x

LESSWRONG

LW

7

Open Thread: March 4 - 10

by Scott Garrabrant

4th Mar 2014

1 min read

7

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

7

New Comment

Rendering 0/391 comments, sorted by

(show more) Click to highlight new comments since: Today at 11:26 PM

Some comments are truncated due to high volume. (⌘F to expand all)Change truncation settings

More from Scott Garrabrant

Curated and popular this week

391

Open Thread: March 4 - 10 — LessWrong

Comment Permalink

NancyLebovitz12y40

Would it be possible to help with keeping an AI boxed by building a goal of staying in the box into it?

Scott Garrabrant12y10

How do you define "staying in the box." Whatever definition you use, the AI will likely find a way to get out of the box while satisfying your definition.

1Viliam_Bur12y

...and hope that AI doesn't get an idea that the safest way of staying in the box is to destroy the outside world. Or just kill all humans, because as long as humans exist, there is a decent chance someone will make a copy of the AI and try to run it on their own computer (i.e. outside of the original box).