There's been a trend of combining multiple language models in a kind of unified system here. They laid out four different conditions that that justify the switch so you know if you've spent a long time many time steps without getting any reward then it switches to higher order thinking instead of relying on instinct and then like when it's prediction for the next action is invalid in the current environment same thing. yeah so i thought this was very cool and again we've seen some of that as well with paper we covered on optimal and single cost of thingsWe can delegate to smaller models in some cases that work just as well, he says.

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