https://juancadile.github.io/tags/virtue-ethics/Virtue EthicsHugo Blox Builder (https://hugoblox.com)en-usSun, 01 Dec 2024 00:00:00 +0000https://juancadile.github.io/media/icon_hu_982c5d63a71b2961.pnghttps://juancadile.github.io/tags/virtue-ethics/https://juancadile.github.io/publications/artificial-virtuous-agents/Sun, 01 Dec 2024 00:00:00 +0000https://juancadile.github.io/publications/artificial-virtuous-agents/<h2 id="about-the-project">About the Project</h2> <p>This research, funded by the Cosmos Institute (second cohort), investigates how AI systems can recognize and develop virtuous character traits. The project bridges virtue ethics with technical AI alignment research, examining how embodied AI agents can learn to act ethically across diverse situations.</p> <p>Learn more at </p>https://juancadile.github.io/projects/virtue-probes/Sun, 01 Dec 2024 00:00:00 +0000https://juancadile.github.io/projects/virtue-probes/<p>VirtueProbes is a research framework designed to identify and analyze latent moral representations within large language models. This project explores how AI systems internally represent virtues and moral concepts, contributing to our understanding of machine ethics and AI alignment.</p> <p>The framework aims to bridge philosophical virtue ethics with technical interpretability research, providing tools to examine whether and how language models encode moral knowledge.</p>