I'd like to recommend Ben Goertzel's book from 2006 Hidden Pattern, and particularly Chapter 2 "Kinds of Minds". (The book is also available at the author's site, but that may trigger SSL certificate warnings.)

We've come to understand that a future AGI may have non-anthropomorphic  implementation and behavior, but this chapter situates possible minds in a variety of types of implementation and embodiment that I have not seen described elsewhere.

Specifically, p.17 compares

  • High-resource minds (like AIXI) or modest-resource

and among modest-resource minds

  • Embodied versus non, and within the "embodied" category: singly versus multiply versus flexibly embodied, and tool-dependent versus non
  • Mindplexes versus fully unified minds
  • Socially-dependent versus non

If there is other literature that enumerates and compares these and other kinds of minds, I'll be glad to know.

New Comment
4 comments, sorted by Click to highlight new comments since: Today at 10:50 PM

I also recommend Roman Yampolskiy's article "The Space of Possible Mind Designs".

Thank you.  Also Sloman's  The structure of the space of possible minds. All these are worthwhile articles, but I'd like to highlight Goertzel's discussion of kinds of embodiment.

What do people in the LessWrong community think of Ben Goertzels SingularityNET project?


The entire project description is full of "we will", "we aim to", "we are creating"... without visible evidence that the project has actually made a novel technical thing, I tend to assume that it's just a cash grab using a pile of buzzwords.

New to LessWrong?