The first thing is to analyze how much data you're throwing at it. So in your example, you said 5000 transcript something like that. That's probably in the prompt regime. We're probably not doing anything beyond that. If we're now in the billion range, we can talk about pre training and layering in this data. The process reinforcement learning with human feedback RLHF. And actually what you do then is you say, well, the inputs are all this deck material, say, and then these companies did really well, and those companies did it.

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