Computer scientists Emma Brunskill of Stanford and Phil Thomas of UMass Amherst join Michael and Dave in a four-way discussion of safety and fairness in AI and machine learning.

[The primary paper discussed, Preventing undesirable behavior of intelligent machines, is by Philip S. Thomas, Bruno Castro da Silva, Andrew G. Barto, Stephen Giguere, Yuriy Brun, and Emma Brunskill, and can be accessed for free via paper in Science ]