That said, I don’t see why Vhazhar would want to touch the Sword of Good if all it does is “test good intentions”. Isn’t that just another way of saying that if the holder survives, he knows that his terminal values correspond to the Sword’s?
It makes sense that Hirou would want Vhazhar to touch the Sword, because since Hirou can touch it, if Vhazhar can touch it too Hirou will know that Vhazhar’s terminal values are similar to his own. But why does Vhazhar give a crap about the Sword’s terminal values?
If the stories of previous wielders of the Sword were public and reasonably accurate, he presumably already evaluated whether the Sword’s terminal values match the terminal values he wished to uphold.
Good answer. I guess it depends on what is meant by “good intentions”. If subconscious intentions are included, then it would be possible to hold false beliefs about one’s own intentions, and being able to touch the Sword would be evidence that these beliefs are mostly correct.
It wouldn’t be extremely strong evidence, though. All Vhazhar could know by studying historical records is that previous owners of the Sword acted in accordance with the values Vhazhar believes he has. However, these owners could have been deluded about their true terminal values their entire lives, and the Sword could therefore have been selecting for individuals with terminal values that don’t accord with their actions, which means it would be a waste of time for Vhazhar to touch it, at best, or a fatal mistake at worst.
And obviously, if “good intentions” means conscious intentions, then Vhazhar already knows he has the terminal values he believes he has.
As the sword killed 90% of those who touched it, Vhazhar could have, upon reading the records, discovered that the sword only allowed to survive those who help increase the CEV for sentient life (and thus slaughtering a ridiculous number of Cohen-esque “heroes”).
Good story. I love Yudkowskian fiction!
That said, I don’t see why Vhazhar would want to touch the Sword of Good if all it does is “test good intentions”. Isn’t that just another way of saying that if the holder survives, he knows that his terminal values correspond to the Sword’s?
It makes sense that Hirou would want Vhazhar to touch the Sword, because since Hirou can touch it, if Vhazhar can touch it too Hirou will know that Vhazhar’s terminal values are similar to his own. But why does Vhazhar give a crap about the Sword’s terminal values?
If the stories of previous wielders of the Sword were public and reasonably accurate, he presumably already evaluated whether the Sword’s terminal values match the terminal values he wished to uphold.
Good answer. I guess it depends on what is meant by “good intentions”. If subconscious intentions are included, then it would be possible to hold false beliefs about one’s own intentions, and being able to touch the Sword would be evidence that these beliefs are mostly correct.
It wouldn’t be extremely strong evidence, though. All Vhazhar could know by studying historical records is that previous owners of the Sword acted in accordance with the values Vhazhar believes he has. However, these owners could have been deluded about their true terminal values their entire lives, and the Sword could therefore have been selecting for individuals with terminal values that don’t accord with their actions, which means it would be a waste of time for Vhazhar to touch it, at best, or a fatal mistake at worst.
And obviously, if “good intentions” means conscious intentions, then Vhazhar already knows he has the terminal values he believes he has.
As the sword killed 90% of those who touched it, Vhazhar could have, upon reading the records, discovered that the sword only allowed to survive those who help increase the CEV for sentient life (and thus slaughtering a ridiculous number of Cohen-esque “heroes”).