. Along with such giants as Chess Assistant and ChessBase, Scid is ranked among the best programs in its class. And it's free! Source: SOURCEFORGE As recently as 15 - 20 years ago, at a time when the best chess software was almost entirely commercialized and paid for, Scid was and still is today, the defining marker of capability and openness. It runs on all popular operating systems. When writing about Scid, one cannot forget about the Scid vs. PC program. The similar name of both programs is not accidental. Scid vs. PC is a program - the "younger brother" of Scid. More or less since 2009 Scid vs. PC has gone its own way and is also being actively developed. What differs between the two programs is the frequency of releases and the pace at which new features are introduced. Scid is more focused on working with chess engines and handling chess databases efficiently and quickly, including the largest ones with millions of games. In contrast, the development of Scid vs. PC is focused more on introducing new features and more frequent releases, including beta. Undoubtedly, the two programs have a great deal in common. In fact, the use of them is almost identical, although they differ in some aspects, e.g. Scid 5 offers a new database format, which latest Scid vs. PC 4.x does not support yet. This has implications especially for working with large game databases. You will find more about this in the body of this review. The reviewed version is Scid 5.0.2 released on March 3, 2023. Let's take a look at some of the data in the table below. Table of Scid 5 specifications. Stockfish CCRL Rating: March 18, 2023. In this review, I will try to answer the following questions: Does the default Dark Theme significantly improve the user experience ? Are the database new format (SI5) and functions that Scid offers at a level that allows it to work efficiently compared to its competitors ? Is the default chess engine well integrated with Scid ? Will the features related to the analysis and use of chess engines meet the expectations of the advanced user ? At what level are the training functions available ? Is Scid a good tool for working with chess openings ? Does Scid 5 offer any online integrations ? Let's check it out. On the blog chessengeria.eu, you will find a lot of content related to the Scid (and Scid vs. PC/Mac) program. You will get the most information from the Course consisting of five parts describing the following topics: Efficient work with a chess database Preparing for an opponent Annotating games Using chess engines Search Masterfully In these five parts, in great detail using numerous examples, I have laid out how to use Scid to accomplish all the most common tasks. The content of the aforementioned course is suitable for Scid vs. PC and also Scid users. In addition, I described Scid in the article "Tools in a chess player's workshop - Linux". For this reason, this review will not include detailed descriptions of features that have existed in Scid software for, say, 10 years. In this review, we will focus on new and most important features and capabilities that have appeared in Scid 5. DARK THEME Dark Theme, also known as dark mode, is an option for displaying the interface of chess programs with a dark background and lighter elements. It is a style of content presentation that aims to reduce eye strain and visual fatigue. With a dark background that has less light than a light background, the contrast between interface elements is reduced, which benefits the user experience of chess programs. Dark Theme has gained popularity in recent years and has become an option in many applications, including those for chess. This mode has been introduced in Hiarcs Chess Explorer Pro and ChessBase, for example. The default (dark) Theme looks like this: #1 Clear, neat and easy to read interface. There is a choice of several Themes. The Dark Theme presents itself as follows: #2 Definitely the brightness of the interface has been reduced. Let's take a look to see if anything changes when other windows are opened. #3 #4 #5 Take a look at the text in the Game Info window (below the chessboard). #6 In Dark Theme, not everything is readable compared to other (lighter) Themes. #7 Some other examples. Scid Help has not been adapted to the Dark Theme. #8 In some places, the icons displayed in Scid Help are almost unreadable. #9 The white background stands out unfavorably, interfering with reading. #10 For comparison, the default Theme with Scid Help enabled. In this case, the composition of colors, backgrounds, subtitles and icons looks correct. #11 Dark Theme -> some elements of the interface have not been properly adapted to this mode, making some of the text, icons and other content is not always readable. In Dark Theme mode, most of Scid interface elements are displayed correctly. The deeper we go in, the more functions we start using available in the new windows, some of the content may not be readable/visible to us. At this point, I have given up on using Dark Theme. I think Dark Theme mode deserves