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

ciphergoth comments on GAZP vs. GLUT - Less Wrong

33 Post author: Eliezer_Yudkowsky 07 April 2008 01:51AM

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

Comments (166)

Sort By: Old

You are viewing a single comment's thread. Show more comments above.

Comment author: ciphergoth 16 March 2010 12:50:12PM 2 points [-]

I'm afraid this is just a misleading intuition pump. Eliezer has GLUT-reading powers, does he? Well, the GLUT has a body that it uses to type its responses in the Turing Test, and that body is capable of scanning the complete state of Eliezer's brain, from which the GLUT's enormous tables predict what he's going to say next.

Comment author: BenAlbahari 16 March 2010 12:55:40PM *  0 points [-]

When does the GLUT's scan occur? Before or after it has to start the Turing Test? If it does it beforehand, then it suffers predictability. But it can't do it afterwards, without ceasing to fit the definition of a lookup table.

Comment author: ciphergoth 16 March 2010 04:07:25PM *  3 points [-]

The point I'm making is that the difference you're drawing between people and GLUTs isn't really to do with their essential nature: it's a more trivial asymmetry on things like how readable their state is and whether they have access to a private source of randomness. Fix these asymmetries and your problem case goes away.

Comment author: BenAlbahari 16 March 2010 05:27:46PM *  0 points [-]

A lookup table is stateless. The human is stateful. RAM beats ROM. This is not a trivial asymmetry but a fundamental asymmetry that enables the human to beat the GLUT. The algorithms:

Stateless GLUT:
Question 1 -> Answer 1
Question 2 -> Answer 2
Question 3 -> Answer 3
...

Stateful Human:
Any Question -> Any Answer other than what the GLUT said I'd say

The human's algorithm is bulletproof against answering predictably. The GLUT's algorithm can only answer predictably.

P.S. I wasn't entirely sure what you meant by "private source of randomness". I also apologize if I'm slow to grasp any of your points.

Comment author: FAWS 16 March 2010 05:42:41PM *  2 points [-]

GLUT:

Task + Question + state of the human -> "Any Answer other than what the GLUT said I'd say"

If the human has looked up that particular output as well then that's another input for the GLUT, and since the table includes all possible inputs this possibility is included as well, to infinite recursion.

Comment author: BenAlbahari 16 March 2010 05:51:35PM *  0 points [-]

The problem for the GLUT is that the "state of the human" is a function of the GLUT itself (the window causes the recursion).

Comment author: FAWS 16 March 2010 05:56:05PM 1 point [-]

And the human has exactly the same problem.

Comment author: BenAlbahari 16 March 2010 06:24:07PM *  1 point [-]

You're right; got it. That's also what ciphergoth was trying to tell me when he said that the asymmetries could be melted away.

Comment author: ciphergoth 16 March 2010 11:30:20PM 1 point [-]

Thanks for update! By "private source of randomness" I mean one that's not available to the person on the other side of the window. Another way to look at it would be the sort of randomness you use to generate cryptographic keys - your adversary mustn't have access to the randomness you draw from it.

Comment author: BenAlbahari 16 March 2010 06:30:44PM 0 points [-]

Thanks ciphergoth; I updated the original comment to allude to the error you spotted.