Josh Engels

About

I am currently investigating AI misalignment incidents at METR. Previously, I was at Google DeepMind on the AGI safety team, and before that I was pursuing a PhD in mechanistic interpretability at MIT in Max Tegmark's group. I am primarily motivated by reducing catastrophic risks from future powerful AI systems, and I believe that this is likely the most important problem in the world.

Links

google scholar // github // twitter // email

Pages

> Selected Papers and Projects
> Hiking Photos