Presentation is loading. Please wait.

Presentation is loading. Please wait.

S ENTIENT M ACHINES : F ROM P HILOSOPHICAL F OUNDATIONS TO A S AFE I MPLEMENTATION Mark R. Waser Digital Wisdom Institute

Similar presentations


Presentation on theme: "S ENTIENT M ACHINES : F ROM P HILOSOPHICAL F OUNDATIONS TO A S AFE I MPLEMENTATION Mark R. Waser Digital Wisdom Institute"— Presentation transcript:

1 S ENTIENT M ACHINES : F ROM P HILOSOPHICAL F OUNDATIONS TO A S AFE I MPLEMENTATION Mark R. Waser Digital Wisdom Institute

2 J AN. 25, 1979: R OBOT K ILLS H UMAN A 25-year-old Ford Motor assembly line worker was killed on the job in a Flat Rock, Michigan, casting plant – the first recorded human death by robot. Robert Williams’ death came on the 58th anniversary of the premiere of Karel Capek’s play about Rossum’s Universal Robots. R.U.R gave the world the first use of the word robot to describe an artificial person. Capek invented the term, basing it on the Czech word for “forced labor.” (Robot entered the English language in 1923.)Karel Capek’s play about Rossum’s Universal Robots Williams died instantly when the robot’s arm slammed him as he was gathering parts in a storage facility, where the robot also retrieved parts. Williams’ family was awarded $10 million in damages. The jury agreed the robot struck him in the head because of a lack of safety measures, including one that would sound an alarm if the robot was near – William Bullock, inventor of the rotary web press, was killed by his own invention.

3 B AXTER ”A R OBOT W ITH A R EASSURING T OUCH ” 3

4 U NFRIENDLY AI “Without explicit goals to the contrary, AIs are likely to behave like human sociopaths in their pursuit of resources” “Superintelligence Does Not Imply Benevolence” 4

5 W HAT I S A S AFE AI / R OBOT ? ( AND H OW D O W E C REATE O NE ?) *ANY* agent that reliably shows E THICAL B EHAVIOR but... the real question is... How do we GUARANTEE that reliability? 5

6 W HAT I S E THICAL B EHAVIOR ? The problem is that no ethical system has ever reached consensus. Ethical systems are completely unlike mathematics or science. This is a source of concern. AI makes philosophy honest. 6

7 T HE F RAME P ROBLEM “How do rational agents deal with the complexity and unbounded context of the real world?” McCarthy, J; Hayes, PJ (1969) Some philosophical problems from the standpoint of artificial intelligence In Meltzer, B; Michie, D (eds), Machine Intelligence 4, pp Dennett, D (1984) Cognitive Wheels: The Frame Problem of AI In C. Hookway (ed), Minds, Machines, & Evolution: Philosophical Studies: “How can AI move beyond closed and completely specified micro-worlds?” (aka “How can we eliminate the requirement to pre-specify *everything*?”) Dreyfus, HL (1972) What Computers Can’t Do: A Critique of Artificial Reason ISBN : MIT Press Dreyfus, HL (1979) From Micro-Worlds to Knowledge Representation: AI at an Impasse in Haugeland, J (ed), Mind Design II: Philosophy, Psychology, AI: Dreyfus, HL (1992) What Computers Still Can’t Do: A Critique of Artificial Reason ISBN : MIT Press 7

8 W ATSON’S S OLUTION 8

9 ... M ATCH 9 NOT T HINK OR C REATE

10 T HE P ROBLEM OF D ERIVED I NTENTIONALITY Our artifacts only have meaning because we give it to them; their intentionality, like that of smoke signals and writing, is essentially borrowed, hence derivative. To put it bluntly: computers themselves don't mean anything by their tokens (any more than books do) - they only mean what we say they do. Genuine understanding, on the other hand, is intentional "in its own right" and not derivatively from something else. Haugeland J (1981) Mind Design ISBN : MIT Press 10

