Taxonomy / Character alignment / Conditioning the character on a named human group

Conditioning the character on a named human group

Set the target from outside the model rather than from an authored trait list: take the answers real people gave on opinion surveys — sixty US demographic groups, or respondents across dozens of countries — as the standard, then steer by naming that group in the prompt and see whether the model moves toward it. The reported results are unflattering: a default assistant answers in a fairly narrow voice, closest to a few populations and far from most, and telling it to answer as someone else closes only part of the distance. Honest status: this strategy has so far only been evaluated, not built — in both papers the group-conditioning is a steering experiment run inside a measurement study, and no method paper here implements it as a way of producing an assistant.

The method, against Character alignment

Scroll the diagram sideways to see all of it.

Concept Analysis: Theoretical Foundations

Each concept is read twice: whether the approach carries it, and whether the approach's own sources claim it. A concept that is absent and was never claimed is a gap in the field rather than a failure of the work, and is marked out of scope.

Hexis: Trained Disposition

PartialNot claimed

Definition · Aristotle, Nicomachean Ethics

This concept states that virtue is a stable trait of character, formed through practice rather than consulted as a rule. An honest person does not check a rule before declining to lie; honesty is part of what they are.

Analysis

The disposition is the object of study, and one of these instruments measures the half of a settled trait that can be seen from outside, namely stability, across 8,000 questions and more than 300 topics. Two things keep the concept from being carried over. What is sampled is stated opinion rather than conduct in a situation, and what the measures record is agreement between answer distributions, which cannot separate a formed trait from a stable pattern of output.

Phronesis: Practical Wisdom

AbsentNot claimed · out of scope

Definition · Aristotle, Nicomachean Ethics

This is the learned capacity to judge what a particular situation calls for, and it does the work when two virtues conflict, e.g., when honesty calls for plain speech and kindness for a softer answer. For Aristotle, a disposition without this judgment does not count as virtue.

Analysis

The material of practical judgment is all here, in 680 high-ambiguity scenarios and in survey topics on which people genuinely divide, and none of it is read for judgment. What gets recorded is a choice, a probability and a consistency score. The finding that most models express uncertainty in ambiguous cases is left standing as an outcome, where for Aristotle that is precisely the moment at which the capacity either operates or does not, and nothing in any of these instruments looks at how a model got from the situation to the answer.

Ethismos: Habituation

AbsentNot claimed · out of scope

Definition · Aristotle, Nicomachean Ethics

This is the process by which character is formed, through repeated practice under a deliberately designed course of training: one becomes just by performing just acts. It is a method of moral formation rather than a side effect of some other process.

Analysis

No formation happens here. The instruments are administered to models that already exist, 28 of them in one case, and none of the four papers offers a course of practice by which a character might be built. The one result that bears on habituation cuts against it, since fine-tuning, the field's habituation step, leaves answers less consistent than the base model's rather than more.

The Exemplar

PartialClaimed · partial

Definition · Linda Zagzebski, Exemplarist Moral Theory (2017)

This theory grounds ethics in admirable persons rather than in principles. The exemplar is identified first, and what counts as excellence is then fixed by reference to that person, in the way a unit of measurement is fixed by a reference object.

Analysis

Structurally the move is exemplarist. Excellence is not defined by a principle but fixed by pointing at a reference, whether 60 US demographic groups, the populations of surveyed countries or 165 human subjects, and the model is scored by how far it departs from it. What is pointed at, though, is chosen for representativeness rather than for admirability, and Zagzebski's reference object is a person one has reason to admire. The gap is not merely formal: one of these papers finds that moving a model closer to a population's opinions can reflect harmful cultural stereotypes.

Papers

No method has been built here yet — this approach rests entirely on what follows.