News for hackers. Stuff that matters.

A comment on AI winter is well on its way. Parent comment

Re:AI winter is well on its way by pleasecalllater on Wednesday May 30, 2018 @02:12AM (#17185473)
> The chess version beat a leading conventional chess program 28 wins, 0 losses, and 72 draws.

In a not equal fight, and the results are still not published. I'm not claiming that AlphaZero wouldn't win, but that test was pure garbage.

[ Parent | on HN ]
Re:AI winter is well on its way by tim333 on Wednesday May 30, 2018 @05:50AM (#17186373)
The results were published - https://arxiv.org/abs/1712.01815

I agree AlphaZero had fancier hardware and so it wasn't really a fair fight.

[ Parent | on HN ]
Re:AI winter is well on its way by red75prime on Wednesday May 30, 2018 @06:16AM (#17186467)
Stockfish is not designed to scale to supercomputing clusters or TPUs, Alpha Zero wasn't designed to account for how long it takes to make a move, fair fight was hard to arrange.
[ Parent | on HN ]
Re:AI winter is well on its way by pleasecalllater on Thursday May 31, 2018 @04:25AM (#17194834)
No, these are not full results. There are just 10 example games published. Where is the rest?
[ Parent | on HN ]
Re:AI winter is well on its way by salvar on Wednesday May 30, 2018 @06:01AM (#17186414)
How was it not equal?
[ Parent | on HN ]
Re:AI winter is well on its way by tim333 on Wednesday May 30, 2018 @06:36AM (#17186528)
There's discussion here https://chess.stackexchange.com/questions/19366/hardware-use... AlphaZero's hardware was faster and Stockfish had a year old version with non optimum settings. It was still an impressive win but it would be interesting to do it again with a more level playing field.
[ Parent | on HN ]