2min chapter

The Gradient: Perspectives on AI cover image

Catherine Olsson and Nelson Elhage: Anthropic, Understanding Transformers

The Gradient: Perspectives on AI

CHAPTER

What Is in Context Learning and Induction Heads?

Some models, especially these large language models starting with GPT two and GPT three are very good at incorporating information that you give them in the context or in the prompt to kind of vary their text generation. They sort of learn from the prefix in a very sophisticated and nuanced way. If you give them a prompt that is serious Q&A with the scientist, they start generating text that is in the serious scientist voice. And they sort of they react very in a very nuanced way or very reactive way to the earlier context of the prompt.

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