Why do you care about AI Existential Safety?

I am concerned about AI existential safety since the possible consequences of powerful AI on society are significant. Ensuring that AI systems are compatible with human values and safety is critical for avoiding unanticipated effects that could harm people or society at large. To maximize the benefits of AI while reducing the risks, we must carefully steer its development.

Please give at least one example of your research interests related to AI existential safety:

Under the evaluating the impact of AI on Poverty, Health, Energy and Climate SDGs call of FLI, I am awarded to work on the Impact of AI on Health, specifically on maternal and newborn health in Sub-Saharan Africa context.