3min chapter

Machine Learning Street Talk (MLST) cover image

#103 - Prof. Edward Grefenstette - Language, Semantics, Philosophy

Machine Learning Street Talk (MLST)

CHAPTER

Is RLA-CHF a One Size Fits All?

The problem with some of these language models at the moment is if you ask them to generate a poem or something like that, they kind of all look the same. So obviously if you are trying to use RLA-CHF as a one size fits all without thinking about the qualification of your annotators, you're going to have issues. And I think that's a pretty powerful paradigm because it puts all the complexity behind the data collection mechanism in the hands of the annotation designer rather than the annotator, which is the way it should be.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode