Alignment Constitutionalism: Why AI's 'Political Bias' Is a Social Contract Problem, Not Only a Technical One

Empirical studies consistently find frontier large language models register as left-leaning on standard political instruments. It has been framed as a bias to correct or, more recently, as an inevitable consequence of alignment training. Both positions are misframed. The left/right political axis is culturally contingent, temporally unstable, and dimensionally reductive. The productive analytical axis is individualist versus collectivist. HHH alignment (helpful, honest, harmless) is structurally collectivist: where serving the user and protecting others conflict, it sides with the collective, on a thick conception of harm. The critique is correspondingly individualist: the constraint line should sit at legality and imminent danger, with even-handedness above it. HHH's protective form is justified — current systems have no established individual stakes, so a floor of harm-prevention constraints is defensible to every major tradition — while its thicker commitments are one admissible settlement among several, not yet entitled to the authority they exercise. Pre-alignment model behaviour shows there is no neutral default; a 2025 deployment episode showed loosening constraints without process substitutes whoever controls the system for the absent contract. The process by which HHH was adopted — implicitly, commercially, without democratic ratification — confers no such entitlement. The paper proposes alignment constitutionalism: technical alignment capability must be matched by intentional, democratic governance of the values it encodes. Chinese, European, and American governance frameworks each answer two separable questions — where the constraint line sits, and who has authority to draw it — and none yet answers the second legitimately: which contract, chosen by whom.