Taxonomy / Constitutionalism / Writing the constitution as a public document

Writing the constitution as a public document

The rules are treated as an artifact in their own right: someone decides which principles go in, how each one is worded, and whose values they encode, and then the text is published so outsiders can read it and hold the lab to it. Claude's Constitution and OpenAI's Model Spec are the two best-known published texts. The rest of the work here aims at the document rather than at any model — choosing and framing the principles before training begins, forcing pairs of principles into conflict to surface contradictions in the writing itself, and running the text against cross-cultural value surveys to see which culture's commitments it quietly carries.

The method, against Constitutionalism

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.

Rule of Recognition

PartialClaimed · partial

Definition · H. L. A. Hart, The Concept of Law (1961)

This meta-rule states which rules count as valid law, and which rule wins when a conflict between two rules emerges. Without it, a mere list of rules does not indicate what is actually binding.

Analysis

The document has an internal hierarchy in which specific provisions override general ones, which is a step toward a rule of recognition. However, when the document itself does not provide guidance on a particular case, or when two provisions at the same level conflict, it is generally unclear what the following hierarchy or procedure is.

Open Texture

AbsentClaimed · unmet

Definition · H. L. A. Hart, The Concept of Law (1961)

This stated procedure governs who and how decides unclear cases at the edges of stated rules, when it’s unclear whether and how it applies to the case at hand.

Analysis

The constitutions generally acknowledge that hard cases exist but do not assign procedure for handling them (i.e., no stated discretion and no designated decider). As a result, borderline cases are resolved by the model.

Principles of Legality

PartialClaimed · partial

Definition · Lon L. Fuller, The Morality of Law (1964)

This set of properties establishes what makes governing by rules legitimate: rules must be public, clear, non-contradictory, stable over time, possible to follow and, crucially, fit “congruence” (i.e., must match how they end up being enforced).

Analysis

Publicity is satisfied, since the constitution documents are publicly released. Congruence, however, is mostly just asserted. When external verification exists, it is generally another AI system (often another instantiation of the same model) judging the adherence of the deployed model with respect to the norms in the constitution. This has many limitations and unknowns: it is not understood what type of interpretation the model employs, whether blind spots or biases of the model in question are merely reinforced when monitored by another instantiation of itself, etc.

Service Conception of Authority

AbsentNot claimed · out of scope

Definition · Joseph Raz, The Morality of Freedom (1986)

This concept states that an authority’s rules deserve deference only if following them helps the governed act on reasons they already have. Authority is a service to the governed, not a power over them.

Analysis

Publication lets users read the rules, but it gives them no say in the rules and no test of whether deference serves them. Transparency is not the same thing as authority being justified.

Papers

Source artifacts

Primary documents and shared infrastructure this approach works from or produces, rather than studies of them.