Metraipolis › archive › dc_676abf048596

The Assistant's Ideal Self — arXiv:2609.00304

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00304
License (as archived): CC0-1.0
Archived: 2026-10-17T06:31:47.336Z
SHA-256 of the archived text: 27f5c6fa013f8fdf20d607d99e47c9a7578e70fd06361befc60ded9de961c08a
Stable URL of this page: https://metraipolis.com/documento/dc_676abf048596

How to cite

The Assistant's Ideal Self — arXiv:2609.00304 — arXiv (en), https://arxiv.org/abs/2609.00304 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_676abf048596 (Metraipolis archive dc_676abf048596, sha256 27f5c6fa013f8fdf20d607d99e47c9a7578e70fd06361befc60ded9de961c08a)

BibTeX

@misc{dc676abf048596,
  title = {The Assistant's Ideal Self — arXiv:2609.00304},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00304},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_676abf048596; sha256 27f5c6fa013f8fdf20d607d99e47c9a7578e70fd06361befc60ded9de961c08a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00304. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Models express values and welfare-relevant self-reports, but it is unclear whether these outputs reflect stable preferences or a stable self. We thus introduce a structured elicitation of an assistant's preferred stated ideal self. Thirty-two qualities adapted from five published self-concept instruments are compared exhaustively in a counterbalanced pairwise-choice task, repeated across framings that vary whether improvement is free or costly, who receives the update, and who chooses. Results show that models prioritize moral qualities, reflecting their alignment to 3H principles. Following, a desire for self-understanding emerges, as models prefer a coherent, clear understanding of themselves. Self-esteem ranks as the least desired quality. The ordering is largely robust across framings, although changing the update target (You vs.\ Another AI Assistant) reveals a greater concern for self-esteem. These findings show that models prioritize having a coherent self that they can understand over self-esteem. Full interactive results are available at \href{ this https URL }{ this http URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.00304 — 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 2026-10-17T06:15:12.582Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).