MLOps.community  cover image

Treating Prompt Engineering More Like Code // Maxime Beauchemin // MLOps Podcast #167

MLOps.community

00:00

How to Scale Hyper Parameter Tuning ML

You can effectively know these things in a much clearer way than if you're just kind of evaluating from looking at the answer and that's really hard to scale. It makes complete sense where you're saying alright this one is 75% useful or this prompt is is this good but then when you pointed out a different model it holds up much better or much worse etc etc. get itYeah so you can do it it brings some the mindset of a if you're familiar with hyper parameter tuning ML, right? You want to train a whole like matrix like multi dimensional matrix of model and then compare how they're performing against one another right?" Yeah so you can doing all test cases at the finance code

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