Evan Hubinger discusses some of the different proposals for building safe advanced AI that are currently actively being researched at OpenAI and DeepMind. Asya Bergal then discusses some recent updates on AI safety work she's excited about.

In the future, may to post a transcript for this talk, but we haven't created one yet. If you'd like to create a transcript for this talk, contact Aaron Gertler — he can help you get started.