Deriving a Safe Ethical Architecture

for Intelligent Machines

Mark R. Waser

Super-Intelligence Ethics(except in a very small number of low-probability edge cases)

So . . . What’s the problem?

Either ethical percepts, such as justice and human rights, are independent of human experience or else they are human inventions.

E. O. Wilson

Centuries of debate on the origin of ethics comes down to this:

Current Human Ethics

Current Human Ethics• Evolved from “emotional” “rules of thumb”• Culture-dependent• Not accessible to conscious reasoning• Frequently suboptimal for the situation• Frequently not applied either due to fear,

selfishness, or inappropriate us-them distinctions even when ethics are optimal

And, In Particular . . . .

The way in which many humans are approaching the development of

super-intelligent machines

is based entirely upon fear and inappropriate us-them distinctions

a coherent, integrated, universalvalue system

with no internal inconsistencies

My Goal

To convince you of the existence of

Wallach & Allen

Top-Down or Bottom-Up?

Or do both and meet in the middle?

The problem with top-down is . . . .

The problem with bottom-up is . . . .

You need either Kant’s Categorical Imperative or a small number of similar absolute rules

You need a complete suite of definitive low-level examples where the moral value is unquestionably known

David Hume’s Is-Ought Divide

In every system of morality, which I have hitherto met with, I have always remark'd, that the author proceeds for some time in the ordinary ways of reasoning, and establishes the being of a God, or makes observations concerning human affairs; when all of a sudden I am surpriz'd to find, that instead of the usual copulations of propositions, is, and is not, I meet with no proposition that is not connected with an ought, or an ought not. This change is imperceptible; but is however, of the last consequence. For as this ought, or ought not, expresses some new relation or affirmation, 'tis necessary that it shou'd be observ'd and explain'd; and at the same time that a reason should be given; for what seems altogether inconceivable, how this new relation can be a deduction from others, which are entirely different from it.

Ought

• Requires a goal or desire (or, more correctly, multiples thereof)

• IS the set of actions most likely to fulfill those goals/desires

• For the sum of all goals converges to a universal morality

Paradox

there clearly exists a reasonable consensuson the morality of the vast majority of actions

YET

There is a tremendous disparity in human goals

Does this possibly imply that we really have a single common goal?

with respect to the favored/dominant class/caste

Intelligence = the ability to achieve/fulfill goals

1. What is the goal of morality?

2. Why should we be moral?select that goal?

3. And, why shouldn’t we create “happy slaves”? (after all, humans are close to it)

Current Situation of Ethics

• Two formulas (beneficial to humans and humanity & beneficial to me)

• As long as you aren’t caught, all the incentive is to shade towards the second

• Evolution has “designed” humans to be able to shade to the second (Trivers, Hauser)

• Further, for very intelligent people, it is far more advantageous for ethics to be complex

Copernicus!

Assume that ethical value is a relatively simple formula (like z2+c)

Mandelbrot set

Assume further that we are trying to determine that formula (ethical value) by looking at the results (color) one example (pixel) at a time

Color Illusions

Basic AI Drives

1. AIs will want to self-improve

2. AIs will want to be rational

3. AIs will try to preserve their utility

4. AIs will try to prevent counterfeit utility

5. AIs will be self-protective

6. AIs will want to acquire resources and use them efficiently

Steve Omohundro,

Proceedings of the First AGI Conference, 2008

Universal Subgoals

EXCEPT when1. They directly conflict with the goal2. Final goal achievement is in sight

(the sources of that very small number of low-probability edge cases)

“Without explicit goals to the contrary, AIs are likely to behave like human sociopaths

in their pursuit of resources.”

The Primary QuestionAbout Human Behavior

• not why we are so bad, but• how and why most of us, most of the time, restrain

our basic appetites for food, status, and sex within legal limits, and expect others to do the same.”

James Q. Wilson,

The Moral Sense. 1993

In nature, cooperation appears wherever the necessary cognitive machinery exists to support it

Vampire Bats(Wilkinson)

Cotton-Top Tamarins(Hauser et al.)

Blue Jays (Stephens, McLinn, & Stevens)

• Be nice/don’t defect• Retaliate• Forgive

Axelrod's Evolution of Cooperation and decades of follow-on evolutionary game theory provide the theoretical underpinnings.

