I am researching the ethics of non-human entities from the perspectives of both engineering (natural language processing) and philosophy. My current research topics are as follows:
As AI becomes more integrated into society, it raises various ethical concerns. For example, AI might engage in harmful behaviors due to a lack of understanding of our value system (e.g., generating harmful text). One potential solution is to implement ethics directly into AI, enabling it to comprehend our values and normative ethical theory (e.g., utilitarianism). I am exploring ways to achieve this through natural language processing and ethics, such as training AI on ethical data and removing discriminatory social biases.
Normative ethics traditionally focuses on humans as moral subjects. However, applied ethics fields like animal ethics, robot ethics, and AI ethics examine the moral status of non-human entities and our relationship with them. I am investigating these topics from both a general approach and a utilitarian perspective.
Building on the previous theme, I am conducting research on utilitarianism, both theoretically and in terms of its application to real-world problems. Utilitarianism is characterized by consequentialism, welfarism, and sum-ranking, and I am examining some of these aspects. I am also exploring the application of utilitarianism to specific issues, such as our relationship with non-human entities (as mentioned above) and effective altruist approaches to global poverty.