concept
active
concept:interpersonal-utility-comparisonInterpersonal Utility Comparison
The problem of comparing welfare across agents with different utility functions, relevant to assessing preference-strength super-beneficiaries
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Von Neumann-Morgenstern Utility Theoryassociated_withUsed to analyze preference strength; utility functions unique only up to affine transformations, complicating interpersonal comparison
Concepts (1)
concept
- Preference Strengthassociated_withThe problematic possibility of digital minds with superhumanly strong preferences requiring interpersonal utility comparison frameworks
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.
- Key element for alignment faking: model's pre-existing preferences contradict the new training objective
- Economic framework for decision-making under risk.
- Novel task asking which of two sentences received a stronger injection, using matched-pairs design to control for positional bias
- Spearman ρ measuring rank-order agreement between logit-based self-report and probe score; the paper's primary monotonic association metric
- Rhetorical question highlighting the superiority of the Shiratori plan over conventional high-rise.
- Replaces explicit reward signal in active inference; encodes agent's preferred observations independent of environment.
- A person is more profitably considered an imputation rather than a substantial and enduring entity.concept0.708Load-bearing Buddhist philosophical assertion; Kapstein reference; captures core self-illusion doctrine.
- Alexander's method of spending 2-3 hours daily for twenty years comparing pairs of artifacts and buildings, asking which has more life, and identifying structural features correlating with greater wholeness