The way these models work is that we tokenize the language into these blocks that are meaningful, a word or some piece of the word. And then that becomes the input to the model which we call a prompt. That prompt sets what we call a context. This is why prompt length is actually quite important. So what we enabled was a very long context window that you could actually feed it a whole book. We in fact, that the entire great Gatsby and we asked it to write the epilogue made up epilogue and it did so. It can do that across the entire context of the book. Imagine like reading the whole book, keeping it all in your mind and

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