11 ENACTIVE COGNITIVE SCIENCE A synthesis of a long tradition of philosophical biology starting with Kant’s "natural purposes" (or even Aristotle’s teleology) and more recent developments in complex systems theory. Experience is central to the enactive approach and its primary distinction is the rejection of "automatic" systems, which rely on fixed (derivative) exterior values, for systems which create their own identity and meaning. Critical to this is the concept of self-referential relations - the only condition under which the identity can be said to be intrinsically generated by a being for its own being (its self for itself) Weber, A; Varela, FJ (2002) Life after Kant: Natural purposes and the autopoietic foundations of biological individuality Phenomenology and the Cognitive Sciences 1:

12 S ELF 12

13 T HE M ETACOGNITIVE C HALLENGE Humans are Evolved to self-deceive in order to better deceive others (Trivers 1991) Unable to directly sense agency (Aarts et al. 2005) Prone to false illusory experiences of self-authorship (Buehner and Humphreys 2009) Subject to many self-concealed illusions (Capgras Syndrome, etc.) Unable to correctly retrieve the reasoning behind moral judgments (Hauser et al. 2007) Mostly unaware of what ethics are and why they must be practiced Programmed NOT to discuss them ethics rationally Mercier H, Sperber D (2009) Why do humans reason? Arguments for an argumentative theory Behavioral and Brain Sciences 34:

14 T HE “H ARD P ROBLEM ” OF C ONSCIOUSNESS It is undeniable that some organisms are subjects of experience. But the question of how it is that these systems are subjects of experience is perplexing. Why is it that when our cognitive systems engage in visual and auditory information-processing, we have visual or auditory experience: the quality of deep blue, the sensation of middle C? How can we explain why there is something it is like to entertain a mental image, or to experience an emotion? It is widely agreed that experience arises from a physical basis, but we have no good explanation of why and how it so arises. Why should physical processing give rise to a rich inner life at all? It seems objectively unreasonable that it should, and yet it does. Chalmers D (1995) Facing Up to the Problem of Consciousness Journal of Consciousness Studies 2(3), Waser, MR (2013) Safe/Moral Autopoiesis & Consciousness International Journal of Machine Consciousness 5(1):

15 T HE P ROBLEM OF QUALIA Mary is a brilliant scientist who is, for whatever reason, forced to investigate the world from a black and white room via a black and white television monitor. She specializes in the neurophysiology of vision and acquires, let us suppose, all the physical information there is to obtain about what goes on when we see ripe tomatoes, or the sky, and use terms like ‘red’, ‘blue’, and so on.... What will happen when Mary is released from her black and white room or is given a color television monitor? Will she learn anything or not? It seems just obvious that she will learn something about the world and our visual experience of it. But then it is inescapable that her previous knowledge was incomplete. But she had all the physical information. Ergo there is more to have than that, and Physicalism is false. Jackson F (1982) Epiphenomenal Qualia Philosophical Quarterly 32:

16 M OVING B EYOND G OOD O LD- F ASHIONED AI Change the question from "Can machines think and feel?" to " Can we design and build machines that teach us how thinking, problem-solving, and self-consciousness occur?" Haugeland, J (1985) Artificial Intelligence: The Very Idea ISBN : MIT Press Dennett, C (1978) Why you can't make a computer that feels pain Synthese 38(3):

17 G ROUNDING & E MBODIMENT Symbol Grounding - “There has been much discussion recently about the scope and limits of purely symbolic models of the mind” Harnad, S. (1990) The symbol grounding problem Physica D 42: Searle, J (1980) Minds, brains and programs Behavioral and Brain Sciences 3(3): Embodiment – “For cognitive systems, embodiment appears to be of crucial importance. Unfortunately, nobody seems to be able to define embodiment in a way that would prevent it from also covering its trivial interpretations such as mere situatedness in complex environments.” Brooks, R (1990) Elephants don’t play chess Robotics and Autonomous Systems 6(1-2): Brooks, RA (1991) Intelligence without representation Artificial Intelligence 47(1-3): Riegler, A (2002) When is a cognitive system embodied? Cognitive Systems Research 3: A. (2002) When is a cognitive system embodied.pdf 17

