2min chapter

The Inside View cover image

3. Evan Hubinger on Takeoff speeds, Risks from learned optimization & Interpretability

The Inside View

CHAPTER

I'm Preparing to Crystalas Work on Ceays, Right?

A so this is a little bit of aweird question, because it depends, i think, very heavily on who i'm giving te advice to. There's the problems that i work on, which are things like myothea and how do we sort of understand what it would be once my o l ha? And then there's more general advice if you're trying to get into a s a p and you have some machine learning experience and just want to do something. My current advice is like, try to do transparent intribitability research, a sort of like on in the style of life's circuit style stuff.

00:00

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