PhilGoetz comments on Exploitation and cooperation in ecology, government, business, and AI - Less Wrong

18 Post author: PhilGoetz 27 August 2010 02:27PM

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

Comments (43)

You are viewing a single comment's thread.

Comment author: Jonathan_Graehl 27 August 2010 08:18:44PM 1 point [-]

A decentralized agent-based AI, in the sense of agent-based software (often modelled on the free market, with software agents bidding on tasks), would be more amenable to mutualistic relationships.

I get the feeling you intend this to be taken as a pun for relationships between the AI and us, although of course you didn't explicitly suggest such a link.

Comment author: PhilGoetz 27 August 2010 09:09:30PM *  0 points [-]

No, that's not my intent at all. I'm speaking of relationships between the different components of the AI. The goal is to design an AI whose components will be more likely to have a good life.