improvements and better integration with interface elements. INTEGRATION WITH CHESS ENGINE(S) Chess engine is nowadays one of the most important components of a chess program and especially – a specialized chess program, which is Scid. On the main page of this program, we can read about the possibility of analysis by means of engines. In the screenshot we even see the Stockfish chess engine. Source: Scid home page, 2023-03-20. What was my surprise when, after launching Scid 5, I found none in the chess engine selection window! Certainly, for some people who would like to use the chess engine(s) after downloading and running Scid 5, this may be a somewhat surprising and disappointing experience. Especially since Scid vs. PC (Scid's "little brother") already offers several different chess engines after the first launch, including Stockfish. What's even more puzzling is that Scid will include the Stockfish chess engine (and other engines depending on the version of Scid for different operating systems). Fedora 37 Linux, Lc0 and Stockfish chess engines available: Windows, Phalanx and Stockfish chess engines available: Mac, Phalanx and Stockfish chess engines available: This example shows a certain inconsistency. The developers have acquired, compiled and placed chess engines in the Scid program. However, these chess engines are invisible to the user by default and are different: Linux: Lc0 and Stockfish Mac, Windows: Phalanx and Stockfish This type of situation should not happen. The user, so to speak, is forced to take his time and must know how to do it in order to install the chess engine in Scid 5. Fortunately, this is not difficult. To learn how to install and use the chess engine(s) I refer you to the course entitled: Scid vs. PC - Using chess engines And that's basically the only inconvenience when it comes to the chess engine(s). Once installed, all chess engine operations work fine. #1 Analyze with Stockfish chess engine. #2 With Stockfish, Berserk, or any other modern chess engine "on board", the results of their analysis are of very high quality; finding the best continuation line or moves is not a problem and takes relatively little time. #3 Of particular note is the new chess engine selection and configuration window. You can easily add and configure chess engines in a new window, with clear access to all parameters. Another new feature, the evaluation bar and best move arrow, may be useful - they will make analyses using chess engines more clearly presented to the user. Evaluation bar and best move arrow. Evaluation bar, extended engine output and variation board. Scid, unlike, for example, ChessBase, perfectly supports chess engines communicating via the UCI protocol, giving access to all their parameters (example: UCI Elo). Highly praiseworthy is the ability to work with engines that use the CECP communication protocol (XBoard, WinBoard), which allows you to use, for example, the famous Crafty and other older engines with an interesting style of play. Position analysis by Berserk and Stockfish chess engines - at the same time! The analysis functions offered by Scid 5 are diverse and allow to use chess engines in various ways including changing their parameters. Analysis of several continuation lines, simultaneous use of different engines, variation board, etc. - the possibilities are many and should satisfy even advanced users. An example of an automatically analyzed whole game (Berserk engine) with Scid 5 annotations. The only thing I miss in a program of this class is the ability to put a visible diagram with a given position in the notation of the game. This would certainly make the visualization more attractive during review and analysis. SI5 - NEW CHESS DATABASE FORMAT To quote the Creators: "(...) One of the most significant changes in this version is the introduction of a new database format, SCID5, that allows you to store up to 4 billion games. With this new format you can, for example, import and study the games of your friends from database.lichess.org and use that knowledge to easily beat them :-)." Source: Scid Wiki Operations on chess databases are the most important part of functionality in a dedicated software like Scid. Nowadays, when storage is widely available and their prices are not prohibitive, the speed of operation can be one of the most important criteria for choosing a program in the field of chess databases. 1. Convert to SI5 format. Scid 5 does not offer base conversion from old formats to the new format. Instead, on request, Scid 5 can take games from the old-format database and paste them into the new-format database. The whole thing is done in a few clicks, and... The transfer takes literally seconds. For testing, we will take CaissaBase 2022. This database contains 4,874,268 chess games. It takes a very short time to transfer a large database of chess games from one with the old SI4 format to one with the new SI5 format. Even on the old computer it took much less than one minute. 