The model is basically GPT-4 with different lenses on prompt engineering that you're then just bouncing back against one another. It's a super cool concept, and I'm curious to see where this takes us. But I suspect that we will go really far with even one, like multiple versions of one language model. As these models get bigger and bigger, just prompting can kind of prompt the model to do other 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