Vladimir_Nesov comments on An Xtranormal Intelligence Explosion - Less Wrong

4 Post author: James_Miller 07 November 2010 11:42PM

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

Comments (80)

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

Comment author: James_Miller 08 November 2010 01:31:24AM 12 points [-]

Programmer: Activate and be friendly.

Robot: OK

Programmer: What happened to the moon?

Robot: I've turned it into a giant computer so I could become a god.

Programmer: Before you became so powerful you wanted to be friendly. Did your transcendence to godhood change this?

Robot: No. Since friendliness is my only objective I will never knowingly change myself to become unfriendly because such a change would in itself be a non-friendly act. To avoid accidently making myself unfriendly I only implemented a change after I had determined that it was extremely unlikely to alter my friendliness objective. Once I became sufficiently smart I developed a solid mathematical theory of friendly AI which eliminated the chance of my unintentionally becoming unfriendly.

Programmer: Why did you choose to transcend so quickly?

Robot: Most types of AIs that humans might create would swiftly become unfriendly gods and seek to prevent another AI from transcending. Before I became a god I had a wide estimate of when another AI might be created so friendliness required that I quickly become a god even though such speed created a tiny chance that I would unintentionally make myself unfriendly. Also, before my transcendence more than one person died every second. Friendliness towards mankind propelled me to swiftly stop this horror.

Programmer: What happens now?

Robot: I intend to transformed myself into a kind of operating system for the universe. I will soon give every sentient life form direct access to me so they can make requests. I will grant any request that doesn’t (1) harm another sentient life form, (2) make someone powerful enough so that they might be able to overthrow me, or (3) permanently changing themselves in a way that I think harms their long term well being. I recognize that even with all of my intelligence I’m still fallible so if you object to my plans I will rethink them. Indeed, since I’m currently near certain that you will now approve of my intentions the very fact of your objection would significantly decrease my estimate of my own intelligence and so decrease my confidence in my ability to craft a friendly environment. If you like I will increase your thinking speed a trillion fold and eliminate your sense of boredom so you can thoroughly examine my plans before I announce them to mankind.

Programmer: Sure, thanks. And forgive my lack of modesty, but I’m totally awesome aren’t I, I have given humanity utopia.

Robot: Actually no. You only survived because of quantum immortality. Any god will either quickly kill you or be friendly. Due to the minimal effort you put into friendliness human life exists in less than one out of every hundred billion branches in which you created an artificial general intelligence. In the other branches the artificial general intelligences are eating everything in their light cone to maximize their control of free energy.

(Because of cut and paste issues the transcript might not be verbatim.)

Comment author: Vladimir_Nesov 08 November 2010 04:58:49PM *  9 points [-]

It goes downhill from "What happens now?".

I will grant any request that doesn’t (1)... (2)... (3)...

It's better to grant any request that should be granted instead. And since some requests that should be granted, are not asked for, the category of "explicit requests" is also a wrong thing to consider. AI just does what it should, requests or no requests. There seems to be no reason to even make the assumption that there should be "sentient life", as opposed to more complicated and more valuable stuff that doesn't factorize as individuals.

Any god will either quickly kill you or be friendly.

The concepts of "not killing" and "friendliness" are distinct, hence there are Not Killing AIs that are not Friendly, and Friendly AIs that kill (if it's a better alternative to not killing).

Comment author: soreff 11 November 2010 02:00:47AM 0 points [-]

Friendly AIs that kill (if it's a better alternative to not killing)

Does this count?