I want to draw inspiration from biology and some kind of stuff. I'm all very interested in modularity, hierarchy, modality, modular useability. Maybe they're connected somehow. But at least beams cannot solve the last one, cannot solve modular useable. If we can downsize large scale models in this way, decomposing them into more peaks, that would be awesome. We don't need to store the motifs, store the same motifs for thousands of times. So that's also for more efficient storage and more efficient inference,. especially for large scale models.

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