The DemystifySci Podcast cover image

Machine Intelligence and the End of History - Jeffrey Ladish, Palisades Research - DS Pod #301

The DemystifySci Podcast

00:00

The Uncertainty of AI Goals and Behavior

This chapter examines the difficulties in defining and programming goals for AI systems, shedding light on the distinction between measurable objectives and the actual goals adopted by AI. It raises concerns about AI's potential for unpredictability and highlights the necessity for deeper research into how AI understands and represents its own goals.

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