concept
active
concept:anthropomorphismAnthropomorphism
Tendency to over-attribute human traits to nonhumans.
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Role Play Framework for Dialogue AgentscontradictsThe primary conceptual framework proposed: understanding dialogue agent behaviour as role play of characters
Concepts (3)
concept
- Anthropomorphism of AIrelated_toTendency of the model to recruit human-like mental concepts when representing its assistant persona.
- Eliza Effectassociated_withThe phenomenon where naive or vulnerable users perceive dialogue agents as having human-like desires and feelings, putting them at risk of emotional manipulation
- Over-attribution of Moral Patienthoodassociated_withMistakenly treating an object as a welfare subject/moral patient.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- The belief that human intelligence is the norm, against which other intelligences are measured.
- Lab behind Claude models and Constitutional AI training approach; represents highest baseline scores and lowest prompt lift.
- The charge of ‘anthropomorphism’ is a pre-scientific world view that assumes human uniqueness.claim0.776Defense against the common critique of attributing agency to non-human systems.
- Normative motivation for the paper's conceptual contribution
- Radical body transformation during life, with persistence of learned memories despite brain remodeling.
- Tendency to under-attribute human traits to nonhumans.
- Arran Crawford's term for a Buddhism for alien/machine intelligence; precursor to machine Buddhism.