The Inside View cover image

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

The Inside View

00:00

Capability Rebustness

Robustness is a luckyyou rethat your objectives. Robustness in general says, according to the actual reward, you generalize well. Capability rebustes is the sub set of robustness that as not according to the Actual Reward and just according to whatever utility function. Torebas toi foro em. Well, so it's its yes? Or maybe a useful thing also for distinguishing thing capability, rebutness and objectorbustness would be, there's like another version of this picture where i have it in terms s like rit. Bm, again, igan take the other one. Is it bilrit noing itis, like the

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