Re: On Our Duty to Not Be Responsible for Artificial Minds

From: Samantha Atkins (
Date: Thu Aug 11 2005 - 22:35:20 MDT

On 8/9/05, Eliezer S. Yudkowsky <> wrote:
> Considering the relation between my parents and myself, "autonomy" consists of
> my parents being able to control a small set of variables in my upbringing and
> unable to control a much larger set of variables in my cognitive design. Not
> because my parents *chose* to control those variables and no other, but
> because my parents were physically and cognitively *unable* to select my
> genome on the basis of its consequences. Furthermore, my cognitive design -
> fixed beyond parental control - determined how I reacted to parental
> upbringing. My fixed cognitive design placed some variables within my
> parents' deliberate control, in the sense that they could, by speaking
> English, ensure I would grow up speaking English. However, some variables
> that my parents greatly desired to control, such as my religion, were beyond
> the reach of their best efforts at upbringing. It is not that they chose not
> to control this variable but that they were incapable of controlling it.
> In the case of an AI researcher we have many, many possibilities. Here are
> some possibilities that occur to me:
> 1) The AI researcher is fully capable of choosing between AI designs on the
> basis of their consequences, and chooses an AI design which invokes no
> significant moral processing within the AI. In this case I would assign moral
> responsibility to the AI researcher alone, for all consequences good or ill;
> the AI itself is not a moral agent.

As the AI designers are of considerably limited intelligence
concerning designing an intelligence as powerfull and especially more
powerful than their own it seems pointless to speculate that they
somehow should have known all the consequences of choosing those
design elements they are capable of choosing within the limited
abilities at their command.

If the AI is as capable of making free (relatively) choices as we are
then it is just as much a moral agent as we are.
> I assign full responsibility to the AI researcher for all consequences,
> intended or unintended.

This seems arbitraty and capricious. How can one be resposible for
unintended consequences utterly beyond one's ability to predict?

> An AI researcher has a responsibility to choose an AI
> design with predictable consequences. If the AI researcher negligently uses
> an AI design the AI researcher can't predict, the AI researcher is still fully
> responsible for all actual consequences.

Such a designed artifact almost of necessity cannot be as intelligent
as the designer.

> 2) A competent AI researcher, acting on a perceived moral responsibility to
> create moral children, deliberately constructs an AI which is tightly or
> loosely analogous to a human - such that the initial design responds to
> environmental stimuli and parental upbringing much as does a human, learns and
> argues morality much as does a human, is partially unaware of its own emotions
> like a human, etc.
> We presume that this is a deliberate attempt to create a child of humankind, a
> worthy participant in the story of Earth-originating life.

OK, but why would attempting to create something like an evolved
being which is not an evolved being at all, be reasonable or at all
compassionate? It seems to me that augmenting exisitng humans would
be a more rational and acheivable course if human like higher
intelligences is the desired outcome.

> In this case I would assign a mixture of moral responsibility to the AI
> researcher and to the AI. The AI, having been deliberately constructed as a
> moral agent, bears responsibility for its actions. If we hold the AI to
> account, it will understand what it means to be held to account, and treat
> this as a moral argument in the same way we do. (In contrast a paperclip
> maximizer would care about human moral arguments only as a sort of cognitive
> activity in humans that might be exploited to create paperclips.) The AI
> researcher is responsible for all predictable consequences of "constructing a
> humanlike moral agent", including liability for child abuse if later
> authorities determine the initial design to have been botched. But I would
> not say that the AI researcher is responsible for all actions of the created
> AI, presuming that the created AI was at least as initially benevolent as an
> average human. Deliberately creating an AI that is worse than average, for
> example, an AI that starts out with the same emotional makeup as an autistic
> or a serial killer, makes the AI researcher liable for both child abuse and
> for the consequences of the AI's actions.
> 3) The AI researcher deliberately chooses an AI design which involves complex
> moral processing, but a different sort of complex moral processing than a
> human being. Coherent Extrapolated Volition, for example. In this case,
> assigning moral responsibility becomes difficult; we're operating outside the
> customary problem space. An AI researcher, responding to a perceived moral
> duty, invents an AI which takes its direction from a complexly computed
> property of the human species as a whole. If this AI saves a life, to whom
> belongs the credit? The researcher? The human species? The AI?
> I would assign moral responsibility to the AI programmer for the predictable
> consequences of creating such an AI, but not the unpredictable consequences,
> provided that the AI as a whole has predominantly good effects (even if there
> are some negative ones). If the AI has a predominantly negative effect,
> whether by bug or by unintended consequence, then I would assign full
> responsibility to the programmer.

Why? The consequences in this case are certainly not predictable so
how is the creator culpable for any and all consequences?

> If a CEV saves you from dying, I would call that a predictable (positive)
> consequence and assign at least partial responsibility to the programmers and
> their supporters. I would not assign them responsibility for the entire
> remaining course of your life in detail, positive or negative, even though
> this life would not have existed without the CEV. I would forgive the
> programmers that your evil mother-in-law will also live forever; they didn't
> mean to do that to you specifically.
> **
> I don't believe there exists any such thing as "autonomy".

Then I think you are arguing a less than useful (and perhaps ironic) position.

