Anders Sandberg on ChatGPT and the Future of AI
Future of Life Institute Podcast
AI Safety - What Values Should We Give to AI?
There is this core technical issue in AI safety of aligning an AI model to a set of values. But there's also the philosophical side of deciding which values we should have, and you quickly get into difficult discussions. We don't know what the true values we ought to have are if it's an ongoing debate," he says.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
