Suppose there are two different super-human chess AI's with different styles -- call them UberTal[1]
and UberPetrosian[2]
-- such that a human chess (and AI) expert who watched a match between the two could reliably guess who was who, without being told which AI was playing white and which was playing black (and of course without being able to beat either one).
Would such a situation contradict the claim you are making here?
Or would you argue that we might see such a situation with only weakly-superhuman AI's, but that the further the AI's advanced beyond human abilities, the less we'd be able to detect a characteristic style?
Widely regarded as a creative genius and the best attacking player of all time, Tal played in a daring, combinatorial style.https://en.wikipedia.org/wiki/Mikhail_Tal
I'm not quite sure of this.
Suppose there are two different super-human chess AI's with different styles -- call them UberTal[1] and UberPetrosian[2] -- such that a human chess (and AI) expert who watched a match between the two could reliably guess who was who, without being told which AI was playing white and which was playing black (and of course without being able to beat either one).
Would such a situation contradict the claim you are making here?
Or would you argue that we might see such a situation with only weakly-superhuman AI's, but that the further the AI's advanced beyond human abilities, the less we'd be able to detect a characteristic style?
Widely regarded as a creative genius and the best attacking player of all time, Tal played in a daring, combinatorial style. https://en.wikipedia.org/wiki/Mikhail_Tal
He was nicknamed "Iron Tigran" due to his almost impenetrable defensive playing style, which emphasised safety above all else. https://en.wikipedia.org/wiki/Tigran_Petrosian