Gradient Dissent: Conversations on AI cover image

Providing Greater Access to LLMs with Brandon Duderstadt, Co-Founder and CEO of Nomic AI

Gradient Dissent: Conversations on AI

00:00

Comparing Foundation Models With Data Kernels

RLA Jeff is in my mind fine tuning when it's hard to define your objective. It first builds a model that tries to predict what people want, almost a model of that objective function and then trains a model to maximize the reward according to that objective function. Do you also do RLA Jeff on your models? And how does that fit in with fine tuning? Like do you view that as a kind of a specialist type of fine tuning or? Yeah. I'm happy to talk more about that if you want to go in that direction.

Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner
Get the app