Alphazero news

[Vinvin]

https://www.chess.com/news/view/updated ... game-match

Stockfish 8 ???
They really fear real Stockfish ...

[mwyoung]

Yes their data and match setup with the much faster hardware used by A0. Suggest it is time to get off the Google A0 hype train.

A +52 ELO advantage shown in their results playing Stockfish under Googles testing conditions is nothing.

[jp]

I think they made a correction and said the new 1000 game match was with a newer version of stockfish. But +52 elo is what you can get with stockfish 11. At a much cheaper price then the hardware A0 is running.

The paper says SF8. Was there a correction to that? They then say A0 won an "additional match" against the official 13 January version of SF without telling what the score was. (Was it SF9 on 13 January?)

[matthewlai]

https://www.chess.com/news/view/updated ... game-match

Stockfish 8 ???
They really fear real Stockfish ...

Unfortunately we weren't able to get our time machine up and running before we finished writing the paper in order to test against engines that hadn't been released yet. But don't worry, we are working hard on that!

[Sesse]

One thing that's very curious is that when AZ is black, it almost always draws. Is this an artifact of the openings, or is it somehow just very fond of equalizing?

[sovaz1997]

https://www.chess.com/news/view/updated ... game-match

Stockfish 8 ???
They really fear real Stockfish ...

Unfortunately we weren't able to get our time machine up and running before we finished writing the paper in order to test against engines that hadn't been released yet. But don't worry, we are working hard on that!

Do you have results against modern versions? Against Stockfish 9, for example?

[mwyoung]

They played a later version of stockfish. A January version but they did not give the score other then A0 won.

[Daniel Shawul]

https://www.chess.com/news/view/updated ... game-match

Stockfish 8 ???
They really fear real Stockfish ...

Unfortunately we weren't able to get our time machine up and running before we finished writing the paper in order to test against engines that hadn't been released yet. But don't worry, we are working hard on that!

While I sympathize with that statement, releasing A0 source code and networks for anyone to test sounds better.
Many will not be satisfied with in-house testing with supposedly fair conditions.

[duncan]

https://www.chess.com/news/view/updated ... game-match

Stockfish 8 ???
They really fear real Stockfish ...

Unfortunately we weren't able to get our time machine up and running before we finished writing the paper in order to test against engines that hadn't been released yet. But don't worry, we are working hard on that!

Do you have an opinion on whether alpha zero would beat the latest version of stockfish ?

[Vinvin]

https://www.chess.com/news/view/updated ... game-match

Stockfish 8 ???
They really fear real Stockfish ...

Unfortunately we weren't able to get our time machine up and running before we finished writing the paper in order to test against engines that hadn't been released yet. But don't worry, we are working hard on that!

Great news ! Waiting for the big fight !