\\ Home Page : Articolo : Stampa
ProteusSF, il mio derivativo da Stockfish GPLv3 open source per tutti gli appassionati di scacchi!
Di Alex (del 23/11/2023 @ 00:00:01, in Giochi intelligenti, letto 16311 volte)
DONATION CROWDFUNDING TARGET 1000 Paypal donations 253
Thanks to: Patrick, Claudia, Alessandra, Yatin Yin, anninghn, Cristian, Robert, Rodriguez, Antoni, Khaled, Rambody6, jannotin , Karl

ProteusSF-Aureo closed PRIVATE betatester program is completed!

NOW OFFERING only PC, Mac M1|Intel & Android compilation of Stockfish and all open sources engines. ASK ME TO DO THE JOB FOR YOU FOR 10!!

ProteusSF FREE DEMO public release
ProteusSF-Piranha 15.1 (with GPLv3 source)
updated to last Stockfish 15.1 + Polybook support

I'm developing next-gen ProteusSF with Artificial Intelligence

On Playchess.com is very good: First 3366 ELO blitz, 2499 bullet, 2529 LT!

After 3 months of developing in C++ I'm starting my first tests of ProteusSFX-AI !!! First implementation: A supervisor asks to Bard and ChatGPT APIs the best strategy according to the opening when out of the book, then ProteusSF applies some pre-configuted patterns. Eg It doesn't try to win against C67 with White. No learning anymore, contestual analysis in real time that is much faster! Like some leading chess programs, such as AlphaZero and Leela Chess Zero, that already use LLM to improve their performance. LLM can be used to improve chess programs in a number of ways. First, LLM can be used to generate new game ideas. This can be done by using LLM to analyze a wide range of chess positions and identify possible moves that could lead to an advantage. Second, LLM can be used to evaluate the strength of a chess position. This can be done by using LLM to analyze the possible moves of both sides and determine which position is more advantageous. Third, LLM can be used to learn from chess games played by humans. This can be done by using LLM to analyze the games and identify the strategies and tactics that were used to win. Some of the specific ways in which LLM can be used to improve chess programs include: Move generator: LLM can be used to generate new game ideas that might not have been considered by a traditional chess engine. Position evaluation: LLM can be used to evaluate the strength of a chess position more accurately than a traditional chess engine can. Learning from chess games: LLM can be used to learn from chess games played by humans more efficiently than a traditional chess engine can. Chess programs that use LLM have been shown to be able to beat traditional chess programs. For example, AlphaZero beat Stockfish, which was considered the best chess engine in the world at the time, in a series of games. It is likely that LLM will continue to improve the performance of chess programs. As LLM technology continues to develop, chess programs that use LLM will become even stronger. Additional information: LLM stands for "large language model". It is a type of artificial intelligence (AI) that is trained on a massive dataset of text and code. LLMs can be used for a variety of tasks, including generating text, translating languages, writing different kinds of creative content, and answering questions in an informative way.

August 18, 2023: PRIVATE Gold Master build is ready! ProteusSF-Aureo based on latest Stockfish-dev 16 with Learning and up to 2 Polyglot books support. Many thanks CLOSED INTERNAL betatesters!!

Inspired by the Golden number, enhancing Stockfish propotions harmony.


Update February 28, 2023: LATEST BUILD 23.5 ProteusSF-Sunrise including an optimized ProteusSF-Sunrise.exp is ready for internal tests!!
Stockfish-dev derivative plus Polybook .bin, MCTS support and Learning. Stronger than ever, holds Stockfish and every derivative. Choice
Contempt, Pure|Hybrid|Classical no NNUE, Positional or Materialistic style!

CLOSED BETA For Microsmeta.com internal PRIVATE TESTERS only!
(GPLv3 PS-23.5 DIRTY source *Linrock architecture still MISSING*)

Very good performance online on Playchess.com running on PCs with only 4 cores against Core i7, Ryzen 7, Ryzen 9, Xeon on ThreadRipper boosted engines up to 128 threads ...beyond AI and Zeus 50.3, Corchess 4, LC0, ShashChess and BrainLearn, Crystal 6, Stockfish 16-dev, Dragon 3.2, Eman 9.40, Charisma, Hypnos, Dark Sister, SF PB and ToreroX3Pro!!!

December 16 2022 - Christmas GIFT:
ProteusSF-Piranha 15.1 (with GPLv3 source)
updated to last Stockfish 15.1 + Polybook support

December 16, 2022: ProteusSF-Piranha 15.1 is available to the public!
Why there has been a delay on releasing the updated ProteusSF-Piranha? For the fine tuning of ProteusSF a smartphone is already exploded and another one is about to do the same. 15000+ downloads and very few supporters! Do you like my work? Please consider 10 donation to help me on energy bills and hosting costs (I need to buy a new dedicated Android)
Since October ProteusSF-Piranha-221016 & Sunrise will be private
I have no budget for free developing & hosting server costs Microsmeta.com private testers will still receive last closed betas via email

Download per Windows | Download per Android | Download per Mac

EXTRA: Ask my customized version of:

- Stockfish-Polybook 15.1
- CorChess3.0-Polybook
- Crystal-Polybook 5 KWK 221106

and my custom compilations of your desired engines...Donating only 10 Euro for each one and specifying in the donation comment for which operating system and version (PC avx2, bmi2, sse41, sse3 or oldPC | Android ARMv8, ARMv7 or Intel | Mac M1 or Intel ) you need to be compiled for you! You will receive it quickly on your email : - )

VISIT BanksiaGui ProteusSF dev Forum
with all development news and tests (ENGLISH ONLY)

featuring TCEC 2022 (Most reliable chess engines tournament worldwide)
ProteusSF unbalanced openings test against top engines & other customized books!

Download Superfinal Jeroen Noomen selection unbalanced opening test suite
VISIT Chess.com official ProteusSF home for generic users



Based on Crystal 5 KWK.
New aggressive tactical playing style and focused on problem solving, ideal for human analysis
...It snifs tactical opportunities. Perfect complement to ProteusSF-Sunrise for PRO players!!



ProteusSF 030822

July 27, 2022 ProteusSF RBE 008c (Rocky Balboa Edition) with learning

Is designed only for powerful hardware or it is too slow!

July 30, 2022 - New huge learning file with latest won games against top engines & books on best hardware! Download & replace the existing one:
ProteusSF.exp-220728.zip 602 MB


NB: Per poter utilizzare il motore necessaria una inferfaccia. Vi consiglio l'ottima e gratuita BanksiaGui disponibile per Windows, Linux, Mac e iOS!
Click per ingrandire l'immagine

Se necessitate di aiuto per installarlo, lasciatemi un commento!