My PhD project is about ethical behaviour in AI agents. In particular, the idea is that agents that can reason about ethical norms and values will behave in an ethical and responsible way. Therefore, my project focuses on reasoning about ethical norms and values.
Machine ethics isn’t a topic that is researched widely, and the CDT provides an opportunity to do that. But crucially, in the CDT I’m surrounded by people with similar interests about safety and trust. This means that, even though my topic isn’t widely popular (yet), I’m surrounded by people that are interested in what I’m doing. I like the social aspect of the CDT, there is always someone to talk to. I can talk to other people in the CDT about research, personal life and any difficulties that I encounter during my PhD. I think this aspect of the CDT makes the PhD a much better experience. I also like my supervisors a lot. They have been great help and I feel that I can rely on them both academically and otherwise.
To me, the CDT feels like an improved version of a PhD, as in every PhD should be like how the CDT is. I have found the additions to my PhD in the CDT to be extremely useful and I feel that I’m getting a more complete education by being part of the CDT.
Research experience: I did internships in Verification and Quantum Computing at the University of Edinburgh. My honors project during my undergraduate degree was about blameworthiness in agents, which made me interested in the broader field of machine ethics.
Achievements: A paper of mine has been accepted to the EUMAS conference.