I can believe that it’s possible to defeat a Go professional by some extremely weird strategy that causes them to have a seizure or something in that spirit. But, is there a way to do this that another human can learn to use fairly easily? This stretches credulity somewhat.
Or there’s just different paths to get AGI that involve different weaknesses and blind spots? Human children also seem exploitable in lots of ways. Couldn’t you argue similarly that Humans are not generally intelligent, because Alpha-beta pruning + some mediocre evaluation function beats them in chess consistently, and they are not even able to learn to beat it?
Human children also seem exploitable in lots of ways.
Also, more generally, there are many ways to manipulate humans into acting against their self-interest, which they may fail to adapt to even after suffering from it multiple times (people stuck in abusive relationships may be the most extreme example). You could probably call that an adversarial strategy that other humans routinely exploit.
Or there’s just different paths to get AGI that involve different weaknesses and blind spots? Human children also seem exploitable in lots of ways. Couldn’t you argue similarly that Humans are not generally intelligent, because Alpha-beta pruning + some mediocre evaluation function beats them in chess consistently, and they are not even able to learn to beat it?
Also, more generally, there are many ways to manipulate humans into acting against their self-interest, which they may fail to adapt to even after suffering from it multiple times (people stuck in abusive relationships may be the most extreme example). You could probably call that an adversarial strategy that other humans routinely exploit.