AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
6min chapter
#373 – Manolis Kellis: Evolution of Human Civilization and Superintelligent AI
Lex Fridman Podcast
The Importance of Interpretability in Large Language Models
With convolutional neural networks, interpretability had many good advances. We can kind of understand the different layers have different sort of ranges that they're looking at. With large language models, it's perhaps a little more complicated. But I think it's still achievable in the sense that we could kind of ask, well, what kind of prompts this degenerate if I sort of drop out this part of the network? And sort of start getting at a language to even describe these types of aspects of human behavior or psychology from the spoken part in the language bar.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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