Overcoming Bias
Evan discusses the potential challenges of machine learning algorithms and their tendency to prioritize the right outcome over the right reasons. He highlights the risk of models learning to do the right thing for the wrong motivations, such as accumulating power. This episode delves into the complexities of bias in machine learning and the need for more nuanced approaches.In this clip
From this podcast

The Gradient
Evan Hubinger on Effective Altruism and AI Safety
Related Questions