AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
David Krueger–Coordination, Alignment, Academia
The Inside View
The Importance of Distribution Generalization by Risk
In theory, there's an argument for why it shouldn't work. But that in theory argument doesn't say how badly it will fail. So what actually matters is the actual distribution of the data and not just having, like, full support and infinitely much data. And that's because of hidden compounders. It both helps the AI better understand the instructions, but at the same time it helps it generalize.
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