Joel Artturi Saarinen

I’m a PhD candidate in Logic at the IRIT in Toulouse, supervised by Dr. Emiliano Lorini. My research aims to ensure that intelligent systems are aligned with human intent and values, specifically through attempting to provide safety guarantees in multi-agent settings. My previous background is a mix of cognitive science, philosophy, and mathematical logic, which have accordingly caused me to take a more neurosymbolic approach. I wrote my masters thesis on extended impossibility results about Solomonoff Induction. See my white paper for a more detailed statement about my work and its aims more generally, and my CV for more formal qualifications.

​​

Outside of my academic work, I enjoy mixed martial arts and gardening. Indeed, I dream one day of running a self-sustaining farm community with my best friends, preferably somewhere in the foothills of the Alps. 

​

I don't really maintain it anymore, but I have some older, philosophical essays on Negative Spaces.