Need to let loose a primal scream without collecting footnotes first? Have a sneer percolating in your system but not enough time/energy to make a whole post about it? Go forth and be mid: Welcome to the Stubsack, your first port of call for learning fresh Awful youāll near-instantly regret.
Any awful.systems sub may be subsneered in this subthread, techtakes or no.
If your sneer seems higher quality than you thought, feel free to cutānāpaste it into its own post ā thereās no quota for posting and the bar really isnāt that high.
The post Xitter web has spawned soo many āesotericā right wing freaks, but thereās no appropriate sneer-space for them. Iām talking redscare-ish, reality challenged āculture criticsā who write about everything but understand nothing. Iām talking about reply-guys who make the same 6 tweets about the same 3 subjects. Theyāre inescapable at this point, yet I donāt see them mocked (as much as they should be)
Like, there was one dude a while back who insisted that women couldnāt be surgeons because they didnāt believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I canāt escape them, I would love to sneer at them.
this is simple. we just need to train a new model for every move. that way the adversarial bot wonāt know what weaknesses to exploit
In chess the table base for optimal moves with only 7 pieces takes like ~20 terrabytes to store. And in that DB there are bizzare checkmates that take 100 + moves even with perfect precision- ignoring the 50 move rule. I wonder if the reason these adversarial strats exists is because whatever the policy network/value network learns is way, way smaller than the minimum size of the ātrueā position eval function for Go. Thus youāll just invariably get these counter play attacks as compression artifacts.
Sources cited: my ass cheeks
i donāt think that can be quite right, as illustrated by an extreme example: consider a game where the first move has player 1 choose āwinā or āhypergo.ā if player 1 chooses win, they win. if player 1 chooses hypergo, begin a game of Go on a 1,000,000,000 x 1,000,000,000 board, and whoever wins that subgame wins. for player 1, the ātrueā position eval function must be in some sense incredibly complicated, because it includes hypergo nonsense. but player 1 strategy can be compressed to āchoose winā without opening up any counterattacks
more generally I suspect that as soon as you are trying to compare some notion of a ātrueā position eval function to eval functions you can actually generate youāre going to have a very difficult time making correct and clear predictions. the reason I say this is that treating such a ātrueā function is essentially the domain of combinatorial game theory (not the same as āgame theoryā), and there are few if any bridges people have managed to build between cgt and practical Go etc playing engines. so itās probably pretty hard to do
(I know thereās a theory of ātemperatureā of combinatorial games that I think was developed for purposes of analyzing Go, but I donāt think it has any known relationship to reinforcement learning based Go engines)