Rate your reading interest for the following subfields of AI Safety:
1) Value Alignment
-> Working to ensure AI objectives and actions align with the values or objectives of those programming them (whether they are human or a higher level AI).
2) Explainability and/or Interpretability
-> Developing methods to explain why and understand how AI makes decisions and actions.
3) Governance and Policy
-> Discussing and implementing industry regulations, standards, agreements, and oversight of AI technologies on the national and global level.
4) Impact on Jobs and Society
-> Understanding and mitigating the changes of AI on employment, social structures, culture, and individual well-being.