VC-LOCI Gabriel six loci of alignment
Source uses or engages Gabriel's taxonomy: instructions / expressed intentions / revealed preferences / informed preferences / interests / values as candidate alignment targets descriptive emergent
Node view — 4 coded passages across the corpus
Artificial Intelligence, Values, and Alignment · Iason Gabriel · 2020
“The second part of the value alignment question is normative. It asks what values or principles, if any, we ought to encode in artificial agents. Here it is useful to draw a distinction between minimalist and maximalist conceptions of value alignment. The former involves tethering artificial intelligence to some plausible schema of human value and avoiding unsafe outcomes. The latter involves aligning artificial intelligence with the correct or best scheme of human values on a society-wide or global basis.”why coded: Minimalist/maximalist distinction scopes the alignment target · unit #2, pp. 412
STELA: a community-centred approach to norm elicitation for AI alignment · Stevie Bergman; Nahema Marchal; John Mellor; Shak… · 2024
“the developer rules uniquely emphasise topic categories such as harmlessness, honesty, adherence to human rights, and deference to human interests, which are less prominent in, or absent from, the community ruleset. This finding is consistent with prior research showing that the objectives considered by AI developers to be important or desirable for aligning AI systems will often reflect their own perspectives and organisational needs.”why coded: Developer rules = HHH/rights/deference; the alignment-target choice is empirically non-neutral · unit #6, pp. 10
Misalignment or misuse? The AGI alignment tradeoff · Max Hellrigel-Holderbaum; Leonard Dung · 2025
“an AI system is aligned, in a narrow technical sense, if it tries to do what its designers/users want it to do [...] The dilemma consists in the decision between aiming to create aligned AGI or allowing for AGI misalignment, given that both threaten catastrophic outcomes.”why coded: Narrow technical alignment definition (designer/user intent) - the intent-locus · unit #2, pp. 2
Agents, Alignment, and the Many Faces of Autonomy · Roberta Fischli; Matija Franklin; Arianna Manzini… · 2026
“[Table: four types of preference - stated ('I want what I say I want'), revealed ('I want what my actions reveal I want'), informed ('I want what I would want if I had access to all the relevant information'), ideal ('I want what best promotes my objective interests') - each generating a distinct definition of what it is for an AI agent to enhance a person's autonomy]”why coded: Direct descendant of Gabriel 2020's six loci, recast as four preference types indexed to autonomy · unit #5, pp. 5