Replit AI Podcast cover image

02: Unleashing LLMs in Production: Challenges and Opportunities with Chip Huyen

Replit AI Podcast

CHAPTER

How to Make Context Learning More Effective

The inject weights basically are doing the feed forward in a training in a different way. It's similar to prompt tuning, but it's happening midway through the feed forward rather than at the beginning as an input. We will have to find a good trade off between how much money we spend so often with redo the pre training and more advanced techniques. So that's one of the fields that I'm following the, the causes right now.

00:00
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