This is a linkpost for https://medium.com/@miad/keeping-ai-safe-and-beneficial-for-humanity-4d0416300dfa
I was interviewed by Mia Dand about the Center for Human-Compatible AI (CHAI) and our approach to AI safety and alignment. This is a link post for the write-up of our conversation. It's aimed at a broad audience who may not be familiar with AI safety concerns, but it might be of interest to people here to learn more about CHAI.