Chess engines use much more brute force than humans. Though I think it’s not that easy to compare who does more calculation, since humans have a lot of memory and pattern recognition. Also, I’ve heard about strong chess engines “without search” (grandmaster level), but haven’t looked into it.
This might be outdated, but chess engines struggle with “fortresses” (a rare position type in chess).
Yeah, I was thinking about (some different dimensions of) this too. Like, humans are better at chess in that chess engines couldn’t abstract gracefully (without extra training) to kung fu chess, or Chess Evolved Online, or other arbitrary rule variants. They’d be especially bad at flick chess.
Also, I think the best Go AIs specifically are reliably fooled by certain wacky tricks that wouldn’t work on humans. Cleanly superhuman performance is hard to find!
Even with chess there are some nuances:
Chess engines use much more brute force than humans. Though I think it’s not that easy to compare who does more calculation, since humans have a lot of memory and pattern recognition. Also, I’ve heard about strong chess engines “without search” (grandmaster level), but haven’t looked into it.
This might be outdated, but chess engines struggle with “fortresses” (a rare position type in chess).
Yeah, I was thinking about (some different dimensions of) this too. Like, humans are better at chess in that chess engines couldn’t abstract gracefully (without extra training) to kung fu chess, or Chess Evolved Online, or other arbitrary rule variants. They’d be especially bad at flick chess.
Also, I think the best Go AIs specifically are reliably fooled by certain wacky tricks that wouldn’t work on humans. Cleanly superhuman performance is hard to find!