AG-COLLECTIVE Collective/multi-agent effects

Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value · Joe Edelman; Tan Zhi-Xuan; Ryan Lowe; Oliver Klin… · 2025

“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.”

why coded: Operator-intent alignment insufficient at the multi-institution level · unit #1, pp. 1

Agents, Alignment, and the Many Faces of Autonomy · Roberta Fischli; Matija Franklin; Arianna Manzini… · 2026

“Yet, we also need to look at the multi-party question and explore what happens, from the standpoint of collective autonomy, when a large number of people use agents that are aligned to their individual preferences (Hammond et al., 2025). Is it possible that these individual autonomy enhancers will limit the agency of others, or affect the autonomy of a society as a whole in unexpected ways?”

why coded: Multi-party/collective autonomy explicitly deferred · unit #14, pp. 17

“One criterion the current framework does not address is non-domination. Republican accounts of freedom focus on arbitrary interference as a distinct threat to freedom that cannot be reduced to preference satisfaction or capability (Dagger, 2005; Pettit, 2012). [...] Assessing our proposed alignment strategies against the standard of non-domination therefore falls outside the scope of this paper.”

why coded: Republican non-domination deferred - citizens vs users distinction · unit #15, pp. 17