Why do you care about AI Existential Safety?

AI has the potential to be profoundly consequential for humanity. That’s why it must be designed and deployed responsibly. If misused or misaligned, the harm it causes could be lasting or deeply destabilizing.

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

I am currently working with my colleagues on an AI impact evaluation resource to support researchers in rigorously assessing the effects of AI interventions. By making randomized controlled trials more efficient and relevant to fast-evolving AI systems, this resource can help researchers surface both beneficial and harmful outcomes of AI. It contributes to AI existential safety by enabling the timely identification of risks before they scale beyond control.