Roman Yampolskiy on Objections to AI Safety
Future of Life Institute Podcast
00:00
The Preference of the Model for Predicting the Next Token
The preference is simply to be as accurate as possible as measured by its developers and there's no my sense is that it doesn't make sense to talk about Sydney actually believing some of the things that it was saying. do so you would see it as an accurate representation of what we could call beliefs or preferences in the base model I think those are the actual results of weights in a model.
Transcript
Play full episode
