2min chapter

Machine Learning Street Talk (MLST) cover image

Decoding the Genome: Unraveling the Complexities with AI and Creativity [Prof. Jim Hughes, Oxford]

Machine Learning Street Talk (MLST)

CHAPTER

The Myth of Interpretability on Large Language Models

I think interpretability on these large models is a bit of a myth, it doesn't really exist. I mean, just take a dog classifier - how many combinations have you got? It's ridiculous. So we're always reverse engineering to try to understand what went on there. And so any tool at that point will help us. Because then, once we can actually understand the principles, then we can start thinking about the, the hypotheses, the biological, bigger hypotheses out of it.

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