Alexander
Einarsson

PhD student working on AI safety.

Maximizing AI potential means minimizing AI harm.

I am interested identifying and mitigating harm caused by applied artificial intelligence.

I graduated from Amherst College in the Spring of 2019 with a Bachelor of Arts in Computer Science and Mathematics. I enrolled at the PhD program in Computer Science at Northwestern University the same Fall. I am currently being advised by Kris Hammond, and work on several projects as a member of his lab group. I am currently doing research into AI safety. My current projects include minimizing harmful bias in automated patrol management systems and measuring information harm from language models.