Andscacs 0.1 with NN file from Coiled ...

[JohnWoe]

Any correct implementation will do the same so there's not much to be gained in reimplementing it

The same is true about NNUE, nothing is gained from reinventing the wheel, nothing is gained from creating own implementation and creating own net. There's that path of doing those things, or half those things and the path of copying SF and net, or copying half of them, or avoiding NNUE altogether and staying with classical evals.

An there's the testers that choose the paths to only test original eval, and others that only test original implementations, and others that only test original nets, and others that only test strong engines, and others that test everything.

All that's all fine and dandy, what is not is the Owners Of Decency dictating that there's some correct paths and that there's some wrong paths and that the authors that choose wrong paths don't deserve to have their engine tested.

I think why people do all this has been forgotten, I've known people that avoided all this by keeping their engine private, and only shared them with their friends, and I was from the very few lucky people that had some of them. But in the end most people don't have valuable things just because others would have critiqued them if they were released publicly.

Apparently the best thing to do is do whatever pleases yourself and don't care about critics' opinion, and release everything you want, there will be people that will enjoy it and will not care about the paths to get there. Now that the gates [of having engines use Stockfish's evals] are open I wish to see some engines' searches with other engines' evaluations, as this will create new chess entities and who knows if a great one is hiding in plain sight, and we could enjoy it if people stopped caring so much about their pocket universes.

There are definitely things to be gained in experimenting with new network architectures and implementations. This is how progress is made and differentiation is achieved. Your comment is rather nonsensical.

Most testers have stated they're uninterested in testing engines which copy Stockfish's evaluation function which shouldn't exactly come as a surprise. Who wants to test a bunch of engines which evaluate positions identically? Testers/users are free to do as they please and, likewise, authors are not entitled to have their engines tested.

Authors are not entitled... lol
I'm giving away a high quality unique product for nothing ( zilch / nil / ingenting ). And I'm entitled to something? That "testers" waste their precious time w/ my lowly engine. It's the other way around. The only thing coming back to my way is some 4 digit number. I didn't pay 1000e for ThinkPad just to see some f*** 4 digit number.

It's like Elon Musk should be humble and entitled that I would pick up some Tesla for free.

Anyway Connor is right that entropy is lost when every top engine is the same!
Every top engine has the monstrous 1,000 lines search function. Which is found in StockFish.
Mayhem is pretty much the only engine which has maximum 20 lines functions.

In philosophy you don't get your name in history if all you can do is perfectly quote Nietzsche. Only if you invent something new you'll make history!

Lately I wrote a tetris AI. Took me some time to find the optimum algorithm. I tried Monte Carlo, Neural networks etc.
Then I figured a the correct algorithm. Well after I checked what others have done. I only came up w/ complexity.
Perfect play. Can even change board size, pieces etc rules and always perfect play.

[Ovyron]

I've performed the experiment described (comparing static evaluation correlations across a large sample of positions) for previous SF networks and can do so again if you'd like. Somehow, I doubt you'd find it convincing as you seem to already be pretty certain of the soundness of your own opinions...

Not static eval, I'm talking about the move choice and score (say, preferring the white or the black side) after the regular time expected to think on a game. I'd expect 59% similarity or less, because the draw width isn't that big and 58% would take an elo hit.

Pairing Stockfish's evaluation function with a similar, yet inferior, search function is not remotely technically interesting in my opinion nor many others'. Consequently, I'd prefer to not see such engines consume too much of testers' resources. That's my bias. So long as more original/technically interesting efforts aren't passed up in favor of lower effort (partial) clones, I'm not particularly inclined to care.

But this is about what you know. If you didn't know what eval an engine was using you could sit an enjoy the games, if that's your thing. If an engine using stockfish NNUE plays more differently than another that has original eval but is more similar then what eval is used doesn't matter.

Then we could draw a line at how similar one engine and another is, and have an objective quality for rejection and for why we'd not want people to test them (because if similarity is high enough then it's as if we were testing the original engine more times). If two engines produce 80% of similar moves then we can test the second one less because we already have the correct samples from the original engine.

But if someone uses a stockfish NN and produces something that plays entirely differently then the issue makes no sense, because it'd be a problem of your knowledge of how the engine was made, in that case, lack of knowledge is the solution, just don't peek at how they're made.