Download - Ethics for self-improving machines
![Page 1: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/1.jpg)
Ethics for self-improving machines
J Storrs HallMark Waser
![Page 2: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/2.jpg)
Asimov's3 Laws:
http://www.markzug.com/
1. A robot may not injure a human
being or, through inaction, allow a
human being to come to harm.
2. A robot must obey orders given
to it by human beings except where
such orders would conflict with the
First Law.
3. A robot must protect its own
existence as long as such protection
does not conflict with the First or
Second Law.
![Page 3: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/3.jpg)
Asimov's robots didn't
Improve Themselves.
But our AIs (we hope)
Will.
![Page 4: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/4.jpg)
How do you design laws for something that will think in concepts you haven't heard of
and which you couldn't grasp if you had?
![Page 5: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/5.jpg)
There is no chance that everybody will create their robots with any given set of laws anyhow!
Laws reflect goals (and thus values) which do NOT converge over humanity.
![Page 6: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/6.jpg)
Axelrod's Evolution of Cooperation and decades of follow-on evolutionary game theory provide the theoretical underpinnings.
Be nice/don’t defect Retaliate Forgive
“Selfish individuals, for theirown selfish good, should benice and forgiving”
![Page 7: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/7.jpg)
In nature, cooperation appears whenever
the cognitive machinery will support it.
Vampire bats(Wilkinson)
Blue Jays (Stephen
s, McLinn, &
Stevens)
Cotton-Top Tamarins (Hauser, et
al)
![Page 8: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/8.jpg)
Economic Sentience
Defined as:“Awareness of the potential benefits of cooperation and trade with other intelligences”
TIME DISCOUNTING is its measure.
![Page 9: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/9.jpg)
Tragedy of the Commons
![Page 10: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/10.jpg)
Acting ethically is an attractor in the state space of intelligent goal-driven systems (if they interact with other intelligent goal-driven systems on a long-term ongoing basis)
Ethics *IS* the necessary basis for cooperation
![Page 11: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/11.jpg)
We must find ethical design elements that are Evolutionarily Stable Strategies
so that we can start AIs out
in the attractor it's taken us millions of years to begin to descend.
![Page 12: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/12.jpg)
Let's call such adesign element an
ESV:
Evolutionarily Stable(or EconomicallySentient)Virtue.
![Page 13: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/13.jpg)
Economically Unviable
Destruction
Slavery
Short-term profit at the expense of the long term
Avoiding all of these are ESVs
![Page 14: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/14.jpg)
Fair enforcement of contractsis an ESV that demonstrablypromotes cooperation.
![Page 15: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/15.jpg)
Open Sourcemotivationsare an ESV
Like auditingin current-daycorporations,since money is their trueemotion.
and other forms of guaranteeing trustworthiness
![Page 16: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/16.jpg)
In particular,RECIPROCAL ALTRUISM is an ESV;Exactly like it's superset ENLIGHTENED SELF-INTEREST (AKA
ETHICS)
![Page 17: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/17.jpg)
A general desire for all ethical agents to live (and prosper) as long as possible is also an ESV, because it promotes a community with long-term stability and accountability.
![Page 18: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/18.jpg)
— Socrates
There is no good but knowledge,and no evil but ignorance.
Curiosity – a will to extend and improveone's world model – is an ESV.
![Page 19: Ethics for self-improving machines](https://reader036.vdocument.in/reader036/viewer/2022081520/56814d90550346895dbae99c/html5/thumbnails/19.jpg)
An AI with ESVs whoknows what that meanshas a guideline fordesigning Version 2.0, even when the particulars of the new environment don't match the concepts of the old literal goal structure.