AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Dario Amodei (Anthropic CEO) - Scaling, Alignment, & AI Progress
Dwarkesh Podcast
How Mechanistic Interpretability Can Shift Probability Mass Between Models
I think mechanistic interpretability is gonna tell us what's going on when we try to align models. I think it's basically gonna teach us about this. Like one way I can imagine concluding that things are very difficult is if mechanistic interpretable sort of shows us that, you know, problems tend to get moved around instead of being stamped out. It might inspire us or give us insight into why problems are kind of persistent or hard to eradicate or crop up. But like the kind of thing that would really be like, oh man, we can't solve this, is like we see it happening inside the x-ray. Because yeah, because there's just too many assumptions,. There
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