I think there's a lot of expectation that like everything is going to be smooth with RLHF. The gap between the RLHF GPT three models, if you look at the sort of reports or the anthropic ones and the ones that are not is large. And so in general, I'm pro RLHF as a concept and where it makes sense to do it if you have a big enough problem. But my advice is always to try to find the simplest solution to what you're trying to do first,. If that doesn't work, go for more complex or harder things.

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