5min chapter

Machine Learning Street Talk (MLST) cover image

#64 Prof. Gary Marcus 3.0

Machine Learning Street Talk (MLST)

CHAPTER

Is It a Driverless Car?

In 19 98, i said that these things are basically just memorizing and not extrapolating. In a transformer model you tend to eat your fingers for the cross cases with respect to arithmetic. Can you imagine a shipping processor where you had to operate freely but don't really have a clean representation of it? I've been thinking about a bunch of them. We could talk about scaling laws in tha second. But let's go back to the other question, which is, what is the reasoning stuff? And why do i call it algebraic?

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