AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Jeremie Harris: Realistic Alignment and AI Policy
The Gradient: Perspectives on AI
The Importance of Alignment in Language Models
There is a concern on the order of years is catastrophic risk from AI, where you have a system that recognizes incentives that differ from our own. An AI system is never better off pursuing its training objective if it gets turned off. If it has access to fewer resources or if it's less intelligent. And what we see with that paper is an early sign that like controllability may be a much more difficult problem than we might have thought.
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