The Inside View cover image

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

The Inside View

00:00

Is It Like Humans Consulting Humans?

i think that like, you know, at least an imitative amplication. Amplication, a actually produces better models. And there's also one ithink, i think one thing that is interesting me is weot modelling. Inee lerning trying to infer in te gen function. Wers am di mind a iset tem was mostly trying to do wayward muddling. But i don't fully understand the difference, am andan. And how, in your blok boast, you givee some solutions with wor muddled. So if you could explain that to me, that would be like, a helpful on a personal level. Yes. It seems kind of

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app