It's an interesting question. I don't think that they would necessarily be infinitesimal. Different generations will draw from different parts to greater or lesser degrees because of the training objective. One open question is in what way does generalization actually influence the output? Like we can't, we haven't looked at that. But there's another really interesting approach here which you can take with a toy model and see how good or bad we are.

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