Viktoria Krakovna is a research scientist at DeepMind. Her research focuses on long-term AI safety, specifically setting good incentives for future advanced AI systems. She is also a co-founder of the Future of Life Institute (FLI), an organization that works on mitigating risks which humanity could face from new technologies.
Viktoria received her PhD from Harvard in statistics and machine learning. She has received numerous awards in mathematics, including a silver medal at the International Mathematical Olympiad and the Elizabeth Lowell Putnam prize.
For Viktoria, improving the world follows naturally from her interest in self-improvement - applying the same skills to something more important than herself. She first learned about effective altruism through an online rationality community called LessWrong and was excited to see other people using rational thinking in order to help others. She already knew that she wanted to use her resources to improve the world, but had been unsure where to start. Finding a community of smart people who are dedicated to making positive changes in the world has helped her to focus on figuring out how she can have an impact.