2. Work speed. We can use the chess database in hundreds of different ways and for different purposes. I will compare the speeds of most common operations on the database in the old format versus the database in the new format. To make the results as clear and understandable as possible, I will make a comparison between a 2014 computer and a 2020 computer. The testing methodology adopted is analogous to that used in the ChessBase 17 review. 2a. Preparing an opening report for my favorite Latvian gambit. Opening Report, is one of the most widely used features in any chess database. Regardless of the database format used, you get a report in just a few seconds. This is several times faster than we can achieve with ChessBase 17 ! Opening Report, Linux arm64 Unfortunately, the same report run on Macs, is generated about 10 times longer, that is, instead of 3 seconds we wait 30 seconds for the result. I have checked this repeatedly on different chess openings and on different Macs: both those with Intel processors and those with the Apple Silicon M1 processor. Opening Report, Mac Apple Silicon M1 The result is unequivocal, when creating Opening Report, Scid running on Macs takes much longer to do so. And although 30 seconds is not long, but the difference in speed reaching ten times (!) is a result that proves the lack of any optimization / testing (?) for Scid 5 for Mac. Scid 5 running on Windows 64-bit achieves almost the same results in this test as those shown in the chart above - on a Linux PC (arm64 & x64).. 2b. Deleting comments from a selection of 100 000 games. Also, during this operation, the new SI5 format performs better. The operation time is shorter compared to the execution time of this operation in the old SI4 format. Again, the difference is only a few seconds between the old and new formats, regardless of whether Scid is running on an older or modern computer. It is worth noting that the times of this operation are several times shorter than in the ChessBase program. 2c. Pasting previously copied games. The results speak for themselves. The new SI5 format is faster than SI4, but what are the differences - just a few seconds! Scid 5 begins to "slow down" only with databases containing 1 million games. And in this test the Mac version of Scid 5 was slower; the differences reached a maximum of a few seconds to the disadvantage of Macs compared to the same operations performed on Linux and Windows computers. 2d. Search for positions by simple, medium and very complex criteria. Searching for any item regardless of criteria takes a few seconds at most. That is, it is extremely fast! 2e. CaissaBase 2022 backup. Backup, in the sense of the function offered by Scid 5, consists in duplicating the selected chess database. When duplicating, there is no compression process to a single file, as, for example, is done in ChessBase. I think it would be to the benefit of users, to make this function available with a choice of compression. 3. Space. Databases in the new format take up more space, although given the capacity of even hard drives that are several years old, this does not matter much. Below is the data on the volume of bases: The new SI5 format takes up a little more space, the difference is about 5%. Of course, for smaller bases the difference will be correspondingly smaller. SI5 - Summary In all types of most common operations, the new SI5 format is faster than the previously used SI4 format. Even on a computer that is already 9 years old (on the day of writing this review), most operations are performed in a surprisingly short time - a few, a dozen seconds at most! The exception is working with Scid 5 on Mac computers. For a reason that is incomprehensible to me, all file operations related to database handling, take much longer than in the same program using the same database, running on a Linux and Windows computer. It is worth noting that the times of almost all operations counted in a few, at most a dozen seconds on a database of millions of games - this is impressive. Compared to all competitors, in this area, Scid 5 is the undoubted leader. CHESS960 SUPPORT Chess960, also known as Fischer Random Chess, is a chess game variant in which the initial positioning of the figures on the board is random (with some restrictions). Chess960 is popular among chess players and chess fans because it avoids chess openings that are often studied and repeated, giving the chance for interesting and creative play. Scid chess program in its latest version 5 supports chess games in Chess960 format and allows their analysis. #1 An example of a loaded Chess960 game in the initial setting. #2 Openings report with reference CCRL-404FRC database. #3 Analysis of positions from the Chess960 game by the Stockfish chess engine. Chess960 became popular thanks to its inventor, former world chess champion Bob Fischer. Fischer believed that chess had always been dominated by openings, and Chess960 allows for more varied and creative play. In recent years, Chess960 has also become popular due to its promotion by the international chess organization, FIDE, which organizes world championships