{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"“Preoccupied with a single leaf...you won't see the tree. Preoccupied with a single tree...you'll miss the entire forest. Don't be preoccupied with a single spot. See everything in its entirety...effortlessly.”\n - Takehiko Inoue\n\nMoral machines will rely upon a combination of practical and philosophical considerations. Bostrom’s Paperclip Maximizer is an absurd, albeit foundational, thought experiment in AI ethics. An AGI determined to produce paperclips could end civilization (Bostrom, 2003). \n\nGranted, it doesn’t seem likely. \n\nThe most daunting, underdiscussed, and bewildering aspect of future AGIs is arguably their potential plurality. As easy as it may be to guffaw at this notion, one consistent trend can be observed in the history of technology: a rapid increase in accessibility. There is no reason to believe AGI will be forever confined to a dozen proprietary systems held by a handful of benevolent organizations. \n\nPopular concern and scholarly attention currently revolves around individual AIs operating alone. Researchers tend to conceive of superintelligent AGI as a monolith with a single “mind.” This is misleading, as AGIs, including very bright ones, may be neither singular nor insular (Alonzi, 2020). \n\nOutcomes on the macro level frequently cannot be extrapolated from individual microbehaviors. \n\nConsider a model of neighborhood segregation where each resident only asks that one third of their neighbors be ethnically or economically similar to themselves. Despite being composed of fairly tolerant individuals, extreme segregation is still observed at the macro level (Schelling, 1969). \n\nFortunately, since LLMs are paving the way for improved simulacras of human behavior in mediums such as video games, it is now possible to begin seriously studying what sort of societies can emerge from the interactions of generative agents (Kim, 2023).  \n\nThere are very real ramifications from failing to step back and examine the forest. \nAnts coordinate with each other in a decentralized fashion. Boasting only simple nervous systems, the sum can hardly be predicted from its parts—at first glance. Naturally, there is no guarantee of such cooperation between the synthetic beings of the future–although perhaps this should not be cause for concern. \n\nIt seems unrealistic to assume that all AGIs, even if they are neuromorphic or programmed to be good, will follow a strictly ethical path: if they are intelligent beings, they are dynamic—capable of rapid change. Cheaters of different kinds abound in animal populations. Yet the rates of suckers, cheaters, and grudge-holders generally find equilibrium (Dawkins, 2016).\n\nKeeping AGI friendly does not end with inculcating individual intelligences with rigid maxims, but satisfactorily explicating upon the emergent phenomena that will arise from the interactions of similarly or differently educated machines—long before AGI becomes more than a possibility. \n\nFor this reason, the vocabulary, methods, and intuitions supplied by systems theory, economics, and evolutionary biology are of immense value to formulating a starting point for further lines of inquiry in the areas of narrow and general AI. \n\nTutelary Spirits and Digital Daemons \n\nA tutelary spirit guards a person or place. A daemon, one’s personal guide, is an example. Yet such spirits could be the defenders of a corporation, ideology, or a nation. Surely, if this is the case, they will on occasion come into conflict with one another. \n\nAt some point machines with near-human intelligence will be interacting with us (and each other) as personal assistants, teachers, nannies, counselors, caregivers, and, for lack of a better word, friends. A machine filling any of these positions would need a grasp of social dynamics and the emotional states of the people it's serving. \n\nWhile it may not matter whether a smart toaster prefers Kant or Mill, AI is poised to largely replace, and in some instances supplant, human workers. Business, national defense, law enforcement, jurisprudence, and governance are not immune to the encroachment of synthetic intelligences (Glenn et al, 2022). \n\nTruthfulness and privacy can clash, especially if something cannot decide exactly when it is trivial to withhold the truth. Total transparency would spell the death of personal liberty. \n\nSelf-interest and altruism are often at odds; a hypermoral machine would find any form of self-indulgence unnecessary or loathsome. Why should someone sit on the couch when there is litter in the street? A personal assistant designed to maximize human pleasure (even if it also attempted to reduce the self-destructiveness of its flesh-and-blood companion). \n\nHandling externalities, finding fair outcomes, determining when force is necessary, and arbitrating disputes are a few of the responsibilities these machines may have to shoulder. Dealing with these situations requires, along with something close to full-fledged AGI, sets of criteria the agents have to refer to make beneficent decisions.\n\nHomogeneity in form or training could be a substantial stumbling block to AGI safety—it may be the worst stumbling block of all. Diverse systems are robust ones. \n\nA population with limited genetic diversity does not stand a chance against an especially virulent pathogen (Mcdonald, 2013).  The same, in all likelihood, applies to digital pathogens and disinformation. \n\nDiversity not only ensures some degree of herd immunity, but assists in problem solving by leveraging the insights of different minds (Page, 2010). \n\nWhat’s Next? \n\nIt is not feasible, necessary, or worthwhile to analyze a film one bacterium at a time. Similarly, only so much can be learned by studying the solitary behaviors of social animals. Anticipating behaviors from a bird’s eye could make the task of overseeing AGI’s evolution substantially easier. \n\nPark et. al, cited at the beginning of this essay, showed remarkable results, reporting their generative agents “wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day.” \n\nWhile these worlds are greatly simplified versions of our own, the essential parts are still there. They allow us to preemptively explore and prepare for the unexpected. It’s not enough to simply tell an AI not to lie or make sure we get in our \n\nThe interdependence of a complex adaptive system’s components makes simulation the most viable avenue for exploring cause and effect relationships within it (Miller and Page, 2009). \n\nChaos theory emphasizes the sensitivity of networks to starting conditions (Boccaletti, 2000), which strongly suggests thought should be put into the architecture of an AGI society long before it begins to take shape. \n\n \nReferences and Suggested Reading\n\nAdam Alonzi; The Foundations of Robosociology: Values and The Aggregate Behaviors of Synthetic Intelligences; AI & Robotics 2020; August 23, 2020\n\nBoccaletti, Stefanos, et al. \"The control of chaos: theory and applications.\" Physics reports 329.3 (2000): 103-197.\n \nBostrom, Nick. \"Ethical issues in advanced artificial intelligence.\" Science fiction and philosophy: from time travel to superintelligence (2003): 277-284.\n\nDawkins, Richard. The selfish gene. Oxford university press, 2016.\n\nGlenn, Jerome C., Theodore J. Gordon, and Elizabeth Florescu. \"State of the future.\" Washington, DC: The Millennium Project (2017).\n\nMiller, John H., and Scott E. Page. Complex adaptive systems: an introduction to computational models of social life: an introduction to computational models of social life. Princeton university press, 2009.\n\nMcDonald, Bruce A., and Celeste Linde. \"Pathogen population genetics, evolutionary potential, and durable resistance.\" Annual review of phytopathology 40.1 (2002): 349-379.\n\nPark, Joon Sung, et al. \"Generative agents: Interactive simulacra of human behavior.\" arXiv preprint arXiv:2304.03442 (2023).\n\nPage, Scott E. Diversity and complexity. Princeton University Press, 2010.\n\nSchelling, Thomas C. \"Models of segregation.\" The American Economic Review 59.2 (1969): 488-493.","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"****","metadata":{}}]}