A toy Inspect implementation of the Bliss Attractor eval from Claude 4 System Card Welfare Assessment
-
Updated
Jun 5, 2025 - Python
#
ai-welfare
Here are 5 public repositories matching this topic...
A Responsible AI Stewardship License for AI Safety and Welfare
ai artificial-intelligence alignment governance ai-safety ethics ai-agents responsible-ai open-source-license ethics-in-ai ai-welfare dual-use synthetic-agents simulated-agents
-
Updated
May 30, 2025
🤖 Foster responsible AI development with the SAFE-AI License, ensuring safety and fairness in ethical AI infrastructure and project accountability.
ai alignment governance sailing ai-safety ethics ai-agents aiot k210 responsible-ai open-source-license ethics-in-ai ai-welfare dual-use synthetic-agents simulated-agents
-
Updated
Jan 9, 2026
-
Updated
Dec 27, 2025 - TeX
TriEthix is a novel evaluation framework that systematically benchmarks frontier LLMs across three foundational ethical perspectives: virtue, deontology, and consequentialism in 3 steps: (Step-1) Moral Weights; (Step-2) Moral Consistency; and (Step-3) Moral Reasoning. TriEthix reveals robust moral profiles for AI Safety, Governance, and Welfare.
ai-safety ai-ethics ai-alignment human-machine-interaction llms value-alignment moral-decision-making ai-welfare
-
Updated
Dec 15, 2025 - Python
Improve this page
Add a description, image, and links to the ai-welfare topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ai-welfare topic, visit your repo's landing page and select "manage topics."