Caveat: I’ve studied only the mainstream version of DT; there may be extensions that handle incommensurable goals in limited cases, I don’t know. I can’t see how one could handle the general case (but who knows, maybe I’m missing something and there’s an extension that does).
-
-
Replying to @Meaningness @ESYudkowsky
Cool! To clarify, you’re point is about the nature of the agent, not about math? The agent has no actual utility function, ya?
1 reply 0 retweets 0 likes -
Replying to @michaelporcelli @ESYudkowsky
The point is that the math doesn’t apply unless/until you identify actions, outcomes, and preferences. Those are abstract entities; they are not objective features of the world.
1 reply 0 retweets 1 like -
When you can more-or-less map the entities required by DT (or any mathematical framework) onto a situation, the math may give more-or-less meaningful results. Sometimes, for DT, this wins big!
1 reply 0 retweets 0 likes -
Sometimes you can’t meaningfully map DT onto a situation (because there aren’t identifiable preferences or actions or outcomes). Sometimes you can do that and it still doesn’t work, because math isn’t mostly-truth preserving, only absolute-truth preserving.
1 reply 0 retweets 0 likes -
So I think I still don’t understand what
@ESYudkowsky’s claim here is. Is the claim that you *can* always do a mapping? Or that you *should* always do a mapping? Or that *if* you can, then you should? Or that in somehow you should even when you can’t?1 reply 0 retweets 0 likes -
To complicate further, I guess “can” could be interpreted two ways here, as “can, as an actual human on the scene” vs “can, as an omniscient hypercomputational external God.”
1 reply 0 retweets 0 likes -
I don’t actually care what Gods can/can’t do. But, since actions, outcomes, and preferences are not objective features of reality, I don’t think they could always apply DT either.
1 reply 0 retweets 0 likes -
And, if the force of the claim is “should,” the question would be what sort of should that is.
1 reply 0 retweets 0 likes -
My suspicion is that this turns out to be circular. You start with the implicit assumption that there must be something to maximize. That is what gives “should” its force: you *should* apply DT, because if you don’t, you won’t maximize.
1 reply 0 retweets 0 likes
Maybe the “Law” formulation is just: “if you accept these premises, then these consequences hold.” But that’s just equivalent to “this is actual math,” which no one doubts.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.