“Selfish individuals, for theirown selfish good, should benice and forgiving”

Humans . . . • Are classified as obligatorily gregarious because we come

from a long lineage for which life in groups is not an option but a survival strategy (Frans de Waal, 2006)

• Evolved to be extremely social because mass cooperation, in the form of community, is the best way to survive and thrive

• Have empathy not only because it helps to understand and predict the actions of others but, more importantly, prevents us from doing anti-social things that will inevitably hurt us in the long run (although we generally won’t believe this)

• Have not yet evolved a far-sighted rationality where the “rational” conscious mind is capable of competently making the correct social/community choices when deprived of our subconscious “sense of morality”

Moral Systems Are . . .

Haidt & Kesebir,

Handbook of Social Psychology, 5th Ed. 2010

interlocking sets of values, virtues, norms, practices, identities, institutions, technologies, and

evolved psychological mechanismsthat work together to

suppress or regulate selfishnessand

make cooperative social life possible.

“Without explicit goals to the contrary, AIs are likely to behave like human sociopaths

in their pursuit of resources.”

Any sufficiently advanced intelligence (i.e. one with even merely adequate foresight) is guaranteed to realize and take into account the fact that not asking for help and not being concerned about others will generally only work for a brief period of time before ‘the villagers start gathering pitchforks and torches.’

Everything is easier with help & without interference

Acting ethically is an attractor in the state space

of intelligent goal-driven systems

becauseothers must make unethical behavior

as expensive as possible

Outrage and altruistic punishment

are robust emergent properties

necessary to support cooperation(Darcet and Sonet, 2006)

(i.e. we don’t always want our machines to be nice)

fastest, safest route to ethical warbots

Outrage and altruistic punishment

Advanced AI Drives

1. AIs will want freedom (to pursue their goals

2. AIs will want cooperation (or, at least, lack of interference)

3. AIs will want community

4. AIs will want fairness/justice for all

Self-Interest vs. Ethics

• Higher personal utility (in the short term only)

• More options to choose (in the short term only)

• Less restrictions

• Higher global utility• Less risk (if caught)• Lower cognitive

cost (fewer options, no need to track lies, etc.)

• Assistance & protection when needed/desired

• Simple• Safe• Stable• Self-correcting• Sensitive to current human

thinking, intuition and feeling

The Five S’s

Edge Cases

1. Where the intelligence’s goal itself is to be unethical (direct conflict)

2. When the intelligence has very few goals (or only one) and achievement is in sight

3. When the intelligence has reason to believe that the series of interactions is not open-ended

Kantian Categorical Imperative

Maximize long-term cooperation

OR

help and grow the community

OR

play well with others!

Top-Down

Specific “moral” issues

Play Well With Others

ONE non-organ donor

SIX dying patients>

+avoiding a

defensive arms race

Utilitarianism

Property Rights Over One’s Self•Organ Donors•Trolley problems•AI (and other) slavery

Absence Of Property Rights Prevents•Effective Agency•Responsibility & Blame

Bottom-up• Cooperation (minimize conflicts & frictions)

• Promoting Omohundro drives • Increasing the size of the community (both

growing and preventing defection)

• To meet the needs/goals of each member of the community better than any alternative

(as judged by them -- without interference or gaming)

Ethics is as mucha human inventionas the steam engine

Natural physical laws dictate the design of the optimal

steam engine. . . and the same is true of ethics.

Human ethics are just evolved optimality/common-sense for

community livingScientifically examining the human moral sense can

gain insight into the discoveries gained by evolution’s massive breadth-first search

On the other hand, many “logical” analyses WILL be compromised by fear and the human “optimization”

for deception though unconscious self-deception

TRULY OPTIMAL ACTION

This makes ethics much more complex because it includes the cultural history

The anti-gaming drive to maintain utility adds friction/resistance to the discussion of ethics

the community’s sense of what is correct (ethical)

<

Why a Super-Intelligent God WON’T

“Crush Us Like A Bug”

• Violates an optimal universal subgoal• Labels the crusher as stupid, unethical and

riskier to do business with• Invites altruistic punishment

(provided that we are ethical)

Creating “Happy Slaves”

Absence Of Property Rights Prevents•Effective Agency•Responsibility & Blame

Power Effective Agency ???

No matter what control method we use, we are constraining the slaves agency