This repo is for the AI Alignment for Open Source Working Group
What is AI Alignment? AI alignment is the effort to design AI systems so that their goals, behaviors, and decisions are consistent with human values. AAI alignment is one area of work within the broader AI safety domain.
Our working group focuses on AI alignment for open source communities - specifically, on metrics that help evaluate how well AI systems understand and respect what open source communities have built, what we know, what we value, and what we expect from AI systems that depend on our projects and participate in our spaces.
Please see the CONTRIBUTING.md file for more information on how to participate and contribute.
Please add other relevant resources as you come across them.
- AI Alignment (Wikipedia definition)
- What is AI Alignment?
- Alignment with who? How AI safety can build on open source scaffolding
- Exploring AI ethics in global contexts: a culturally responsive, psychologically realist approach
- OECD Principal 6 Respect for the rule of law, human rights and democratic values, including fairness and privacy (Principle 1.2)