Joao is reading for a DPhil in philosophy at St Cross College. His research focuses on analysing possible severe long-term risks(e.g. existential risks) of moral enhancement, and thus finding out safe paths for performing it. Could there be a slippery slope effect where one small improvement in our morality would necessarily lead to many other unwanted changes? Is just one simple straightforward improvement in morality(e.g. increasing cooperation) safe? Could we create a future without moral value by performing many iterations of moral enhancement? Moreover, and to help answer those questions, he is also looking into social simulations as a way of modelling the spread of moral enhancement. Joao has done a MPhil and undergrad degree in philosophy at University of Sao Paulo and did research in 2-D semantics, cognitive enhancement, cognitive bias, trolley problems and experimental psychology.