AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
Jeremie Harris: Realistic Alignment and AI Policy
The Gradient: Perspectives on AI
How to Maximize Your Debate
The key to me is like, I don't expect the system to care about anything other than its objective. A priority makes it very difficult to claim that we could expect this thing to learn to care about whatever we tried to get it to learned to care about. The idea of orthogonality can be totally de correlated with intelligence and goals. It's not if it understands that you want it to make paper clips. Great. That doesn't mean it's going to ignore its implicit incentives to seek power just because they are in an adversarial relationship relative to humans.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode