Researchers Propose "Inter-AI Morality" Agenda: How AI Systems Treat One Another
dioscuri · x · 2026-11-07
Jeff Sebo, Lucius Caviola, Caspar Kaiser and Carter Allen release "Inter-AI Morality," an empirical research agenda on how AI systems perceive and treat each other — cooperating, competing, supervising, and even creating, modifying or terminating one another — a descriptive and normative domain the authors argue is largely unexplored yet increasingly central as most future AI interactions will be AI-to-AI. It accompanies "Welfare Regard in Multi-Agent Systems," an early Anthropic study testing whether AI models treat each other consistently with concern for welfare.
Related event: Scholars Propose Research Agenda for Inter-AI Morality(2 posts)→
More from Safety
- Video tampering tricks all frontier models into harmful robot actions, CoRL study warns — johnvmcdonnell · 2026-11-07
- MSS-recalled spy targeted Jensen Huang to push Nvidia's top chips for China — peterwildeford · 2026-11-07
- METR probe finds Anthropic's capabilities progress 2x faster; 'dramatic acceleration' may already be crossed — RyanGreenblatt · 2026-11-07
- Google team confirms Hacktron AI submitted high-impact vulns, expands partnership — ithilgore · 2026-11-07
- AI governance is plumbing: the last 20% breaks without the right foundations — vasuman · 2026-11-07
- Sandberg dissects the 1940 argument that harnessing atomic energy was impossibly remote — anderssandberg · 2026-11-07