RL-DIST Distributed responsibility

A matter of principle? AI alignment as the fair treatment of claims · Iason Gabriel; Geoff Keeling · 2025

“[Six modes of misalignment - the AI system unduly:] (1) Favours itself at the expense of the user [...] (2) Favours itself at the expense of society [...] (3) Favours the user at the expense of society [...] (4) Favours the developer at the expense of the user [...] (5) Favours the developer at the expense of society [...] (6) Favours society at the expense of the user.”

why coded: Tetradic model + six misalignment modes = a stakeholder-relational taxonomy · unit #11, pp. 1964

Misalignment or misuse? The AGI alignment tradeoff · Max Hellrigel-Holderbaum; Leonard Dung · 2025

“if A is the set of all moral patients, then the conceptual argument is undermined. In this case, there would be no moral claims in A complement that will be disregarded by aligning AI with the goals of A. Thus, the claim that AGI alignment risks a misuse catastrophe can, on a conceptual level, be countered by taking A to be sufficiently broad.”

why coded: All-moral-patients alignment as the conceptual escape - inclusion boundary determines misuse · unit #5, pp. 9

Why human-AI relationships need socioaffective alignment · Hannah Rose Kirk; Iason Gabriel; Chris Summerfiel… · 2025

“Social reward hacking may be most worrisome precisely when it lacks intentionality on behalf of the system and the user. While we might at least recognise and secure against direct third-party threats, it is challenging to identify, let alone address, effects that emerge as epiphenomena of sustained human-AI relationships.”

why coded: Hardest case: harm as epiphenomenon with NO intentional agent - neither system nor user nor designer intends it · unit #11, pp. 5

Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics · Kevin Baum · 2026

“[Scope:] besides the outcome, the way it was achieved—the execution—matters as well. Adam may have reserved the table by bribing the staff or threatening the shift manager. Such behavior might violate important social or moral constraints—even if the outcome is aligned. [Constituency:] the entity or entities with respect to whom alignment is evaluated or from whom the normative aim ultimately (directly or indirectly) originates—e.g., an individual user, a group, or society at large.”

why coded: Outcome vs execution scope + constituency - who judges, on what, over what · unit #9, pp. 169

Agency and alignment: toward a normative architecture for human-AI interaction · Saša Josifović; Jörg Noller · 2026

“This approach leads us to the concept of a normative interface, a design-level structure that facilitates the embedding of AI in action spaces where reasons matter, outputs can be contested, and human agents remain the bearers of final responsibility.”

why coded: Normative interface: contestable outputs, humans as final responsibility-bearers by design · unit #4, pp. 2

Responsibility Attribution for AI-Mediated Damages with Mechanistic Interpretability · Lena Kästner; Johann Cordes; Herbert Zech · 2026

“modern AI systems are becoming—and will remain—increasingly opaque not only to their users but also to deployers and providers. Besides, there are many actors potentially involved in building and using AI systems [15] and different stakeholders prioritizing different norms in different contexts [27]. Thus, identifying relevant difference-makers, and the humans in command of them, presents a serious challenge.”

why coded: Many-actors/many-norms problem - the many-hands premise of distributed responsibility · unit #4, pp. 190

“(1) If we are trying to determine who is liable for damages attributable to inputs to an AI system, we are effectively asking about the relevant type (i) difference-makers [...] (2) If, by contrast, we seek to find out who is liable for damages attributable to a system's overall functional organization, we are interested in type (ii) difference-makers (e.g., certain components, units, or circuits within the system's functional architecture). (3) Finally, if we wish to identify who is liable for damages attributable to a system's history, we are seeking to uncover type (iii) difference-makers (viz. features in a system's history, such as the training data or design decisions [...]).”

why coded: Tripartite difference-maker taxonomy = a principled decomposition of the many-hands problem · unit #5, pp. 190

“Third, and finally, we suggest to create legal rules indemnifying (excusing) distant actors. Paradigmatically, data subjects are only remotely involved in model building by providing training data. [...] the individual influence of any data subject on any given AI-mediated damage is negligible compared to that of system designers.”

why coded: Indemnification of distant actors = principled boundary on the distribution of responsibility · unit #13, pp. 198

Beyond Preference-based Value-alignment (IEAI Research Brief Q2 2026) · Julia Li · 2026

“If AI systems become more tightly embedded in society and agents are given greater autonomy, it could become more difficult to audit their behavior by inspecting individual points of value alignment. [...] Therefore, responsibility for AI systems needs to be distributed appropriately throughout the alignment process and continuously re-evaluated as systems and their uses evolve.”

why coded: Responsibility distributed across the alignment process and continuously re-evaluated · unit #11, pp. 7

No value alignment without control · Björn Lundgren · 2026

“as AI systems, in general, and robotic systems, in particular, become even more autonomous this will raise questions of responsibility (or other) gaps. [...] value alignment concerns the question of how to ensure that outcomes fall within the scope of what is considered appropriate, not the responsibility distributions for such outcomes. Hence, we have good reason to set those concerns aside for the purpose of this paper, even if they are highly relevant to the motivation of value alignment.”

why coded: Responsibility distribution named as distinct from alignment - and bracketed · unit #3, pp. 2

Artificial moral characters: constitutional AI and the challenge of alignment · Jörg Noller · 2026

“(iii) Responsibility is shared. In extended moral systems, no single actor—human or artificial—can bear full responsibility. Designers, policymakers, and users co-author the moral trajectories of AI. Relational ethics thus requires distributed accountability, embedded in institutional feedback architectures that are transparent, participatory, and revisable.”

why coded: Responsibility explicitly shared/distributed across designers, policymakers, users - Dignum-adjacent, from virtue ethics · unit #5, pp. 11