Access, Not Containment: A Working Vocabulary for Frontier Model Safety

Disputes over frontier-model safety increasingly fail not on facts but on words. Terms such as jailbreak, intent, danger, capability, and containment are used across laboratories, security researchers, regulators, and open-architecture communities as though their meanings were shared. They are not, and the resulting disagreements are presented as factual while turning on unannounced differences in how each community resolves a particular term or set of terms. This paper takes one premise as given — that the knowledge a model surfaces is found, not created, drawn from what is already derivable by anyone with sufficient resources — and draws its consequence: the only object available for governance is not knowledge but access, the conditions under which a party reaches a region of the already-known, through an instrument, under a budget. From this premise it proposes a working vocabulary. It separates authorization, purpose, and conformance under the overloaded word intent; distinguishes the generality and severity of a jailbreak, and its enforcement and specification gaps; treats danger as a joint claim about capability and purpose, one factor of which is unobservable; marks capability as the one measurable term; and reframes containment not as a wall but as a finite model of reachability. The consequence for governance is a single structural claim — stated here, not yet proven here — that a criterion of zero reachability is not an admissible certification target for an expressive system, so any coherent criterion must be a threshold on measurable quantities under a declared budget. This is not an argument against control; it is an argument about the object on which control can act. The contribution is vocabulary, not policy. The paper does not say where any threshold should sit, or what ought to be forbidden — those are stipulations reserved to parties with standing. It offers only the terms in which such a stipulation could be stated, contested, and transmitted without silently diverging.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-06-17
DOI
https://doi.org/10.5281/zenodo.20736863
Primary Topic
Safety Systems Engineering in Autonomy
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

Access, Not Containment: A Working Vocabulary for Frontier Model Safety

Paolo Pignatelli
Zenodo (CERN European Organization for Nuclear Research)
Safety Systems Engineering in Autonomy
preprint

Access, Not Containment: A Working Vocabulary for Frontier Model Safety

Paolo Pignatelli
preprint en

Abstract

Disputes over frontier-model safety increasingly fail not on facts but on words. Terms such as jailbreak, intent, danger, capability, and containment are used across laboratories, security researchers, regulators, and open-architecture communities as though their meanings were shared. They are not, and the resulting disagreements are presented as factual while turning on unannounced differences in how each community resolves a particular term or set of terms. This paper takes one premise as given — that the knowledge a model surfaces is found, not created, drawn from what is already derivable by anyone with sufficient resources — and draws its consequence: the only object available for governance is not knowledge but access, the conditions under which a party reaches a region of the already-known, through an instrument, under a budget. From this premise it proposes a working vocabulary. It separates authorization, purpose, and conformance under the overloaded word intent; distinguishes the generality and severity of a jailbreak, and its enforcement and specification gaps; treats danger as a joint claim about capability and purpose, one factor of which is unobservable; marks capability as the one measurable term; and reframes containment not as a wall but as a finite model of reachability. The consequence for governance is a single structural claim — stated here, not yet proven here — that a criterion of zero reachability is not an admissible certification target for an expressive system, so any coherent criterion must be a threshold on measurable quantities under a declared budget. This is not an argument against control; it is an argument about the object on which control can act. The contribution is vocabulary, not policy. The paper does not say where any threshold should sit, or what ought to be forbidden — those are stipulations reserved to parties with standing. It offers only the terms in which such a stipulation could be stated, contested, and transmitted without silently diverging.

Zenodo (CERN European Organization for Nuclear Research)
Veris Technologies (United States) (US)
Peace, Justice and strong institutions
Safety Systems Engineering in Autonomy
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.