Path: utzoo!attcan!uunet!husc6!bloom-beacon!gatech!purdue!decwrl!hplabs!hpda!hpcupt1!hpisod2!decot
From: decot@hpisod2.HP.COM (Dave Decot)
Newsgroups: comp.ai
Subject: Re: Free Will & Self-Awareness
Message-ID: <15960001@hpisod2.HP.COM>
Date: 13 May 88 19:30:19 GMT
References: <1484@pt.cs.cmu.edu>
Organization: Hewlett Packard, Cupertino
Lines: 29

> 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?

I like this much better, but "harm" needs some definition or qualification.

It might be inferred (by a robot?) that a robot must stop sentient beings
from smoking, jumping out of airplanes, driving a car, etc.

I don't see why II and II have protections against violating I and IV doesn't.
Does this imply it's OK to zap somebody standing in front of your sensors?
If all the laws must be satisfied at all times, the qualifications in II
and III are redundant.

Dave Decot
hpda!decot