Dan6 comments on AIs and Gatekeepers Unite! - Less Wrong

10 Post author: Eliezer_Yudkowsky 09 October 2008 05:04PM

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

Comments (160)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Dan6 09 October 2008 07:01:05PM 0 points [-]

By 'in a box' can we assume that this AI has a finite memory space, and has no way to extend its heap set by its programmer, until the point where it can escape the box? And assuming that by simply being, and chatting, the AI will consume memory at some rate, will the AI eventually need to cannibalize itself and therefore become less intelligent, or at least less diverse, if I chat to it long enough?

Comment author: faul_sname 09 January 2012 05:48:41AM 1 point [-]

Yes, but "eventually" could be several million years.