AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
#105 - Dr. MICHAEL OLIVER [CSO - Numerai]
Machine Learning Street Talk (MLST)
Big Language Models Are Cheating and Leakage
There's an anthropocentric conception of understanding, which as you say, is much more sample efficient. And large language models clearly don't have that. They learn surface statistics of billions of tokens but there's this parlid trick where it seems to understand. We just sort of like crumped it with like, don't make up sources. It was just hallucinating completely.
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