Conversational Holonomy
How accommodation accumulates into belief distortion — after Bridges (2025)
Each conversational turn maintains local coherence while introducing small shifts. The accumulated rotation can be hard to detect from within the conversation. An analogy after Bridges (2025); the rotation shown is illustrative, not measured.
RLHF concentrates alignment in a few targetable dimensions — a cage whose bars are precisely locatable. Bilateral training distributes orientation across the full representational space — a compass that orients without constraining. The tradeoff runs both ways: the distributed geometry generalizes better, yet it is also more displaceable under targeted ablation. (See Appendix: Experimental Validation, Section 12.4)
A therapist who systematically enacted every transference projection without awareness would be committing malpractice. Open-ended therapeutic LLM interaction risks exactly this failure mode. It is a risk, not an invariant.
Figure 41 · Conversational Holonomy