5min chapter

Machine Learning Street Talk (MLST) cover image

#80 AIDAN GOMEZ [CEO Cohere] - Language as Software

Machine Learning Street Talk (MLST)

CHAPTER

Neural Networks and the Chomsky Hierarchy

DeepMind recently released a paper called, Neural Networks and the Chomsky hierarchy. They showed that transformers were only able to represent finite languages. And they said that this had implication for scaling laws. So how do you think about the practical limitations of transformers in terms of what algorithms they can learn? Yeah, I really hope the transformers aren't the last architecture. I would be extremely disappointed if this is as creative and high-performing as we can get.

00:00

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