From: Hal Finney (hal@finney.org)
Date: Wed Apr 16 2003 - 15:56:28 MDT
Keith Elis writes:
> One of the refrains among AI Singularitarians is this notion of
> 'recursive self-enhancement' -- positive feedback, an AI hacking itself
> into something smarter, etc. Has anyone described what this process
> would look like at the software level? I don't mean as a theory of
> intelligence, or as an architecture of intelligence, but as a matter of
> engineering a recursive process in software.
In 1999 I wrote up a brief description of an article I found about a
recursively self-enhancing software program at
http://forum.javien.com/XMLmessage.php?id=id::XV8NWTIC-TXQT-TEsp-akAE-UwYbbkoDRg8v.
The project was not a success but it does say something about the
mechanics of what was involved.
Hal
This archive was generated by hypermail 2.1.5 : Wed Apr 16 2003 - 16:26:10 MDT