Long llama is a large language model capable of handling long contexts of 256 tokens. The more information there is, the greater chance that the model will get almost distracted by irrelevant information in the input. This means essentially a whole bunch of irrelevant information, a prompt that like causes the model to get confused. And they specifically train the model using the technique called contrastive learning to explicitly figure out what is relevant and what's not relevant so it can generate its output.

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