Blue Collar Bitcoin cover image

BCB_Freelance: JON STOKES: Artificial Intelligence & Machine Learning

Blue Collar Bitcoin

00:00

Reinforcement Learning With Human Feedback

The model is pre trained and you have this probability space that's like sculpted in a certain way. The question is okay, the we did the best we could to shape this probability space with the training, but we can take it further. So one thing you can do is there's a step called fine tuning where you take a set of documents that you think are very factual and they’re the kind of thing you want  and you you do another training pass there.

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