1min snip

Dwarkesh Podcast cover image

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

Dwarkesh Podcast

NOTE

Language Models and Generalization

Language models demonstrate the ability to generalize from experiences and training, showing similar affordances to humans. Strong acceptance of this generalization and transfer has been observed, with models being able to behave well in other languages if fine-tuned with English data. Despite occasional mistakes in choosing the language to reply in, models generally respond appropriately by matching the language of the query.

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