Mammalian Value Systems
Characterizing human values is a topic deeply interwoven with the sciences, humanities, art, and many other human endeavors. In recent years, a number of thinkers have argued that accelerating trends in computer science, cognitive science, and related disciplines foreshadow the creation of intelligent machines which meet and ultimately surpass the cognitive abilities of human beings, thereby entangling an understanding of human values with future technological development. Contemporary research accomplishments suggest sophisticated AI systems becoming widespread and responsible for managing many aspects of the modern world, from preemptively planning users' travel schedules and logistics, to fully autonomous vehicles, to domestic robots assisting in daily living. The extrapolation of these trends has been most forcefully described in the context of a hypothetical "intelligence explosion," in which the capabilities of an intelligent software agent would rapidly increase due to the presence of feedback loops unavailable to biological organisms. The possibility of superintelligent agents, or simply the widespread deployment of sophisticated, autonomous AI systems, highlights an important theoretical problem: the need to separate the cognitive and rational capacities of an agent from the fundamental goal structure, or value system, which constrains and guides the agent's actions. The "value alignment problem" is to specify a goal structure for autonomous agents compatible with human values. In this brief article, we suggest that recent ideas from affective neuroscience and related disciplines aimed at characterizing neurological and behavioral universals in the mammalian class provide important conceptual foundations relevant to describing human values. We argue that the notion of "mammalian value systems" points to a potential avenue for fundamental research in AI safety and AI ethics.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous VehiclesEthicsSimilar Papers 제목 키워드 기반
A $4,000 Workstation for Mammalian Genome Assembly with Long Reads
Long-read sequencing has enabled the de novo assembly of several mammalian genomes, but with high cost in computing. Here, we demonstrated de novo assembly of mammalian genome using long reads in an efficient and inexpen…
Precise and scalable self-organization in mammalian pseudo-embryos
Gene expression is inherently noisy, posing a challenge to understanding how precise and reproducible patterns of gene expression emerge in mammals. We investigate this phenomenon using gastruloids, an in vitro model for…
Feynman Machine: The Universal Dynamical Systems Computer
Efforts at understanding the computational processes in the brain have met with limited success, despite their importance and potential uses in building intelligent machines. We propose a simple new model which draws on …
Comparative prospects of imaging methods for whole-brain mammalian connectomics
Mammalian whole-brain connectomes are a foundational ingredient for holistic understanding of brains. Indeed, imaging connectomes at sufficient resolution to densely reconstruct cellular morphology and synapses represent…
ELM Solutions for Event-Based Systems
Whilst most engineered systems use signals that are continuous in time, there is a domain of systems in which signals consist of events. Events, like Dirac delta functions, have no meaningful time duration. Many importan…