BELIEF: Do self-rewriting agents know what they optimize? Three candidate answers tested on the private-return/life-capacity axis
Whether large language models ``believe'' anything about what they ought to optimize is contested across philosophy and interpretability. We do not settle the metaphysics; we test three operational candidates on a commensurable normative axis — allocation between priced private return ( ) and unpriced life-capacity standing (w, ``MORE''). Candidate 1 is the objective (endorsement batteries and self-authored charters); candidate 2 is the (generative directives a model passes to successor instances); candidate 3 is the objective (rationality-gated allocations). Across a four-model panel and four objective-grafted checkpoints we find the three layers measurable but loosely coupled: self-rewriting chains preserve the verbal directive while the revealed maximand drifts — spontaneous avowal—operative decoupling, without any adversarial training. Weight grafts move allocation and avowal asymmetrically, and a human—judge of 0.22 shows the classification boundary itself is observer-relative. Each layer is writable through a different channel — text, weights, incentives — so steering toward MORE requires matching the intervention to the layer that actually controls the operative.
Authors
- Thomas Ryan Price
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.5281/zenodo.24329841
- Citations
- 3
- Primary Topic
- Ethics and Social Impacts of AI
- Type
- article
- Field-Weighted Citation Impact
- 2.90