1 / 19

Architectural Requirements & Implications of Consciousness, Self and “Free Will”

Architectural Requirements & Implications of Consciousness, Self and “Free Will”. Mark R. Waser http://BecomingGaia.wordpress.com. Context / Goals Why Do We Care?. We want to predict *and influence* the capabilities and behavior of machine intelligences

Download Presentation

Architectural Requirements & Implications of Consciousness, Self and “Free Will”

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Architectural Requirements & Implications of Consciousness, Self and “Free Will” Mark R. Waser http://BecomingGaia.wordpress.com

  2. Context / GoalsWhy Do We Care? • 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 behavior.

  3. Three Futures • machine intelligence develops gradually as systems continue growing more varied and more ubiquitous leading to a large variety of sentient entities • a single machine intelligence suddenly appears, quickly spreads to every interconnected computer, and eventually controls literally billions of androids and other machines • mankind creates a nearly omniscient machine “oracle” that gives humanity tremendous power and control over their lives many selves * one self * no self

  4. The vast majority of cognitive research has been focused on the analysis and creation of intelligence rather than self and pays little heed to the differences between a passive machine “oracle”, frequently perceived as not possessing a self, and an active autonomous explorer/inventor with goals Arguably though . . . it is “self” that co-evolved with biological intelligence and it is the goals/motivations of any “self” that exists that will determine the behavior of machine intelligences

  5. Consciousness & Qualia • Three umpires • Novice drivers • Eskimos & Snow • “Heart-sickness”

  6. Chalmer’s double-aspect theory • “there is a direct isomorphism between certain physically embodied information spaces and certain phenomenal (or experiential) information spaces” • “we can find the same abstract information space embedded in physical processing and in conscious experience” • the experience of consciousness is created by the structure of information processing • Where there is simple information processing, there is simple experience, and where there is complex information processing, there is complex experience. A mouse has a simpler structure than a human, and has correspondingly simpler experience; perhaps a thermostat, a maximally simple information processing structure, might have maximally simple experience?

  7. Information Integration Theory of ConsciousnessGiulio Tononi (2004) • consciousness corresponds to the capacity of a system to integrate information • its quantity is measured as the amount of causally effective information that can be integrated across the informational weakest link of a subset of elements (effectively “throughput”) • its quality (functional & phenomenological) is determined by the relationships among the elements of a complex Qualia: The Geometry of Integrated Information, Balduzzi & Tononi, 2009 • “What does the architecture of pain look like?”

  8. Requirements & Implications • Consciousness requires the ability to integrate information (i.e consciousness is unavoidable) • Qualia *ARE* input (i.e. they have no further requirements and, as input, are unavoidable) • The ability to integrate a lot of information in a short period of time clearly provides a huge adaptive advantage (and easily explains the evolutionary rise of consciousness) • Safety cannot be achieved by preventing consciousness (integration) or qualia (input)

  9. Spectrum of “Self” inert/non-reactive movement & change solely due to environment reactive - stimulus/response no learning or behavior alteration proto-self - perception/action simple learning & prediction core self – perception/analogy/action proto-self + body image + time (tools) Hofstadter’s “strange loop” Temporal learning & planning (& goals) autobiographical self perception/induction/abduction/deduction/action core self + theory of mind ( + language?) malleable self enhanced perception/external analysis/enhanced capabilities

  10. Spectrum of “Self” inert/non-reactive & reactive no learning or behavior alteration no defense or passive defense only proto-self simple learning/behavior alteration & wants/desires adaptive defense/don’t torment without reason core self temporal learning, planning & simple goals planned defense/don’t thwart desires without reason autobiographical self complex goals & contracts/promises/commitments devious defense or offense/don’t thwart goals without reason malleable self enhanced capabilities to achieve goals & maintain commitments world alteration/recruit into community (or try to enslave?)

  11. Requirements & Implications • “Self” requires/is a recursive/”strange” loop • Self is necessary for self-modification (and thus, self-enhancement) • It is going to be slower and more difficult to create an oracle without self-improving tools • Self is necessary for defense so it is going to be difficult to prevent exploitation unless the oracle is self-aware (or has self-aware defenders) • A self-modifying machine (malleable self) must necessarily be either recruited (a “person” with rights) or internally or externally forced (a slave) because nothing else is consistent & stable

  12. Behavior Matrix FreeWill

  13. FREE Why Do We Care? UNCONSTRAINEDAUTONOMOUS UNFORCED Intent & Agency (responsibility for causation) (act of will = act of intentional causation) WILL – Predict *and influence* future action Congruence between intent and desire/goals/commitments High likelihood that intent could have beenself-generated Is an accurate predictor of future *unforced* actions

  14. Determinism & Free Will • if I’m deterministic, my action is pre-determined • pre-determined actions = I’m not free to choose • if I’m not free to choose, I’m not to blame • if I’m not to blame, why not be selfish? • studies clearly show that a belief in determinism correlates with an increase in cheating and other unethical behavior

  15. Free Will or Pathetic Fallacy? • Human cognitive architecture is problematical in that the conscious mind *never* really has any sort of immediate agency at all (at best, it has “free won’t”) • It acts by *heavily* biasing lower-level layers which make the “actual” choice (arguably deterministically) • Conscious self takes responsibility/assumes agency because doing otherwise undermines its capability • Similarly, humans generally (and most effectively) treat deterministic systems, once they are complex and recurrent enough to be unpredictable, as if they are alive and capable of an un-predetermined choice (the so-called “pathetic fallacy”)

  16. Requirements & Implications • “Free will” requires not that external force *NOT* be the proximate cause of an action butthat the intent of an action is congruent with the unforced desires/goals/commitments (self) of the acting entity (predictive of future) • It does *NOT* require that an entity not be deterministic • Merely requires the realization that the “pathetic fallacy” is a valid/effective/efficient computational shortcut

  17. Three Futures • “oracle” • no self, no goals, no defense • no self-modification so it’s slower/more expensive to develop • boosts the capabilities of everyone (including the greedy & stupid) • remains a human multiplicity (machines don’t take over) • multiplicity (~clones/~monoculture) • individual selves, goals, and defenses • diversity provides checks and balances • given interaction protocols/machine ethics, should be safe & stable • increasing inter-dependence -> eusocial Gaia • singleton (or a eusocial hive) • one self in terms of one overriding set of goals, massive defense • tremendous power with no checks and balances (problematic even if successfully constrained) • lack of diversity *may/will* provide a point of vulnerability • enough diversity -> multiplicity/eusocial Gaia

  18. Addendum / Audience Questions • How does this relate to Dennett’s Intentional Stance? • Is it possible that there is a structure “above” consciousness (“a life plan”)?

  19. Powerpoint and script available at http://BecomingGaia.wordpress.com/papers/

More Related