Research Scientist, DeepMind
Co-founder, Future of Life Institute
Viktoriya Krakovna is a research scientist in AI safety at DeepMind, and co-founder of the Future of Life Institute. Her PhD thesis in statistics and machine learning at Harvard University focused on building interpretable models. Viktoriya gained numerous distinctions for her accomplishments in math competitions, including a silver medal at the International Mathematical Olympiad and the Elizabeth Lowell Putnam prize.
Special Session: Social Impact of AI – future of AI and society, ethics
【Day 2-5】Safety and Benefits in the Long Term
AI safety: what, why and how?
What is AI safety, why think about it, and how can we build safe AI? In this talk, we will step away from science fiction scenarios towards real problems that need to be solved – teaching artificial agents about core human values and giving them good incentives to follow those values. We will discuss the history of the AI safety field, the current state of research, the key problems we are working on, and how you can contribute.