> The causal graph of physics goes back at least to the Big Bang. If you don't
> know the cause, that's your own ignorance; it doesn't mean there is no cause.

Cause? Are we still caught up in pointless clockwork universe models?
 Everything can be reduced to physics but not everything can
*usefully* be reduced to phhysics.
> I am not "autonomous". I am a Word spoken by evolution, which determined both
> my tendencies, and my susceptibility to environmental influence.

But not your detailed choices. Our ability to even meaningfully
conceive of going beyond our evolved nature illustrates nicely the
lack of predictability regardless of how many causes we may enumerate.

> Where there
> is randomness in me it is because my design permits randomness effects.
> Evolution created me via a subtle and broken algorithm, which caused the goals
> of my internal psychology to depart far from natural selection's sole
> criterion of inclusive genetic fitness. Either way, evolution bears no moral
> responsibility because natural selection is too far outside the humane space
> of optimization processes to internally represent moral arguments.

Since evolution is not a being much less a moral being it obviously
cannot bear "moral responsibility".
> My parents were almost entirely powerless compared to an AI designer.

The poor AI designer is powerless to do much beyond set up some
hopefully fruitful and benevolent intial conditions. Since the young
AI is a totally different species it may be that the programmer has
even less insight and use as a model for the AI child.

> My
> parents can bear moral responsibility only for what they could control. Given
> those fixed background circumstances, I understand, respect, and am grateful
> to my parents where they deliberately chose not to exercise a possible
> control, seeing an obligation to let me make up my own mind. Which is to say
> that my parents handed determination back to the internal forces in my mind,
> which they did not choose to create. My parents let me make my own decision
> rather than crushing me, in a case where my internal cognitive forces would
> exist regardless. Had my parents also knowingly selected my nature, their
> decision not to nurture too hard would take on a stranger meaning.
> It is not clear what, if anything, an AI researcher can deliberately do that
> is analogous to the choice a human parent faces - even if we understand and
> respect and attach significant moral value to a human parent's choice not to
> determine offspring too strongly. The mechanisms of "autonomy", if we value
> them, would need to be deliberately created in a nonhuman mind. It is
> predictable that if you construct a mind to love it will love, and if you
> construct a mind to hate it will hate.

It is barely predictable how a human mind raised to love will turn
out. I doubt such a complex quality can simply be programmed in.

> In what sense would the AI programmer
> *not* be responsible?

In that the self-improving nature of the AI will take it and its
choice space far beyond the competence of any merely human creator to
reliably map and predict.

> Perhaps we can rule that we value human likeness in
> artificial minds, that it is good to grant them many emotions sometimes in
> conflict. We could hold the AI researcher responsible for the choice to
> construct a humanlike mind, but not for the specific and unpredictable outcome
> of the humanlike emotional conflicts.
> This exception requires that the AI researcher gets it right and creates a
> healthy child of humankind. Screw it up - create a mind whose internal
> conflicts turn out to be simpler and less interesting than human average, or
> whose internal conflicts turn out to be more painful - and I would hold the
> designers fully responsible. If you can't do it right, then DON'T DO IT.

So unless we are much more competent than I have reason to believe we
are we should just let human level minds bungle their way into [almost
inevitiable] oblivion?

> If
> you aren't sure you can do it right, WAIT until you are. I would like to see
> humankind get through the 21st century without inventing new and horrible
> forms of child abuse.

Unless we radically augment ourselves and perhaps even then, that day
we are that uber-competent will in my opinion never come.

> An AI researcher who deliberately builds an AI unpredictable to the designer,
> but which AI does not qualify as a healthy child of humankind, bears full
> responsibility for the consequences of the AI's unpredictable actions whatever
> they may be.

Of course no AI can qualify as a healthy child because that isn't
remotely what it is. So how is this a valid distinciton?

> This is so even if the AI researcher claims deliberate refusal
> to understand in order to preserve the quote autonomy unquote of the AI. I
> would advise that you not believe the claim. Incompetence is not a moral
> duty, but people often try to excuse it as a moral duty.

Claiming competence beyond what is possible for mere humans is not useful.

> "Moral autonomy" is
> not randomness. There is nothing moral about randomness. Nor is everything
> that you're too incompetent to predict "autonomous".

Autonomous here largely means capable of choosing among alternatives
without undue coercion. Anything which makes such choices and learns
in the process from the outcome of those choices is in principal not
fully predictable unless the set of possible states is artificially
constrained. I don't see any more how to constrain such an AI in this
way than I see how to constrain it with the three laws of robotics.
> Moral autonomy requires a specific kind of cognitive complexity which will
> take high artistry to create in an artificial mind. The designers might
> *choose* not to compute out in advance the child's destiny, nor fine-tune the
> design on the basis of such predictions. But be very sure, the designers do
> understand *all* the forces involved - if they possess the art to create a
> healthy child of humankind.

This is a mere assertion that I consider bogus. We may be competent
enough to create the seed of a real AI but I do not belief we are
competent to design it to this fine degree of predictability.

> Ignorance exists in the mind, not in reality.

Not useful as in reality the minds of the designers have quite finite
limits that may fall far short of *the answer* in reality. Ignorance
is an inescapable aspect of limited intelligence.

- samantha

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:51 MDT