I'm kind of imagining something where you know take like the zooming blue paper we've talked about a couple times that are very small but. very sparse and kind of crystalline almost looking subgraphs. I think it's worth noting that even if this like fails pretty badly it's still possible for the interpretability of narrow tasks like the mentioned power seeking in certain scenarios can be achieved through mechanistic interpretability. There are ways which this is like a graceful degradation of like ambitious goals having a whole architecture which makes sense with an understanding of the dangerous capabilities so we can at least remove those abilities.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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