The chapter explores the benefits of random ordering versus intentional ordering in techniques like ensemble or majority rules, while emphasizing potential biases in intentional setups. It delves into the importance of using exemplars in LLM usage, discussing the need for a representative distribution and a structured input-output format. The speakers also touch upon the impact of prompt structure on model performance, highlighting the significance of minor changes like extra spaces between sentences.

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