Difference between revisions of "Machine ethics"

From Lesswrongwiki
Jump to: navigation, search
(Focus more on present machine ethics)
m (Further Reading & References)
 
(7 intermediate revisions by 2 users not shown)
Line 1: Line 1:
 
{{wikilink}}
 
{{wikilink}}
'''Machine Ethics''' is the emerging field which seeks to create machines which consider the moral implications of their actions and seeks to act morally. A machine which does so is called an '''Artificial Moral Agent''' or '''AMA'''. Machine ethics is a subject whose application is currently limited to simple machines programmed with narrow AI. Various moral philosophies have been programmed, using many techniques and all with limited success.  
+
'''Machine Ethics''' is the emerging field that tries to understand how machines which consider the moral implications of their actions and act accordingly can be created. That is, how humanity can ensure that the minds created through AI can reason morally about other minds - thus creating Artificial Moral Agents (AMAs).
  
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 made them feel devalued, but could also permit them greater independence. The development of driverless cars will save lives but raise conflict between gas efficiency and environmentalism, and may force a solution to be programmed for the [[Wikipedia:Trolley Problem|trolley problem]]. Programming AMAs is not currently used in industry, and present computer errors could be eliminated with only better programming. However, the moral decisions used in making these programs are hardly unbiased.
+
Historically, the earliest famous  attempt at machine ethics was that by Issac Asimov in a 1942 short story, a set of rules known as the [[Wikipedia:Three Laws of Robotics|Three Laws of Robotics]]. The basis of many of his stories, they demonstrated how the law's seeming impermeability could so often fail - even without the errors inevitable from machine comprehension.  
  
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. Due to the explicitness required in programming machines to act ethically, as said by [[Wikipedia:Daniel Dennett|Daniel Dennett]], "AI makes philosophy honest".  
+
Currently, machine ethics is a subject whose application is limited to simple machines programmed with narrow AI - various moral philosophies have been programmed, using many techniques and all with limited success. Despite that, it has been argued that as we approach the development of a [[superintelligence]], humanity should focus on the task of developing machine ethics for an [[artificial general intelligence]] before that moment arrives.  
  
A famous early attempt at machine ethics was that by Issac Asimov in a 1942 short story, a set of rules known as the [[Wikipedia:Three Laws of Robotics|Three Laws of Robotics]]. The basis of many of his stories, they demonstrated how the law's seeming impermeability could so often fail - even without the errors inevitable from machine comprehension. The zeroth rule was a later addition extrapolated by his robots from the three programmed rules. The laws are:
+
As Wallach and Allen pose it, “even if full moral agency for machines is a long way off, it is already necessary to start building a kind of functional morality, in which artificial moral agents have some basic ethical sensitivity”.  
: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 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.
 
  
The fields of machine ethics and [[friendly artificial intelligence]] are presently disjoint, but informal efforts have been made to bridge this gap. A particular challenge is that a portion of the machine ethics community believes in [[Wikipedia:Moral universalism| moral universalism]]. As the development of a [[superintelligence]] approaches, it is expected that more of the machine ethics community will focus on the task of developing machine ethics for an [[artificial general intelligence]].
+
== Further Reading & References ==
 
+
* [http://intelligence.org/files/IE-ME.pdf Intelligence Explosion and Machine Ethics] by Luke Muehlhauser and Louie Helm
== References ==
+
* [http://intelligence.org/files/MachineEthicsSuperintelligence.pdf Machine Ethics and Superintelligence] by Carl Shulman, Henrik Jonsson, and Nick Tarleton
* [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
+
* Moral Machines: Teaching Robots Right from Wrong by Wendell Wallach and Colin Allen
* [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
 
 
* [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/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
 
* [http://commonsenseatheism.com/wp-content/uploads/2011/02/Powers-Prospects-for-a-Kantian-Machine.pdf Prospects for a Kantian Machine] by Thomas M. Powers
 +
* [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 Sharkeyture
  
== Applications Today ==
+
==See also==
* [http://www.peterasaro.org/writing/asaro%20just%20robot%20war.pdf How Just Could a Robot War Be?] by Peter M. Asaro
+
*[[Utility]]
* [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
+
*[[Utilitarianism]]

Latest revision as of 08:32, 23 May 2013

Smallwikipedialogo.png
Wikipedia has an article about

Machine Ethics is the emerging field that tries to understand how machines which consider the moral implications of their actions and act accordingly can be created. That is, how humanity can ensure that the minds created through AI can reason morally about other minds - thus creating Artificial Moral Agents (AMAs).

Historically, the earliest famous 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. The basis of many of his stories, they demonstrated how the law's seeming impermeability could so often fail - even without the errors inevitable from machine comprehension.

Currently, machine ethics is a subject whose application is limited to simple machines programmed with narrow AI - various moral philosophies have been programmed, using many techniques and all with limited success. Despite that, it has been argued that as we approach the development of a superintelligence, humanity should focus on the task of developing machine ethics for an artificial general intelligence before that moment arrives.

As Wallach and Allen pose it, “even if full moral agency for machines is a long way off, it is already necessary to start building a kind of functional morality, in which artificial moral agents have some basic ethical sensitivity”.

Further Reading & References

See also