using this formula. IMPROVED PGN SUPPORT This is the last new feature in Scid 5, which is worth writing about, because it improves the comfort of work. A few words of description from the Creators: " It is now possible to directly modify games without having to convert the PGN files. Additionally, new line characters in comments are not removed or added, preserving the formatting chosen by the user. " Source: Scid Wiki Scid 5 allows direct modifications, so the user saves time and does not need to perform additional steps. It works well and as described. It is such seemingly small improvements that make Scid even better to use - especially if you often use databases in PGN format. TRAINING FUNCTIONS Scid 5 and its previous versions, is not a program specialized for chess training. If you are looking for a free chess program dedicated to training, then I suggest you take a look at Lucas Chess. However, Scid 5 has some capabilities in this area that can be used for basic training. A few examples. #1 When analyzing with the engine, after pressing the icon with a barbell (Training) and setting a thinking time, Scid 5 will insert the movement that the engine proposes into the notation window. Instead of 15...b4, the proposed move is 15.... Rce8. #2 In the Play menu, we have several training functions, among which Review game is an interesting one. This function works in such a way that after indicating a move to analyze - in this case 15...b4 - the program after a set time (set to 5 seconds, visible in the picture) provides its commentary on this move and offers to show a solution / another move. If we need Scid to make a more thorough check, we can extend the analysis to even many minutes of thinking time. Below is a window with an analysis of another move in the same game. Scid 5, like its main competitors Chess Assistant and ChessBase, can be used as a tool for prepare even very advanced training. Due to the nature and capabilities of this program (chess base support), Scid 5 can be tailored adequately to meet the training needs for chess players at any level. OPENINGS For working with chess openings, for creating, changing, expanding and so on - Scid is not the best choice. It is not always a convenient tool. For example, to create a new opening book (polyglot), according to the Scid help file, it is best to use the command line. Other functions are available through Scid's graphical interface. We also have an opening book tuning function. In general, for working with Openings, I recommend the Lucas Chess program more. Chess Openings are obviously very important in Scid 5 as a key component used in database work. One should mention Opening Report and others, which I covered in great detail in a series of Scid vs. PC courses (see the beginning of this review). I REALLY NEED... HELP! The help system in Scid is very extensive and functional. What is noteworthy, is that the user gets access to the Help offline, without using the Internet. Information can be obtained in various ways, such as through thematic sections: And also through specific keywords: Also at the user's disposal is a mailing list and... tips of the day :) In general, due to the popularity of Scid, you can also get constructive a help on various chess forums on the Internet, as Scid has many long-time loyal and knowledgeable users. ONLINE INTEGRATIONS Scid 5 offers the possibility to use FICS - Free Internet Chess Server. You can play over the Internet, observe games and tournaments, train using so-called lecture bots. As the name suggests, the use of FICS is free. You can use this server anonymously, or you can create an account and enjoy the benefits of doing so (progress tracking, rating, etc.). BUGS During about 100 hours of use of Scid 5, many times the program unexpectedly stopped working. #1 #2 #3 Few times, the program crashed right after starting. #4 This occurred while using various functions. #5 Undoubtedly, Scid, although easy to use, is a complex program that, in addition, has versions for different operating systems. I make no secret of the fact that I am a little surprised by the bugs found. They did not appear a lot, but as always in such situations - at the least unexpected moments. For reference, Scid vs. PC - that is, the "little brother" of the reviewed Scid program - during the extremely intensive and very long (about 1000 hours) use by me while writing courses, it worked stably and correctly. SUMMARY Here's what the developers of Scid wrote on the project's website. Source: SOURCEFORGE (2023-03-21) Does the default Dark Theme significantly improve the user experience ? No. Are the database new format (SI5) and functions that Scid offers at a level that allows it to work efficiently compared to its competitors ? Yes Is the default chess engine(s) well integrated with Scid ? No. Will the features related to the analysis and use of chess engines meet the expectations of the advanced user ? Yes. At what level are the training functions available ? Basic. Is Scid a good tool for working with chess openings ? No. Does Scid 5 offer any online integrations ? Yes. Upon first launching Scid 5, the user is greeted by a neat, clear and almost minimalist interface. We don't see too many options, there are no ribbons occupying a significant area of the screen space and additional menus overloaded with dozens more functions. Scid 5 GUI draws handfuls from the best solutions seen in Linux distributions and macOS systems. Despite the program's very large capabilities, it is easy for the user to find them, as everything is literally in front of him on the sole and main bar. The entire interface is highly customizable. You can work with one window, and you can have multiple windows open, and in addition, they don't have to be docked - that is, the user can place them where he wants and in the size he needs. Of all the advanced chess programs, I was most comfortable using Scid 5. It's a bit of a pity that the whole thing is disrupted by the somewhat underdeveloped Dark Theme, which makes it difficult or impossible to read some information from the screen. I think that improving this mode shouldn't be a big challenge for the developers, as it's just a matter of some subtle changes in the color scheme. At the heart of a program like Scid 5 is the level, speed and quality of support for chess databases. Here Scid stands out from all its competitors. Databases containing up to hundreds of thousands of games and more are in all - even the most advanced ways - Scid 5 handled extremely fast and at a very high level. If we add to this that even on older computers the processing speed is very high - we have the undisputed Leader in this segment of operation. In a modern chess program, the possibility of using chess engines cannot be missing. Also in this area, in terms of the possibilities offered, Scid 5 positively stands out. The user can use one or multiple engines at the same time for various tasks related to position and whole-game analysis, automatic annotations or accurate verification of specific moves. The training functions, and those for handling chess openings, are aimed at users who need them at a rather basic level. Nevertheless, they are not poorly implemented, on the contrary, you can train, for example, the different phases of the game, tactics, move prompts, etc. Nowadays, it is hard to imagine an advanced chess program without any web/online integrations. Here, Scid doesn't have much to boast about; the user is only offered integration with FICS (Free Internet Chess Server) for free. We don't have, for example, the possibility to connect to an extensive database of openings / tablebases / engines, etc. Scid is a program that has been known and used by a large chess community for many years. Among other things, it owes its popularity to the fact that it is available for many operating systems. Unfortunately, in this case, quantity does not always go hand in hand with quality. The Mac version significantly deviates in speed compared to the Linux and Windows versions. On Mac, the speed of execution of some operations is up to 10 times lower than in Linux and Windows environments. Scid 5 has no officially available version for the latest and fastest Macs using Apple Silicon cpu's. Only the x64 version is available. Interestingly, the Mac version of Scid 5 is the most stable and least crashing. Bugs and underdeveloped functions are Scid 5's biggest weakness. I don't remember a chess base program that unexpectedly closed or crashed so often and in so many different situations. The Mac version is the best in this regard, followed by the Windows version, and I have noted the most errors using the Linux version (x64 and arm64). So what if Scid 5 processes data even a few faster than its competitors, if it crashes unexpectedly during or after completing this activity. Unfortunately, more than once I found such situations where I lost my work and had to start all over again. It is clear that the testing phase and, consequently, the elimination of bugs - this was not a particularly heavily exploited activity before the release of the fifth version of Scid. Another weakness of Scid is underdeveloped features. One I have already mentioned, I mean Dark Theme. Another example is the lack of integration of Scid 5 with the default chess engine. I showed exactly what this consists of in the text of this review. This type of situation has a negative impact on the user experience. I'm sure this can be corrected relatively easily, and that's what I'm hoping for in the next release of Scid. Scid is a program that sometimes just stops working. And this is unacceptable in a program of such class and reputation built over the years. Scid is also a program that has some capabilities at a higher level and in better quality than its competitors, including commercial ones. Is it worth giving Scid 5 a chance ? In my opinion, yes, but it suggests waiting for updates, which I hope so - will eliminate the biggest pains of this program, which I described in this review. SCID 5 SCORE In the Files area you will find free Scid 5 for download.