New paper 'Inter-AI Morality' studies how AI systems treat one another
jacyanthis · x · 2026-11-07
Lucius Caviola, with Caspar Kaiser, Carter Allen, and Jeff Sebo, released a new paper, Inter-AI Morality: How AI Systems Treat One Another.
- Most AI-and-morality research covers how humans should treat AI or how AI should treat humans.
- The paper highlights a neglected quadrant: AI systems increasingly interact with each other (agent-to-agent trading, negotiation, collaboration), yet how AIs treat other AIs is almost unstudied.
- An accompanying diagram maps the field as a moral-agent × moral-patient matrix: moral psychology, AI welfare, AI safety, and the new field of inter-AI morality.
An emerging research agenda for agent ethics.
Related event: Scholars Propose Research Agenda for Inter-AI Morality(2 posts)→
More from AGI Musings
- tszzl: Nature destroyed itself five times — stop reading morality into it — tszzl · 2026-11-07
- Vitalik Buterin: 'Open weight is not open source' on AI models — wonderwomancode · 2026-11-07
- Analyst predicts China AI consolidation: DeepSeek talent drain leads to 'two big, two small' endgame — teortaxesTex · 2026-11-07
- Mira Murati: Next-gen models never stop listening, chatbots will look like fax machines — Chris_Armstrong · 2026-11-07
- Gary Marcus echoes claim that AI tech hit its limits years ago and will fizzle out — GaryMarcus · 2026-11-07
- Google exec: the race for best AI is irrelevant, scaling affordable access is what matters — docmilanfar · 2026-11-07