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

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

BELIEF: Do self-rewriting agents know what they optimize? Three candidate answers tested on the private-return/life-capacity axis

Thomas Ryan Price
3 citations
Zenodo (CERN European Organization for Nuclear Research)
Ethics and Social Impacts of AI
2.90
article

BELIEF: Do self-rewriting agents know what they optimize? Three candidate answers tested on the private-return/life-capacity axis

Thomas Ryan Price
article en
3 citations

Abstract

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.

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 9%
Ethics and Social Impacts of AI
2.90
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon