in Search
0 members online
Immortality

Michael Anissimov

Friendly AI 101

Cross-posted from Accelerating Future

An 'ethical robotics' bit has started hitting the AI news sites today, this time from tech philosopher Bernhard Irrgang at the Dresden University of Technology.  As always, I ask, "does this person have a clue?"  And from reading his paper, "Ethical Acts in Robotics", the answer is, unfortunately, a firm no.

From the opening:

To consider the question, can Computers/Robots act morally, one must first distinguish between the participant perspective (subjective experience: first person perspective) and the observer perspective (objective experience: third person perspective) in phenomenogical and hermeneutic terms.  From the observer (i.e., third person) perspective, Ricoeur's approach of modeling acts (actions) without the subjective action is possible.  There it seems the Automatic Machines can act on their own without moral values being assigned to them.  Paul Ricoeur thinks about the dialectic of a self-identity (Ipse-Identity) and about the same-identity (Idem-Identity).  Based on the philosophy of Rene Descartes ("I think, therefore, I am") Ricoeur refers to the two aspects of personal identity, where these two aspects refer to "I think - I am".  This is all that cannot be doubted, according to Descartes.  And, the self-executable thoughts in thinking and execution, is a category of existence and a category of thought to be parallel to each other.  Thus, the starting point is the question of execution of Thoughts (Denken).  According to the failure of a materialistic anthropology we can determine human-beings (Menschen) only by their execution of Thoughts, which is in thereby a execution of "I" at the same time.


More:

For artificial intelligence to become true intelligence, it must become artificial soul and not be limited to a pure mind or pure cognition.  In addition, it's necessary to understand that feeling and motivation actually contribute to the increase of intelligence to a considerable degree and that they are possible in the computer.


Opaque, italicized and capitalized philosophical dribble-words, check.  Reviews of Descartes' thinking as if we had never heard of it before reading this paper, check.  Conception of emotions as a detached mindstuff-object supervening on normal cognition rather than an inevitable product of incremental evolution from pre-intelligent descendents, check.  Repudiation of posthumanism in the conclusion, check.

Why is it so hard to make concrete progress on the problem of how to write an intelligent software program that behaves such that we don't regret creating it?  A lack of experimental evidence is certainly a contributing factor, but theoretical progress is certainly possible, and we already know of dozens of immediate roadblocks that screw peoples' ideas up before they even get started.  Blatant anthropocentrism, unfamilarity with cognitive science, confusing metaphorical statements for ontological statements, mistaking words and phrases for the structure of cognitive content, etc.  I could list dozens of common errors that get in the way when we ask the simple question, "how would we build a machine that acts a certain way?"

Over the past six years, I've heard hundreds of proposals for approaches to building intelligent machines that are on humanity's side.  Sadly, it remains the case that the only proposals that have any real value are those coming out of the Singularity Institute for Artificial Intelligence.  The problem is certainly not solved, and any solution will likely require the efforts and input of many more geniuses than the number that are currently working at SIAI.  

What is Friendly AI?  There is a good place to start asking this question, and it can be found on the Singularity Institute's website.  However, to make matters simpler, I will post it here.  The tagline of this short list of 24 definitions is "looking at the issue of AI morality from enough different angles to at least try and show what the question is":

