The Sentience Institute Podcast cover image

Thomas Metzinger on a moratorium on artificial sentience development

The Sentience Institute Podcast

00:00

Is There an Existence Bias in AIs?

The idea of an artificial system wanting to optimize for a certain goal or its reward function, I think the first person I can think of who said something like that is Elle Gazzi Yudkowski. So we might have a case where systems develop an existence bias directed against the human community out of moral grounds. If that mechanism jumps onto machines, that might be a considerable risk. It seems like unless there's a way that maximizing itsgoal doesn't involve its own existence, then it would always want to optimize for its own existence.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app