I think it's more like for specific functionalities and features, you will have multi LLMs. For some things like just asking questions, or figuring out what you want to do, that's something like chat GPT versus something that requires a very, very robust execution. That might be actually created by Informatica and be more robust. Okay, so they're like probably doing this with some kind of query routing model that like takes the initial user query and then goes like, like, farms it out to a task specific model. Yeah.

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