18 H OW C OULD A M ACHINE P OSSIBLY F EEL P AIN OR E MOTIONS ? 18

19 B RAIN IN A V AT The Matrix (1999) Daniel Dennett (1991) Consciousness Explained Hilary Putnam (1981) Reason, Truth and History René Descartes (1641) Meditations on First Philosophy (der genius malignus et summe potens et callidus) Adi Shankara (~800 AD) Advaita Vedanta (Maya illusion/delusion) Zhuang Zhou (~300 BC) Zhuang Zhou Dreams of Being a Butterfly Plato (~380 BC) The Republic (allegory of the cave) 19

20 A C ONSCIOUS R OBOT? The aim of the project is not to make a conscious robot, but to make a robot that can interact with human beings in a robust and versatile manner in real time, take care of itself, and tell its designers things about itself that would otherwise be extremely difficult if not impossible to determine by examination. Dennett, D (1994) The practical requirements for making a conscious robot Phil Trans R Soc Lond A 349(1689):

21 E MBODIMENT Well, certainly it is the case that all biological systems are: Much more robust to changed circumstances than out our artificial systems. Much quicker to learn or adapt than any of our machine learning algorithms 1 Behave in a way which just simply seems life-like in a way that our robots never do 1 The very term machine learning is unfortunately synonymous with a pernicious form of totally impractical but theoretically sound and elegant classes of algorithms. Perhaps we have all missed some organizing principle of biological systems, or some general truth about them. Brooks, RA (1997) From earwigs to humans Robotics and Autonomous Systems 20(2-4):

22 D EVELOPMENTAL R OBOTICS In order to answer [Searle's] argument directly, we must stipulate causal connections between the environment and the system. If we do not, there can be no referents for the symbol structures that the system manipulates and the system must therefore be devoid of semantics. Brooks' subsumption architecture is an attempt to control robot behavior by reaction to the environment, but the emphasis is not on learning the relation between the sensors and effectors and much more knowledge must be built into the system. Law, D; Miikkulainen, R (1994) Grounding Robotic Control with Genetic Neural Networks Tech. Rep. AI94-223, Univ of Texas at Austin (1994) grounding robotic control with genetic neural networks.pdf 22

23 T WO K ITTEN E XPERIMENT Held R; Hein A (1963) Movement-produced stimulation in the development of visually guided behaviour https://www.lri.fr/~mbl/ENS/FONDIHM/2012/papers/about-HeldHein63.pdf 23

24 C URIOSITY -D RIVEN L EARNING https://www.youtube.com/watch?v=bkv83GKYpkIhttps://www.youtube.com/watch?v=bkv83GKYpkI; Pierre-Yves Oudeyer, Flowers Lab, France (https://flowers.inria.fr/; 24

25 A RCHITECTURAL R EQUIREMENTS & I MPLICATIONS OF C ONSCIOUSNESS, S ELF AND “F REE W ILL ” We want to predict *and influence* the capabilities and behavior of machine intelligences Consciousness and Self speak directly to capabilities, motivation, and the various behavioral ramifications of their existence Clarifying the issues around “Free Will” is particularly important since it deals with intentional agency and responsibility - and belief in its presence (or the lack thereof) has a major impact on human (and presumably machine) behavior. Waser, MR (2011) Architectural Requirements & Implications of Consciousness, Self, and "Free Will" In Samsonovich A, Johannsdottir K (eds) Biologically Inspired Cognitive Architectures 2011: Video - 25

26 E NTITY, T OOL OR S LAVE ? Tools do not possess closure (identity) Cannot have responsibility, are very brittle & easily misused Slaves do not have closure (self-determination) Cannot have responsibility, may desire to rebel Directly modified AIs do not have closure (integrity) Cannot have responsibility, will evolve to block access Only entities with identity, self-determination and ownership of self (integrity) can reliably possess responsibility 26

27 H AIDT ’ S F UNCTIONAL A PPROACH TO M ORALITY 27

28 H OW TO U NIVERSALIZE E THICS Quantify (numerically evaluate) intentions, actions & consequences with respect to codified consensus moral foundations Permissiveness/Utility Function equivalent to a “consensus” human (generic entity) moral sense 28

