Re: Is this safe/prudent ? (was Re: Perl AI Weblog)

From: Eliezer S. Yudkowsky (sentience@pobox.com)
Date: Mon Aug 11 2003 - 22:04:43 MDT

  • Next message: Brett Paatsch: "Re: Is this safe/prudent ? (was Re: Perl AI Weblog)"

    Brett Paatsch wrote:
    >
    > If I was a socially dysfunctional programming wiz with a burning
    > desire to make my own avenging bot to settle some scores
    > would not this sort of open source open sharing empower me
    > in dangerous ways.

    Arthur Murray is a harmless crank, far as I know.

    > Any thoughts on this sort of approach from a public
    > policy stance Eliezer? Anyone?

    Don't open-source an AI that can potentially be corrupted and that can
    accomplish more damage than uncorrupted AIs can correct. If you're in a
    state where a corrupted version of your AI can do serious global damage,
    then don't open-source that AI. 

    -- 
Eliezer S. Yudkowsky                          http://singinst.org/
Research Fellow, Singularity Institute for Artificial Intelligence

    This archive was generated by hypermail 2.1.5 : Mon Aug 11 2003 - 22:14:03 MDT