There are domains where, let's say, something like any text that is generated must be funny. And I can't imagine like writing a validator that maybe assigns like a scoring function to humor,. Like that's just very hard to do. So there are those domains where this re-asking strategy doesn't work. But the idea of taking what is correct and trying to codify some of that is useful in terms of prompting the large language model. It allows guardrails to construct like prompts that are more effective at getting you what you want. Then it also allows you to like post-shock validation.

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