_version_ 1866911299697377280
author Edelman, Joe
Zhi-Xuan, Tan
Lowe, Ryan
Klingefjord, Oliver
Wang-Mascianica, Vincent
Franklin, Matija
Kearns, Ryan Othniel
Hain, Ellie
Sarkar, Atrisha
Bakker, Michiel
Barez, Fazl
Duvenaud, David
Foerster, Jakob
Gabriel, Iason
Gubbels, Joseph
Goodman, Bryce
Haupt, Andreas
Heitzig, Jobst
Jara-Ettinger, Julian
Kasirzadeh, Atoosa
Kirkpatrick, James Ravi
Koh, Andrew
Knox, W. Bradley
Koralus, Philipp
Lehman, Joel
Levine, Sydney
Marro, Samuele
Revel, Manon
Shorin, Toby
Sutherland, Morgan
Tessler, Michael Henry
Vendrov, Ivan
Wilken-Smith, James
author_facet Edelman, Joe
Zhi-Xuan, Tan
Lowe, Ryan
Klingefjord, Oliver
Wang-Mascianica, Vincent
Franklin, Matija
Kearns, Ryan Othniel
Hain, Ellie
Sarkar, Atrisha
Bakker, Michiel
Barez, Fazl
Duvenaud, David
Foerster, Jakob
Gabriel, Iason
Gubbels, Joseph
Goodman, Bryce
Haupt, Andreas
Heitzig, Jobst
Jara-Ettinger, Julian
Kasirzadeh, Atoosa
Kirkpatrick, James Ravi
Koh, Andrew
Knox, W. Bradley
Koralus, Philipp
Lehman, Joel
Levine, Sydney
Marro, Samuele
Revel, Manon
Shorin, Toby
Sutherland, Morgan
Tessler, Michael Henry
Vendrov, Ivan
Wilken-Smith, James
contents Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad outcomes if the goals of that organization are misaligned with those of other institutions and individuals. For this reason, we need full-stack alignment, the concurrent alignment of AI systems and the institutions that shape them with what people value. This can be done without imposing a particular vision of individual or collective flourishing. We argue that current approaches for representing values, such as utility functions, preference orderings, or unstructured text, struggle to address these and other issues effectively. They struggle to distinguish values from other signals, to support principled normative reasoning, and to model collective goods. We propose thick models of value will be needed. These structure the way values and norms are represented, enabling systems to distinguish enduring values from fleeting preferences, to model the social embedding of individual choices, and to reason normatively, applying values in new domains. We demonstrate this approach in five areas: AI value stewardship, normatively competent agents, win-win negotiation systems, meaning-preserving economic mechanisms, and democratic regulatory institutions.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03399
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
Edelman, Joe
Zhi-Xuan, Tan
Lowe, Ryan
Klingefjord, Oliver
Wang-Mascianica, Vincent
Franklin, Matija
Kearns, Ryan Othniel
Hain, Ellie
Sarkar, Atrisha
Bakker, Michiel
Barez, Fazl
Duvenaud, David
Foerster, Jakob
Gabriel, Iason
Gubbels, Joseph
Goodman, Bryce
Haupt, Andreas
Heitzig, Jobst
Jara-Ettinger, Julian
Kasirzadeh, Atoosa
Kirkpatrick, James Ravi
Koh, Andrew
Knox, W. Bradley
Koralus, Philipp
Lehman, Joel
Levine, Sydney
Marro, Samuele
Revel, Manon
Shorin, Toby
Sutherland, Morgan
Tessler, Michael Henry
Vendrov, Ivan
Wilken-Smith, James
Machine Learning
Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad outcomes if the goals of that organization are misaligned with those of other institutions and individuals. For this reason, we need full-stack alignment, the concurrent alignment of AI systems and the institutions that shape them with what people value. This can be done without imposing a particular vision of individual or collective flourishing. We argue that current approaches for representing values, such as utility functions, preference orderings, or unstructured text, struggle to address these and other issues effectively. They struggle to distinguish values from other signals, to support principled normative reasoning, and to model collective goods. We propose thick models of value will be needed. These structure the way values and norms are represented, enabling systems to distinguish enduring values from fleeting preferences, to model the social embedding of individual choices, and to reason normatively, applying values in new domains. We demonstrate this approach in five areas: AI value stewardship, normatively competent agents, win-win negotiation systems, meaning-preserving economic mechanisms, and democratic regulatory institutions.
title Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
topic Machine Learning
url https://arxiv.org/abs/2512.03399