Výsledky vyhľadávania - "Value Alignment Problem"

Cybernetic Shamanism and the Discipline of Architectural Consciousness

Autori: Olinger, Zack

Predmety: Hermeticism, Self-Directed Goal Formation, Neurodiversity, Autism, Recursive Self-Improvement, Generalization, Novel Synthesis, AI Co-Processor, Systems Theory, Architectural Consciousness, Epistemology, Anti-Fragility, AGI Ethics, Creativity, Value Alignment Problem, Participatory Universe, Artificial Intelligence, Jungian Psychology, Spiritual Technology, Psychology, Cybernetic Shamanism, Complexity Science, Self-Reflection, Autonomy, AGI, Grounding, Alignment, Self-Referential Systems, Meta-Cognition, Ontology, Few-Shot Generalization, Philosophy of Technology, Symbol Grounding, Transfer Learning, Consciousness Studies, Ontological Operating System, Generativity Beyond Training Data, Epistemological Cybernetics, FOS: Philosophy, ethics and religion, Transdisciplinarity, FOS: Psychology, Philosophy, Knowledge Systems, Sovereign Consciousness, Human-AI Collaboration, Dialogic Field, Artificial General Intelligence, Gnostic Engine

How Does Artificial Intelligence Pose an Existential Risk?

Autori: Vold, Karina Harris, Daniel R. Véliz, Carissa, book editor

Prispievatelia: Vold, Karina Harris, Daniel R. Véliz, Carissa, book editor

Zdroj: Oxford Handbook of Digital Ethics.

Dostupnosť: https://doi.org/10.1093/oxfordhb/9780198857815.013.36

AI Ethics and Value Alignment for Nonhuman Animals

Autori: Soenke Ziesche

Zdroj: Philosophies, Vol 6, Iss 2, p 31 (2021)

Predmety: AI safety, AI ethics, AI value alignment problem, value extraction, value aggregation, nonhuman animals, Logic, BC1-199, Philosophy (General), B1-5802

Relation: https://www.mdpi.com/2409-9287/6/2/31; https://doaj.org/toc/2409-9287; https://doaj.org/article/d58a9069b5e84f4aa6e8aabeb2978d0b

Dostupnosť: https://doi.org/10.3390/philosophies6020031
https://doaj.org/article/d58a9069b5e84f4aa6e8aabeb2978d0b

Value alignment: a formal approach

Autori: Sierra, Carles Osman, Nardine Noriega, Pablo a ďalší

Prispievatelia: Sierra, Carles Osman, Nardine Noriega, Pablo a ďalší

Zdroj: Digital.CSIC. Repositorio Institucional del CSIC
instname

Predmety: FOS: Computer and information sciences, Responsible AI, Artificial Intelligence (cs.AI), Norms, Computer Science - Artificial Intelligence, 05 social sciences, 0202 electrical engineering, electronic engineering, information engineering, Value-alignment problem, 0501 psychology and cognitive sciences, 02 engineering and technology

Prístupová URL adresa: http://arxiv.org/abs/2110.09240
http://hdl.handle.net/10261/238919

Personal Universes: A Solution to the Multi-Agent Value Alignment Problem

Autori: Yampolskiy, Roman V.

Zdroj: Faculty and Staff Scholarship

Predmety: AI Safety, Alternate Reality, Simulation, Value Alignment Problem, VR, Artificial Intelligence and Robotics, Computer Engineering, Computer Sciences, Engineering

Popis súboru: application/pdf

Relation: https://ir.library.louisville.edu/faculty/424; https://ir.library.louisville.edu/context/faculty/article/1430/viewcontent/Personal_Universes.pdf

Dostupnosť: https://ir.library.louisville.edu/faculty/424
https://ir.library.louisville.edu/context/faculty/article/1430/viewcontent/Personal_Universes.pdf

Value alignment: A formal approach

Autori: Sierra, Carles [0000-0003-0839-6233] Osman, Nardine [0000-0002-2766-3475] Noriega, Pablo [0000-0003-1317-2541] a ďalší

Témy: Responsible AI, Value-alignment problem, Norms, comunicación de congreso

URL: http://hdl.handle.net/10261/238919
Sí