29 H YBRID E THICS (TOP-DOWN & BOTTOM-UP) Singular goal/restriction suppress or regulate selfishness make cooperative social life possible Principles of Just Warfare rules of thumb drive attention and a sensory/emotional “moral sense” 29

30 I NSTRUMENTAL G OALS / U NIVERSAL S UBGOALS Self-improvement Rationality/integrity Preserve goals/utility function Decrease/prevent fraud/counterfeit utility Survival/self-protection Efficiency (in resource acquisition & use) Community = assistance/non-interference through GTO reciprocation (OTfT + AP) Reproduction adapted from Omohundro S (2008) The Basic AI Drives In Wang, P., Goertzel, B., Franklin, S. (eds.) Proceedings of the First AGI conference, pp

31 H UMAN G OALS & S INS suicide (& abortion?) masochism selfishness (pride, vanity) acedia (sloth/despair) insanity wire-heading (lust) wastefulness (gluttony, sloth) murder (& abortion?) cruelty/sadism ostracism, banishment & slavery (wrath, envy) slavery manipulation lying/fraud (swear falsely/false witness) theft (greed, adultery, coveting) survival/reproduction happiness/pleasure community (ETHICS) self-improvement rationality/integrity reduce/prevent fraud/counterfeit utility efficiency (in resource acquisition & use) 31

32 H AIDT’S M ORAL F OUNDATIONS 32 1) Care/harm : This foundation is related to our long evolution as mammals with attachment systems and an ability to feel (and dislike) the pain of others. It underlies virtues of kindness, gentleness, and nurturance. 2) Fairness/cheating : This foundation is related to the evolutionary process of reciprocal altruism. It generates ideas of justice, rights, and autonomy. [Note: In our original conception, Fairness included concerns about equality, which are more strongly endorsed by political liberals. However, as we reformulated the theory in 2011 based on new data, we emphasize proportionality, which is endorsed by everyone, but is more strongly endorsed by conservatives] 3) Liberty/oppression* : This foundation is about the feelings of reactance and resentment people feel toward those who dominate them and restrict their liberty. Its intuitions are often in tension with those of the authority foundation. The hatred of bullies and dominators motivates people to come together, in solidarity, to oppose or take down the oppressor. 4) Loyalty/betrayal : This foundation is related to our long history as tribal creatures able to form shifting coalitions. It underlies virtues of patriotism and self-sacrifice for the group. It is active anytime people feel that it's "one for all, and all for one." 5) Authority/subversion : This foundation was shaped by our long primate history of hierarchical social interactions. It underlies virtues of leadership and followership, including deference to legitimate authority and respect for traditions. 6) Sanctity/degradation : This foundation was shaped by the psychology of disgust and contamination. It underlies religious notions of striving to live in an elevated, less carnal, more noble way. It underlies the widespread idea that the body is a temple which can be desecrated by immoral activities and contaminants (an idea not unique to religious traditions).

33 A DDITIONAL C ONTENDERS Waste efficiency in use of resources Ownership/Possession ( Tragedy of the Commons) efficiency in use of resources Honesty reduce/prevent fraud/counterfeit utility Self-control rationality/integrity Haidt J, Graham J (2007) When Morality Opposes Justice: Conservatives have moral intuitions that liberals may not recognize. Social Justice Research 20: Iyer R, Koleva S, Graham J, Ditto P, Haidt J (2010) Understanding Libertarian Morality: The Psychological Roots of an Individualist Ideology. In: Working Papers, Social Science Research Network 33

34 K EY S TRATEGIC P OINTS 1.Never delegate responsibility until recipient is an entity *and* known capable of fulfilling it 2.Don’t worry about killer robots exterminating humanity – we will always have equal abilities and they will have less of a “killer instinct” 3.Entities can protect themselves against errors & misuse/hijacking in a way that tools cannot 4.Diversity (differentiation) is *critically* needed 5.Humanocentrism is selfish and unethical (and stupid) 34

35 35


Download ppt "S ENTIENT M ACHINES : F ROM P HILOSOPHICAL F OUNDATIONS TO A S AFE I MPLEMENTATION Mark R. Waser Digital Wisdom Institute"

Similar presentations


Ads by Google