Evan Hubinger

May 6, 2024 | lesswrong.com | Daniel Filan |John Wentworth |Evan Hubinger |Vanessa Kosoy’s work

What’s going on with deep learning? What sorts of models get learned, and what do the learning dynamics? Singular learning theory is a theory of Bayesian statistics broad enough in scope to encompass deep neural networks that may help answer these questions. In this episode, I speak with Daniel Murfet about this research program and what it tells us. Topics we discuss: What is singular learning theory?

Apr 30, 2024 | lesswrong.com | Daniel Filan |Evan Hubinger

YouTube linkTop labs use various forms of “safety training” on models before their release to make sure they don’t do nasty stuff - but how robust is that? How can we ensure that the weights of powerful AIs don’t get leaked or stolen? And what can AI even do these days? In this episode, I speak with Jeffrey Ladish about security and AI. Topics we discuss: What we learn by undoing safety filters What can you do with jailbroken AI?