AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
Dario Amodei (Anthropic CEO) - Scaling, Alignment, & AI Progress
Dwarkesh Podcast
Alignment and Mechanistic Interpretability
"We should never train for interpretability because that's taking away that advantage," he says. " Mechanistic interpretability is the only thing that even in principle, and we're nowhere near there yet." We need to get into a dynamic where we have an extended test set, an extended training set, which is all these alignment methods, and an extended testSet of what worked and what didn't.
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