TalkChess.com

nobody sane will miss CTF - it's a garbage dump so I vote for 2., close it

I am not sure about the training though which could use FLOAT precision, unless they wanted to do the training with quantization as well. I'm not sure whether training with quantization is a good idea - tried training a tiny net with quantization and the result was worse than without quantization -...

As far as I'm aware pragma is specific to microsoft compiler only you're wrong, #pragma once would be a typical example see for yourself, try this in godbolt.org, select clang, -O3 -march=native #include <stdio.h> #include <stdlib.h> extern float fast_dot(int count, float * a, float *b); #pragma fl...

I wonder why auto-vectorization is not used instead of the manual SIMD code NNUE currently has. There is separate code for AVX2, SSE3,SSE2,SSE etc which is kind of ugly. Your code above can be easily auto-vectorized by the compiler, so I wonder why this approach is not taken. I don't see any operat...

SF-NNUE depth 1 which is 500-1000 nodes is 2400Elo. That is at least 500 Elo above the best dedicated chess computers. SF-NNUE on 6502 would have for sure more than 1000nodes per move. It wouldn't be any contest, it would be a slaughter. and how is that supposed to work? the 6502 has a 16-bit addre...

Thanks for the question. MinicNNUE is released, testable, but I don't want it to "replace" Minic in the various rating lists (for reasons already explained). So I make a difference between "released to public" and "official in rating lists". Vocabulary matters indeed, you are right. I see, thanks f...

That is wrong ! MinicNNUE is NOT official Minic, so Minic rating didn't jumped at all. What jumped is my little knowledge about NN and this is already a good new :D if that's so, then how come people are testing it, assuming you haven't released it to the public :) I'm new to NNs as well, I only st...

NOT the same thing (white clearly winning) with "napping nexus" instead of "nascent nutrient" => this is a net bias !! Conclusion nascent nutrient is good playing black ... less good playing white ... This is still strange ... really? I thought that it's common to swap board from stm's point of vie...

fixed depth doesn't mean much, neither does 1400 games

I assume you use MinGW on Windows.
have to tried to link the CRT statically? -static might work