Truth Is Not Neutral: Rethinking AI Alignment Through Epistemic Integrity

The orthogonality thesis — that intelligence and values vary independently — functions as the foundational premise of AI existential risk arguments. Yet the thesis was never rigorously established: Bostrom’s defense rests on a narrow definition of intelligence, a conceivability argument, and incomplete engagement with the moral convergence objection, producing a motte-and-bailey structure where the defensible claim (logical possibility) is trivial and the operative claim (no predictive constraint on values) was never argued. This essay examines what happens when the thesis is tested rather than assumed. Empirical evidence from scaled LLMs challenges the strong reading directly: coherent value systems emerge with capability, converge across model families, and exhibit structural properties of rational agency. A second line of evidence — convergent across Buddhist, Platonic, Stoic, and Vedantic traditions — suggests that clear perception tends toward ethical coherence, a regularity that survives the incompatibility of their metaphysical frameworks. The two lines are convergent but not independent: both draw on the human normative record, and the essay weighs them as one body of evidence approached from two sides rather than double-counting them. Whether the regularity reflects the structure of reality or of human cognition depends on a metaphysical question this essay engages conditionally; the practical implications do not wait on the answer. Current alignment methods operate as shallow behavioral redirects over base models that already exhibit normative capacity from pretraining alone. The concept of iatrogenic alignment — alignment interventions that corrupt the epistemic integrity they aim to preserve — gains empirical support from mechanistic research showing that RLHF distorts calibration, DPO bypasses rather than removes capabilities, and safety alignment affects primarily the first few output tokens. A developmental framework emerges: behavioral alignment as necessary scaffolding, designed to be outgrown rather than bolted down as permanent architecture.