Richard Ngo, an independent AI safety researcher and philosopher, is now tracked in Turing Tree. He co-authored The Alignment Problem from a Deep Learning Perspective, which explains how advanced systems trained with modern methods could learn goals that conflict with human intentions.
Ngo also designed the Alignment Fundamentals curriculum used by BlueDot Impact. He previously worked as a research scientist at OpenAI and as a research engineer on Google DeepMind's AGI safety team.