  • Friendly AI is the art of designing and constructing minds that play a positive role in the universe.
  • A "Friendly AI" is an AI that takes actions that are, on the whole, beneficial to humans, humanity, and sentient life; actions that are benevolent rather than malevolent, nice rather than hostile.
  • Friendly AI is the means by which we ensure that transhuman intelligence in AIs is linked to transhuman morals, altruism, wisdom, and philosophy.
  • A Friendly seed AI is one such that the resulting Singularity is at least as good as a Singularity sparked by any individual human or combination of humans.
  • Friendliness is a "metawish" - a way of saying to an AI:  "When you grow up, grow into what we would have made you to be, if we were as smart as you."
  • A Friendly AI is an AI that wants to be Friendly - one which, like Martin Luther King or Gandhi, is altruistic not because someone is forcing it to be altruistic but because that is the AI's own choice. Gandhi had the power to stop being altruistic at any time, but chose not to do so.
  • Friendly AI is an attempt to get rid of the concept of "Asimov Laws" (a science-fictional plot device invented in the 1940s) and replace it with a serious discipline.
  • Friendly AI is an attempt to get rid of the concept of "Asimov Laws" (external programmatic constraints on an AI) and replace it with a solution which works even if the AI has unrestricted access to its own source code.
  • Friendly AI is an attempt to get rid of the concept of "Asimov Laws" (coercive restrictions placed on AIs, by humans, for essentially selfish purposes) and get past the "us vs. them" attitude that currently permeates discussion of AI.
  • Friendly AI is the set of technical and moral issues involved with standing, not just in loco parentis, but in loco evolution, to a new intelligent species.
  • Friendly AI is a channel for transferring human morality which obeys the constraint that each statement communicated, on any matter of fact or morality, is honestly believed or personally held by the programmer(s) making the statement.
  • Friendly AI is the art of constructing an AI morality such that the final result is not sensitive to the choice of which particular programmers built the AI, as long as the programmers had the basic belief that an AI should try to avoid sensitive dependency on the choice of initial programmer.
  • Friendly AI is a strategy for ensuring that the personal quirks and philosophical errors of the original programmers don't remain fixed in the mind of the AI after it grows up.
  • A Friendly AI is a mind that, as it grows, grows into whatever a human upload would grow into as intelligence approached infinity as a limit. (If it makes a difference, this can be further qualified by specifying that the human upload starts out with a philosophical commitment to rationality and altruism, or even that the human upload starts out as a pure altruist.)
  • Friendly AI is a strategy for ensuring that the Singularity transcends the quirks and errors of whichever technological civilization first creates self-improving minds (i.e: only two generations ago in the United States, blacks rode in the back of the bus; we don't know what deep and shallow mistakes may persist in our contemporary conceptions of morality).
  • A Friendly AI is an AI that is "on the side" of sentient life.
  • Friendly AI is the technological pathway required to defend the integrity of the class of Singularities originally sparked by an AI.
  • A Friendly AI is a human-equivalent philosopher.
  • Friendly AI is the strategy by which the basic challenge of constructing an AI morality is transferred over to the AI itself, so that the problem can be handled or reconsidered by the transhuman intelligence of an AI that surpasses human intelligence.
  • Friendly AI is a way of transferring to a transhuman AI the question "What morality should be given to a transhuman AI?"
  • Friendly AI is an attempt to create an AI, which, when it grows into a transhuman, will be capable of dealing with issues that exhibit dependency on the philosophical question:  "What is good, what is evil, and how should we be asking this question?"
  • Friendly AI is the attempt to describe the complex functional adaptations underlying metamorality - the forces that influence how humans think when faced with a choice between alternative moral or philosophical systems.
  • Friendly AI is the attempt to describe the structure of human cognition about metamorality in sufficient detail to include all structural properties underlying our intuitive understanding of the metawish "Be the best AI we could have constructed you to be."
  • Friendly AI is the attempt to construct a nonanthropocentric theory of cognitive processes underlying moral and metamoral reasoning, with sufficient generality to predict the differential results of different AI designs.


For more on Friendly AI, see 'Beyond anthropocentrism'.

Published Thursday, September 07, 2006 12:13 AM by Michael Anissimov

Comment Notification

Join or sign in to track comments

Comments

 

Mr. Farlops wrote on September 10, 2006 1:08 AM

I don't think it's any more easy to make an artificial brain that's somehow restricted to be friendly than it is to make a human brain that is somehow restricted to friendly. The whole "friendly AI" idea that has floated around our circles for the past few years I think is simplistic.

I'm not saying it isn't doable. I'm just saying it overlooks some key points.

Some of the scary stuff Abolitionist was and is writing about at this site would probably have to be used to force a brain, natural or artificial, to be friendly. Altering a person's emotional hardware and pleasure/pain responses would be one way to enforce ethical behavior.

Asimov always assumed his three laws were wired so deeply into robot brains that the brain would be badly damaged if they were tampered with or removed.

As a result Asimov's robots are incredibly fragile. Whenever they faced a paradox or dilemma involving the three laws, they'd suffer mental illness, that experts like Susan Calvin would have to step in and explain or fix.

Even though this is all fiction, I think it illustrates a useful point. Restricting brains in this way makes them fragile to surprise and change. Asimov's robots are noble and highly ethical but they are also very fragile.

It also smacks of slavery. In his later stories, Asimov's robots are at least as smart, wise and creative as his humans but they are still restricted by these hardwired rules. Eventually, in "That thou art mindful of him" Asimov has his robots cleverly think of a very subtle way to get out from their slavery, a process that takes decades.

Sapient beings, emergent or artificial, are full of surprises. There are probably lots of ways we could restrict human and non-human brains so they are physically incapable of thinking or doing certain things but is it really a good idea to do this?

And as they get smarter then we are, it's going be very hard to bottle them up.  When their perception and accumen grows superhumanly subtle, they'll see flaws in our schemes that we don't.

 

Michael Anissimov wrote on September 11, 2006 2:29 AM

Farlops,

Please read "Creating Friendly AI", then comment.

 

Sideways wrote on September 12, 2006 6:53 PM

I don't know how we can expect to create friendly AI when we don't even manage to be friendly human beings half the time.

Join or sign in to post a comment
Submit

Syndication

This Blog

Top Tags

No tags have been created or used yet.
Advertise | Help | Contact | About | Terms | Privacy | Copyright © 2007 Betterhumans | Powered by Community Server | Partners:
World Transhumanist Association Institute for Ethics and Emerging Technologies Immortality Institute Methuselah Mouse Prize Foresight Institute Singularity Institute for Artificial Intelligence Lifeboat Foundation