Path: utzoo!utgpu!water!watmath!clyde!bellcore!tness7!tness1!nuchat!jackson!egranthm
From: egranthm@jackson.UUCP (Ewan Grantham)
Newsgroups: comp.ai
Subject: Re: Free Will & Self-Awareness
Message-ID: <174@jackson.UUCP>
Date: 18 May 88 14:44:54 GMT
References: <4134@super.upenn.edu> <3200014@uiucdcsm> <1484@pt.cs.cmu.edu> <31738@linus.UUCP>
Organization: Mississippi Dept. of Corrections
Lines: 37

In article <31738@linus.UUCP>, bwk@mbunix.UUCP writes:
> 
> I propose the following variation on Asimov:
> 
>       I.   A robot may not harm a human or other sentient being,
>            or by inaction permit one to come to harm.
> 
>      II.   A robot may respond to requests from human beings,
>            or other sentient beings, unless this conflicts with
>            the First Law.
> 
>     III.   A robot may act to protect its own existence, unless this
>            conflicts with the First Law."
> 
>      IV.   A robot may act to expand its powers of observation and
>            cognition, and may enlarge its knowledge base without limit.
> 
> Can anyone propose a further refinement to the above?
> 
> --Barry Kort

Well, this still seems to leave the question of how do you properly
define a sentient being so that the robot can have no doubt about
whether a being is sentient or not. Again the robot may feel that
he himself/herself is sentient, and therefore place self-preservation
above the first law by applying the first law to itself.

I also find that the human/sentient statement doesn't go far enough.
For example, should a robot be able to kill a dog just for barking
at it. Especially if the robot is quite well capable of being bitten
with no harm?

Ewan Grantham

(uunet!nuchat!jackson!egranthm)

My bosses aren't responsible for me, and vice-versa.