The architecture suggests the potential for modularity right i mean we see all these projects where certain you know a language model is frozen and combined to something else. It's quite in essence it's quite similar yes yeah almost like a different head so to speak if you had a similar maybe even the same concept. If you can train a single global model that can handle different kinds of inputs and represent them in a meaningful way then you could have different local models that create different sorts of outputs based on that single understanding. The more i learned about it it makes sense why some of the leading thinkers in this space have been very excited about this paper.

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