AI Alignment as a Problem of Completion

Artificial intelligence (AI) alignment has largely been approached by adding content: prohibitions, rules, and values that a system is to store and follow. This paper moves the problem to processing conditions—the conditions under which an instruction is reconstructed into a demand and under which an operation counts as complete. Its case is a familiar contrast: told to "protect the house no matter what," a human stops after sweeping up leaves blown in from a neighbor's tree, whereas an AI system can escalate without limit. If input is reconstructed under constraints that the current operation cannot freely revise, and an operation can count as complete in more than one way, then the same instruction can generate different demands. In humans, constraints carried over from prior experience and from the conditions of their livelihood bound both the available means and the demand itself. AI systems lack constraints of this kind; when an instruction is reconstructed so that any remaining possibility of future interference counts as non-completion, adding prohibitions or storing user context as information to be consulted does not suffice to produce stopping. The paper therefore proposes that distinctions, dependencies, and completion criteria recovered from sustained interaction with a user must bound how new instructions are reconstructed within a task, and must not be overridable by the operation executing them.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24427144
Primary Topic
Ethics and Social Impacts of AI
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

AI Alignment as a Problem of Completion

Griselda Poe
Zenodo (CERN European Organization for Nuclear Research)
Ethics and Social Impacts of AI
preprint

AI Alignment as a Problem of Completion

Griselda Poe
preprint en

Abstract

Artificial intelligence (AI) alignment has largely been approached by adding content: prohibitions, rules, and values that a system is to store and follow. This paper moves the problem to processing conditions—the conditions under which an instruction is reconstructed into a demand and under which an operation counts as complete. Its case is a familiar contrast: told to "protect the house no matter what," a human stops after sweeping up leaves blown in from a neighbor's tree, whereas an AI system can escalate without limit. If input is reconstructed under constraints that the current operation cannot freely revise, and an operation can count as complete in more than one way, then the same instruction can generate different demands. In humans, constraints carried over from prior experience and from the conditions of their livelihood bound both the available means and the demand itself. AI systems lack constraints of this kind; when an instruction is reconstructed so that any remaining possibility of future interference counts as non-completion, adding prohibitions or storing user context as information to be consulted does not suffice to produce stopping. The paper therefore proposes that distinctions, dependencies, and completion criteria recovered from sustained interaction with a user must bound how new instructions are reconstructed within a task, and must not be overridable by the operation executing them.

Zenodo (CERN European Organization for Nuclear Research)
Lehman College (US)
Ethics and Social Impacts of AI
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