They can take a llama to a base model and fine tune it to achieve agent performance similar to GPD 3.5. Their system is impressive because it reaches a level that previous models couldn't. They can perform tasks like online shopping, web browsing, and general computer tasks. When fine tuning, they retain the general world knowledge to help the agents perform better on general reasoning tasks. This approach is different from traditional fine tuning for dialogue and instruction following.

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