Marek Masiak

Marek is a DPhil student in the Fundamentals of AI CDT programme at Oxford. His research focuses on mechanistic interpretability, AI safety and the training dynamics of neural networks, increasingly through the lens of developmental interpretability. He believes that AI has the potential to do an enormous amount of good by accelerating scientific discovery and that interpretability will play a major role in this. He is concerned about risks from deliberate misuse of AI, loss of control, biorisks and gradual disempowerment.