Decius comments on The Need for Human Friendliness - Less Wrong

6 Post author: Elithrion 07 March 2013 04:31AM

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

Article Navigation

Sort By: Best

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

Comment author: Decius 07 March 2013 08:09:44AM 1 point [-]

How much would you be willing to wager that you will be able to follow the proof of friendly for the specific AI which gets implemented?

Comment author: drethelin 07 March 2013 08:15:22AM 0 points [-]

Very little. I don't like my odds. If Eliezer has provable friendliness theorems but not an AI, it's in his and everyone's interest to distribute the generalized theorem to everyone possible so that anyone working on recursive AGI has a chance to make it friendly, which means the algorithms will be checked by many, publicly. If Eliezer has the theorems and an AI ready to implement, there's nothing I can do about it at all. So why worry?

Comment author: Decius comment score below threshold [+] (8 children)

Comment author: wedrifid 07 March 2013 02:05:19PM 1 point [-]

You could Trust Eliezer and everyone who checked his theorems and then put money towards the supercomputer cluster which is testing every string of bits for 'friendly AI'.

In fact, at that point that project should become humanity's only notable priority.

Probably not. That project does not sound efficient (to the extent that it sounds unfeasible).

Comment author: Decius 07 March 2013 05:33:57PM -1 points [-]

Does the expected return on "this has a one in 2^(10^10) chance of generating a proven friendly AI" lose to anything else in terms of expected result? If so, we should be doing that to the exclusion of FAI research already.

Comment author: wedrifid 07 March 2013 06:04:03PM * 2 points [-]

Does the expected return on "this has a one in 2^(10^10) chance of generating a proven friendly AI" lose to anything else in terms of expected result?

Yes. It loses to any sane strategy of finding an FAI that is not "testing every string of bits".

Testing every string of bits is a nice 'proof of concept' translation of "can prove a string of bits is an FAI if it in fact is an FAI" to "actually have an FAI". It just isn't one that works in practice unless, say, you have a halting oracle in your pocket.

Comment author: Decius 07 March 2013 11:27:46PM 0 points [-]

If I had a halting oracle, I would have AGI.

By your logic, testing an actual AI against the proofs of friendliness isn't worth the expense, because there might be an inconclusive result.

Comment author: wedrifid 08 March 2013 02:23:33AM 0 points [-]

If I had a halting oracle, I would have AGI.

No you wouldn't.

By your logic, testing an actual AI against the proofs of friendliness isn't worth the expense, because there might be an inconclusive result.

No, my logic doesn't claim that either.

Comment author: Decius 08 March 2013 04:55:20AM 0 points [-]

I write a program which recognizes AGI and halts when it finds one. It tests all programs less than 1 GB. If it halts, I narrow the search space. If it doesn't, I expand the search space. Each search takes the time used by the halting oracle.

We already have a way to prove that a string of bits is FAI; it is trivial to generalize that to AI.

"I have a string of bits. I do not know if it is FAI or not, but I have a way of testing that is perfectly specific and very sensitive. The odds of an AI researcher writing a FAI are vanishingly small. Should I test it if it was written by an AI researcher? Should I test it if it isn't?

Comment author: wedrifid 08 March 2013 08:59:48AM 0 points [-]

We already have a way to prove that a string of bits is FAI; it is trivial to generalize that to AI.

Yes, if you have that proof and a halting oracle then you have AGI. That is vastly different to the claim "If I had a halting oracle I would have an AGI".

continue this thread »

Decius comments on The Need for Human Friendliness - Less Wrong

Article Navigation

Comments (28)

Nearest Meetups

Virtual Study Room

Recent Comments

Recent Posts

Recent Rationality Quotes

Recent Wiki Edits

Top Contributors, 30 Days

Recent Karma Awards

Comments (28)

Top Contributors, 30 Days

You'll need to login or register to do that

(Don't worry, it only takes a few seconds)

Create

Login