Difference between revisions of "Machine ethics"

From Lesswrongwiki
Jump to: navigation, search
(Half a first draft)
 
Line 1: Line 1:
Machine Ethics is the emerging field which seeks to create technology with moral decision making capabilities. A [[superintelligence]] will take many actions with moral implications; programming it to act morally is the main goal of the field of [[friendly artificial intelligence]].  
+
'''Machine Ethics''' is the emerging field which seeks to create technology with moral decision making capabilities. A [[superintelligence]] will take many actions with moral implications. Programming it to act morally is the main goal of the field of [[friendly artificial intelligence]].  
 
   
 
   
 
A famous early attempt at machine ethics was that by Issac Asimov in a 1942 short story, a set of rules known as the Three Laws of Robotics. They formed the basis of many of his stories.  
 
A famous early attempt at machine ethics was that by Issac Asimov in a 1942 short story, a set of rules known as the Three Laws of Robotics. They formed the basis of many of his stories.  
 +
:0. A robot may not harm humanity, or, by inaction, allow humanity to come to harm.
 
# A robot may not injure a human being or, through inaction, allow a human being to come to harm.
 
# A robot may not injure a human being or, through inaction, allow a human being to come to harm.
 
# A robot must obey the orders given to it by human beings, except where such orders would conflict with the First Law.
 
# A robot must obey the orders given to it by human beings, except where such orders would conflict with the First Law.
 
# A robot must protect its own existence as long as such protection does not conflict with the First or Second Laws.
 
# A robot must protect its own existence as long as such protection does not conflict with the First or Second Laws.
Later, he added a zeroth rule, used in further expanding his series.  
+
The zeroth rule was a later extrapolated by his robots from the three programmed rules; it is more in line with present approaches to Machine Ethics.  
:0. A robot may not harm humanity, or, by inaction, allow humanity to come to harm.
+
 
These rules were implemented in fictional "positronic brains"; in reality today the field usually concerns itself in discussing the practical ethics and programming of such issues as robots in war, as home assistants, and lately in driverless cars.
+
Various moral philosophies have been explored as bases for machines. Several attempts have been made to program robots to obey utilitarian and deontological ethics. Programs which analyze a situation, compare it with others in a database, and return the an analysis have been created in several narrow ethical fields. An approach developed by [[Eliezer Yudkowsky]], [[Coherent Extrapolated Volition]], permits for the [[singularity]] to occur without a set of clear ethics driving it.  
 +
 
 +
Today, there are many practical applications of Machine Ethics. Drones used in war, though they risk no operator's life, make targeted killing easier. Robots developed to care for the elderly may reduce their human contact, reduce their privacy and make their feel frailer, but also permit them greater independence. The development of driverless cars will save lives but increase pollution as they are driven more.
 +
 
 +
Due to the explicitness required in programming machines to act ethically, as said by Danniel Dennet and frequently repeated, "AI makes philosophy honest".  
  
 
=== References ===
 
=== References ===
 +
* [http://commonsenseatheism.com/wp-content/uploads/2011/11/Muehlhauser-Helm-The-Singularity-and-Machine-Ethics-draft.pdf The Singularity and Machine Ethics] by Luke Muehlhauser and Louie Helm
 
* [http://intelligence.org/upload/machine-ethics-superintelligence.pdf Machine Ethics and Superintelligence] by Carl Shulman, Henrik Jonsson, and Nick Tarleton
 
* [http://intelligence.org/upload/machine-ethics-superintelligence.pdf Machine Ethics and Superintelligence] by Carl Shulman, Henrik Jonsson, and Nick Tarleton
 
* Moral Machines: Teaching Robots Right from Wrong, by Wendell Wallach and Colin Allen
 
* Moral Machines: Teaching Robots Right from Wrong, by Wendell Wallach and Colin Allen
 +
* [http://commonsenseatheism.com/wp-content/uploads/2011/02/McLaren-Lessons-in-machine-ethics-from-the-perspective-of-two-computational-models-of-ethical-reasoning.pdf Lessons in Machine Ethics from the Perspective of Two Computational Models of Ethical Reasoning] by Bruce M. McLaren
 +
* [http://commonsenseatheism.com/wp-content/uploads/2011/02/Powers-Prospects-for-a-Kantian-Machine.pdf Prospects for a Kantian Machine] by Thomas M. Powers
 +
 +
==== Applications Today ====
 +
* [http://www.peterasaro.org/writing/asaro%20just%20robot%20war.pdf How Just Could a Robot War Be?] by Peter M. Asaro
 +
* [http://staffwww.dcs.shef.ac.uk/people/A.Sharkey/sharkey-granny.pdf Granny and the robots: Ethical issues in robot care for the elderly] by Amanda Sharkey and Noel Sharkey

Revision as of 06:01, 11 July 2012

Machine Ethics is the emerging field which seeks to create technology with moral decision making capabilities. A superintelligence will take many actions with moral implications. Programming it to act morally is the main goal of the field of friendly artificial intelligence.

A famous early attempt at machine ethics was that by Issac Asimov in a 1942 short story, a set of rules known as the Three Laws of Robotics. They formed the basis of many of his stories.

0. A robot may not harm humanity, or, by inaction, allow humanity to come to harm.
  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 the 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 Laws.

The zeroth rule was a later extrapolated by his robots from the three programmed rules; it is more in line with present approaches to Machine Ethics.

Various moral philosophies have been explored as bases for machines. Several attempts have been made to program robots to obey utilitarian and deontological ethics. Programs which analyze a situation, compare it with others in a database, and return the an analysis have been created in several narrow ethical fields. An approach developed by Eliezer Yudkowsky, Coherent Extrapolated Volition, permits for the singularity to occur without a set of clear ethics driving it.

Today, there are many practical applications of Machine Ethics. Drones used in war, though they risk no operator's life, make targeted killing easier. Robots developed to care for the elderly may reduce their human contact, reduce their privacy and make their feel frailer, but also permit them greater independence. The development of driverless cars will save lives but increase pollution as they are driven more.

Due to the explicitness required in programming machines to act ethically, as said by Danniel Dennet and frequently repeated, "AI makes philosophy honest".

References

Applications Today