TalkChess.com

IpMan was also very kind to provide some compiles.

They can be found at: http://ipmanchess.yolasite.com/compiles.php

Release highlights: Not too long after 3.0 was released there was an important false mate fix upstream, which has now been merged. Small performance improvement. Slightly better tactical awareness. Small progress scoring improvement. Numerous upstream patches to Stockfish. Release Page: https://gith...

What is happening is the superior NNUE eval allows for more aggressive search optimizations (narrower search) than what was/is optimal with only hand-coded eval.

Using classical eval still has the more aggressive pruning, which is not optimal for it.

Fwiw, I strongly recommend using a power of 2 for hash size. Others may or may not "work."

What was your test? Nothing like that. But those ideas bring up a good point which may or may not be clear to others... While I can only speak for myself, I do not personally have any issue whatsoever with the idea of biases in weights or internal structures of the NN provided the information avail...

You did not answer the question. And nobody asked what you meant. As has already been explained, search is meaningless to the OP. A static evaluation literally cannot be an opening book without search. Policy recommendations are not static evaluations, either. In fact, they're not even evaluations, ...

It's a good thing that we're not comparing the static evaluations, but the engines themselves. Lol, what exactly do you think is meant by the NN? The OP is not referring to the monte carlo tree search. And I hope, for your sake, you are referring to the static eval, because anything else is laughab...

In fact, the nice thing about SPSA is that it only learns on match results. And yet, I believe you will find the static eval of SF (especially classic) is hundreds of Elo weaker than Lc0 networks. It is very hard to find a three-move line that SF doesn't have shockingly reasonable PVs for with low ...

There's no way around it: SF's search is hilariously well tuned on openings. What? There is no phase information used in or available to search. This statement makes me rather suspicious of your other assertations. Furthermore, a robust (wide) 3-moves book is use for testing, which is rather the op...

cucumber wrote:SF12 knows opening theory better than Leela does.

On 1 node (or equal node counts) or via search? Because I have a hard time believing the former....