Are we sure that Stockfish NNUE is better than the Normal Stockfish ?

[Chessqueen]

https://tcec-chess.com/live.html

[DrCliche]

Sure enough that three draws (lol) at TCEC shouldn't measurably change our extreme confidence, yes.

[Laskos]

Sure enough that three draws (lol) at TCEC shouldn't measurably change our extreme confidence, yes.

Just a different worldview and perceptions. I guess the priors of both of you have a similar mean but very different widths. Both of you expected SF NNUE to be stronger than SF Classic by a similar margin, say 124 Elo points, but with different emotional and mental attitude about your confidence in that.

I pictured the priors here:



After these 3 TCEC draws, the posterior estimate of the difference between SF NNUE and SF Classic in his case dropped to 32 Elo points from a priori 124 Elo points, in your case dropped to 113 Elo points from the same 124 a priori Elo points. So he is legit in asking "Are we sure that Stockfish NNUE is better than the Normal Stockfish ?" and you are right in replying "Sure enough that three draws (lol) at TCEC shouldn't measurably change our extreme confidence, yes."

[peter]

Sure enough that three draws (lol) at TCEC shouldn't measurably change our extreme confidence, yes.

Just a different worldview and perceptions. I guess the priors of both of you have a similar mean but very different widths. Both of you expected SF NNUE to be stronger than SF Classic by a similar margin, say 124 Elo points, but with different emotional and mental attitude about your confidence in that.

I pictured the priors here:



After these 3 TCEC draws, the posterior estimate of the difference between SF NNUE and SF Classic in his case dropped to 32 Elo points from a priori 124 Elo points, in your case dropped to 113 Elo points from the same 124 a priori Elo points. So he is legit in asking "Are we sure that Stockfish NNUE is better than the Normal Stockfish ?" and you are right in replying "Sure enough that three draws (lol) at TCEC shouldn't measurably change our extreme confidence, yes."

46 games right now in this division with 3 games won, so 43 draws.

[Laskos]

Sure enough that three draws (lol) at TCEC shouldn't measurably change our extreme confidence, yes.

Just a different worldview and perceptions. I guess the priors of both of you have a similar mean but very different widths. Both of you expected SF NNUE to be stronger than SF Classic by a similar margin, say 124 Elo points, but with different emotional and mental attitude about your confidence in that.

I pictured the priors here:



After these 3 TCEC draws, the posterior estimate of the difference between SF NNUE and SF Classic in his case dropped to 32 Elo points from a priori 124 Elo points, in your case dropped to 113 Elo points from the same 124 a priori Elo points. So he is legit in asking "Are we sure that Stockfish NNUE is better than the Normal Stockfish ?" and you are right in replying "Sure enough that three draws (lol) at TCEC shouldn't measurably change our extreme confidence, yes."

46 games right now in this division with 3 games won, so 43 draws.

Where is Jeroen? His openings usually avoided this drawfest. With TCEC if one goes with the usual openings the draw rates between top engines are above 90%.

6 more draws of SF NNUE, and DrCliche will start to listen to Chessqueen

[peter]

Where is Jeroen? His openings usually avoided this drawfest.

As far as I just read at TCEC-Rules, Premier Division is played

with a randomized 8-move opening book by Nelson Hernandez

Jeroen's openings will come at Superfinal.

[Nay Lin Tun]

It is already 6 games, 6 draws for SFNNUE!

[peter]

It is already 6 games, 6 draws for SFNNUE!

Yet only one less win than LC0, Stoofvlees (which has lost one game on the other hand too) and Ethereal have each. So no really clear superperformance over the 6 draws neither from any of the other engines.

[mwyoung]

https://tcec-chess.com/live.html

Where have we seen results like this before?

[peter]

https://tcec-chess.com/live.html

Where have we seen results like this before?

In this one Bonus
StockfishNNUE 20200704-StockFiNN-0.2 vs Top4
of latest season

https://tcec-chess.com/#div=nnueg&game=1&season=18

from 56 games hefty 4 ones were won.