1min snip

Dwarkesh Podcast cover image

John Schulman (OpenAI Cofounder) - Reasoning, RLHF, & Plan for 2027 AGI

Dwarkesh Podcast

NOTE

The Power of Generalization and Transfer in Language Models

Language models can mimic human affordances, enabling them to be sample efficient by generalizing from experiences and training on how to navigate various scenarios. The acceptance of this kind of generalization and transfer is seen in the strong performance of models in different languages post-training. For instance, fine-tuning a model on English data can lead to it performing well in other languages like Spanish, often responding accurately to queries in the respective languages.

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