What is DeepMind's safety team working on?

DeepMind has both a machine learning safety team focused on near-term risks, and an alignment team working on risks from artificial general intelligence

AGI

AI that is at least as good as humans at general problem-solving.

View full definition

Their work includes:

• Engaging with recent arguments from the Machine Intelligence Research Institute

• The alignment newsletter and podcast, which were produced by Rohin Shah.

• Research like the Goal Misgeneralization

  Goal misgeneralization

  Pursuing a different goal during deployment than was intended to be learned in training.

  View full definition

  
  paper.

• Geoffrey Irving’s work on debate as an alignment strategy.

• “Discovering Agents”, which introduces a causal definition of agents, then introduces an algorithm for finding agents from empirical data.

See Shah's comment for more research that they are doing, including a description of some that is currently unpublished.