Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

PhilGoetz comments on Announcing the AI Alignment Prize - Less Wrong Discussion

7 Post author: cousin_it 03 November 2017 03:45PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (10)

You are viewing a single comment's thread.

Comment author: PhilGoetz 15 December 2017 07:41:12PM *  2 points [-]

I think that first you should elaborate on what you mean by "the goals of humanity". Do you mean majority opinion? In that case, one goal of humanity is to have a single world religious State, although there is disagreement on what that religion should be. Other goals of humanity include eliminating homosexuality and enforcing traditional patriarchal family structures.

Okay, I admit it--what I really think is that "goals of humanity" is a nonsensical phrase, especially when spoken by an American academic. It would be a little better to talk about values instead of goals, but not much better. The phrase still implies the unspoken belief that everyone would think like the person who speaks it, if only they were smarter.

Comment author: entirelyuseless 16 December 2017 03:04:22AM 1 point [-]

I considered submitting an entry basically saying this, but decided that it would be pointless since obviously it would not get any prize. Human beings do not have coherent goals even individually. Much less does humanity.

Comment author: cousin_it 19 December 2017 12:43:02PM *  0 points [-]

For example, not turning the universe into paperclips is a goal of humanity.

Comment author: entirelyuseless 19 December 2017 03:38:06PM 0 points [-]

Not really. I don't care if that happens in the long run, and many people wouldn't.

Comment author: cousin_it 19 December 2017 03:51:47PM *  0 points [-]

I hope at least you care if everyone on Earth dies painfully tomorrow. We don't have any theory that would stop AI from doing that, and any progress toward such a theory would be on topic for the contest.

Sorry, I'm feeling a bit frustrated. It's as if the decade of LW never happened, and people snap back out of rationality once they go off the dose of Eliezer's writing. And the mode they snap back to is so painfully boring.

Comment author: entirelyuseless 20 December 2017 03:43:01AM 0 points [-]

I do care about tomorrow, which is not the long run.

I don't think we should assume that AIs will have any goals at all, and I rather suspect they will not, in the same way that humans do not, only more so.

Comment author: Lumifer 19 December 2017 04:40:27PM 0 points [-]


That's not conventionally considered to be "in the long run".

We don't have any theory that would stop AI from doing that

The primary reason is that we don't have any theory about what a post-singularity AI might or might not do. Doing some pretty basic decision theory focused on the corner cases is not "progress".