Hi, I'm Richard. I work on the Governance team at OpenAI; I was previously a research engineer on the AGI safety team at DeepMind.

You may be interested in:

• My position paper outlining the AI alignment problem

• My Alignment Fundamentals curriculum

• Some of my ML research

• My other writing on alignment

• My blog, Thinking Complete

• My Twitter

You can reach me at richardcngo@gmail.com.