Re: Building a friendly AI from a "just do what I tell you" AI

From: Panu Horsmalahti (nawitus@gmail.com)
Date: Thu Nov 22 2007 - 13:06:58 MST

Next message: Norman Noman: "Re: Morality simulator"
Previous message: Panu Horsmalahti: "Re: Building a friendly AI from a "just do what I tell you" AI"
In reply to: Panu Horsmalahti: "Re: Building a friendly AI from a "just do what I tell you" AI"
Next in thread: Wei Dai: "Re: Building a friendly AI from a "just do what I tell you" AI"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]

One more note: the whole simulation inside simulations is located in an
island booby trapped with nuclear bombs. If an extra electronic signal is
detected the whole thing blows up. Not safe enough. That *island* is a an
actual simulation run in another real island. Actually, that second island
is a simulation too. I would like to see an UFAI to escape that.

Next message: Norman Noman: "Re: Morality simulator"
Previous message: Panu Horsmalahti: "Re: Building a friendly AI from a "just do what I tell you" AI"
In reply to: Panu Horsmalahti: "Re: Building a friendly AI from a "just do what I tell you" AI"
Next in thread: Wei Dai: "Re: Building a friendly AI from a "just do what I tell you" AI"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:00 MDT