Fat Fritz 1.1 update and a small gift

Time to update

If you haven’t yet updated your copy of Fat Fritz, now is the time to do it as it brings more than minor enhancements or a few bug fixes. This update will bring the first major update to the Fat Fritz neural network, stronger than ever, as well as a new smaller one that is quite strong on a GPU, but also shines on even a plain CPU setup.

When you open Fritz 17, presuming you have Fat Fritz installed, you will be greeted with a message in the bottom right corner of your screen advising you there is an update available for Fat Fritz.

Fat Fritz is updated

When Fat Fritz was released with Fritz 17, updates were promised with the assurance it was still improving. Internally the version number of the release was v226, while this newest one is v471.

While thorough testing is always a challenge since resources are limited, a match against Leela 42850 at 1600 nodes per move over 1000 games yielded a positive result:

Score of Fat Fritz 471k vs Leela 42850: +260 -153 =587 [0.553]

Elo difference: 37.32 +/- 13.79

1000 of 1000 games finished.

Also, in a match of 254 games at 3m +1s against Stockfish 11 in AlphaZero ratio conditions, this new version also came ahead by roughly 10 Elo.

Still, it isn’t about Elo and never was, and the result is merely to say that you should enjoy strong competitive analysis. For one thing, it is eminently clear that while both Leela and Fat Fritz enjoy much of the same AlphaZero heritage, there are also distinct differences in style.

The Perfect Opening: Berlin or Najdorf?

Perhaps one of the most obvious ways to highlight this is just the start position. If you let the engine run for a couple of minutes on decent hardware, it will tell you what it thinks is the best line of play for both White and Black based on its understanding of chess.

As such, I ran Leela 42850 with its core settings to see what it thought. After 2 million nodes it was adamant that perfect chess should take both players down the highly respected Berlin Defence of the Ruy Lopez.

Leela 42850 analysis:

info depth 19 seldepth 56 time 32675 nodes 2181544 score cp 23 hashfull 210

nps 75740 tbhits 0 pv e2e4 e7e5 g1f3 b8c6 f1b5 g8f6 e1g1 f6e4 d2d4 e4d6 b5c6

d7c6 d4e5 d6f5 d1d8 e8d8 h2h3

This is fine, but it is also very much a matter of taste.

Fat Fritz has a different outlook on chess as has already been pointed out in the past. At first it too will show a preference for the Ruy Lopez, though not the Berlin, but given a bit more time by 2.6 million nodes it will declare the best opening per its understanding of chess and calculations is the Sicillian Najdorf.

Within a couple of minutes this is its mainline:

info depth 16 seldepth 59 time 143945 nodes 7673855 score cp 28 wdl 380 336

284 hashfull 508 nps 54227 tbhits 0 pv e2e4 c7c5 g1f3 d7d6 b1c3 g8f6 d2d4

c5d4 f3d4 a7a6 f1e2 e7e5 d4b3 f8e7 e1g1 c8e6 c1e3 e8g8 f1e1 b8c6 h2h3 h7h6

e2f3 a8c8 d1d2 c6b8 a2a4 f6h7 a1d1 b8d7 f3e2 h7f6

Remember there is no right or wrong here, but it does help show the natural inclinations of each of these neural networks.

Even if chess is ultimately a draw, that doesn’t mean there is only one path, so while all roads may lead to Rome, they don’t all need to pass through New Jersey.

A new tune

Trying to find the ideal recipe of parameters for an engine can be daunting, and previously multiple attempts had been made with the well-know tuner called CLOP by Remi Coulom. Very recently a completely new tuner 'Bayes-Skopt' was designed by Karlson Pfannschmidt, a PhD student in Machine Learning in Paderborn University in Germany, who goes by the online nickname "Kiudee" (pronounced like the letters Q-D). It was used to find new improved values for Leela, which are now the new defaults.

His tuner is described as "A fully Bayesian implementation of sequential model-based optimization", a mouthful I know, and was set up with his kind help as it ran for over a week. It produces quite fascinating graphical imagery with its updated values. Here is what the final version looked like:

These values, slightly rounded, have been added as the new de facto defaults for Fat Fritz.

Fat Fritz for CPU

This is a completely new neural network trained from Fat Fritz games, but in a much smaller frame. Objectively it is not as strong as Fat Fritz, but it will run much faster, and above all it has the virtue of being quite decent on even a pure CPU machine. It won’t challenge the likes of Stockfish, so let’s get that out of the way, but in testing on quad-core machines (i.e. my i7 laptop) it defeats Fritz 16 by a healthy margin.

Note that this is not in the product description, so needless to say, it is more nor less a gift to Fritz 17 owners.

Enjoy it!

About the Author

Born in the US, he grew up in Paris, France, where he completed his Baccalaureat, and after college moved to Rio de Janeiro, Brazil. He had a peak rating of 2240 FIDE, and was a key designer of Chess Assistant 6. In 2010 he joined the ChessBase family as an editor and writer at ChessBase News. He is also a passionate photographer with work appearing in numerous publications.

Related news:

	Fat Fritz 2.0 - The new number 1 @ 09/02/2021 by ChessBase Shop (en)
	Fat Fritz: Small differences, big effect @ 20/04/2020 by Albert Silver (en)
	Fat Fritz and the 1200 - Chess Improvement made Easy! @ 03/03/2020 by Tanmay Srinath (en)
	Fat Fritz analysis: A matter of technique @ 20/12/2019 by Albert Silver (en)
	Introducing Fritz 17 with Fat Fritz and other goodies @ 13/11/2019 by ChessBase (en)
	Fritz 17 - The giant PC chess program, now with FAT Fritz* @ 01/11/2019 by ChessBase Shop (en)
	Analysing your openings repertoire with Fat Fritz @ 28/10/2019 by ChessBase (en)
	Fat Fritz and the KID @ 25/09/2019 by Albert Silver (en)
	Using Fat Fritz in the Engine Cloud @ 21/09/2019 by Nadja Wittmann (en)
	Fat Fritz – What on Earth is that? @ 12/09/2019 by Albert Silver (en)