This Day in AI Podcast cover image

Nvidia & The AI Goldrush, Neuralink Human Trials, LLM Specialization & Meta's MEGABYTE | E16

This Day in AI Podcast

00:00

The Importance of Preference in AI Training

Lima was trained on just a thousand curated high quality prompts, right? And they're getting 45% preference when compared to GPT four. It's interesting to the data that they selected to train it on. I think it could give some insight into what OpenAI trains on. So stack exchange, stem topics, stack exchange, other they don't really specify wiki how.

Play episode from 40:06
Transcript

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