Metraipolis › archive › dc_a770bf122258

A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences — arXiv:2608.08240

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08240
License (as archived)
CC0-1.0
Archived
2026-10-19T06:49:32.970Z
SHA-256 of the archived text
5f8dce7e261e669655e65cd1e5b37037e0be5ee7ba63f3266a5c7547bbbb1f2d
Stable URL of this page
https://metraipolis.com/documento/dc_a770bf122258

How to cite

A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences — arXiv:2608.08240 — arXiv (en), https://arxiv.org/abs/2608.08240 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a770bf122258 (Metraipolis archive dc_a770bf122258, sha256 5f8dce7e261e669655e65cd1e5b37037e0be5ee7ba63f3266a5c7547bbbb1f2d)
BibTeX
@misc{dca770bf122258,
  title = {A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences — arXiv:2608.08240},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08240},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a770bf122258; sha256 5f8dce7e261e669655e65cd1e5b37037e0be5ee7ba63f3266a5c7547bbbb1f2d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08240. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper explores the idea of promoting well-being and safety in human-AI interactions by forcing AI agents explicitly to empower humans and to manage the power balance between humans and AI agents in a desirable way. Using a principled, partially axiomatic approach based on desirable properties, we design a parametrizable and decomposable objective function for AI systems that represents an inequality- and risk-averse long-term aggregate of human power. It can take into account models of human bounded rationality and social norms, and crucially, considers a wide variety of possible human goals. We prove how certain desiderata enforce particular functional forms and restrict parameter ranges. We exemplify the consequences of softly maximizing this metric in several paradigmatic situations and describe what instrumental sub-goals it will likely imply.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Science and Game Theory (cs.GT); Multiagent Systems (cs.MA); Theoretical Economics (econ.TH).
Pagina del lavoro: https://arxiv.org/abs/2608.08240 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T06:45:31.709Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).