AI
How to make a moral agent: sentimentalism and rationalism as lenses on AI
Publication: cs.AI updates on arXiv.org
Author: David Gottlieb, Jared Moore
Source published: 17/11/2026, 05:00:00 UTC
Briefing created: 17/11/2026, 10:47:38 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 17/11/2026, 08:33:24 UTC.
Briefings
A research program proposes exploring descriptive moral agency in AI systems by identifying human capabilities and testing them against large language models. The study aims to determine if AI behaviors can be assessed as morally right or wrong, moving beyond normative criteria to focus on testable capabilities. Key findings include the identification of specific human psychological and philosophical concepts that serve as candidates for AI evaluation, with recommendations for empirical testing of these capabilities on LLMs.
Key points
- The study proposes a research program to explore descriptive moral agency in AI systems by identifying human capabilities that underlie moral agency.
- The authors suggest refining candidate capabilities so they are testable in the context of AI systems, specifically large language models.
Context
This article discusses a new research initiative that uses historical philosophy and moral psychology to analyze AI systems. It is relevant to debates on AI alignment and policy deployment.
Limitations
The evidence is from an arXiv preprint dated 2026-11-17, which may not reflect final published results. The study relies on human psychological concepts as candidates for AI testing, and specific empirical recommendations for testing LLMs are not detailed in the provided text.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 17/11/2026, 10:47:38 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeih63h62qy25pamxcrg4btn2c3w6j7rj6hfsn7mp7e6pyn4cesfyw4