AXRP - the AI X-risk Research Podcast cover image

2 - Learning Human Biases with Rohin Shah

AXRP - the AI X-risk Research Podcast

00:00

Is Initialization a Good Approach?

The strength of that, like quotin qord prior or something that you're putting on the model is going to depend a lot on like, how long your training with your step size is and such. I think i would lean away from the vasion perspective, just because then you have to design a hypothesis pace and so on. That was just the first approach that occurred to me, and so i tried it, and it seemed to work all right? Reasonably well, i think so. And so so assumption to a essentially comes down to, like, when we train or m not works to mimbic humans, where can be initialized at this trained at this demonstrative tht

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