A lot of, a lot of stuff in AI is like you're wasting your time. And so very quickly we realized what's the surface area of this? What kind of things do we have to get good at? For instance, one of the big areas is, okay, we have to reduce hallucinations. So how do you do that? How do we kind of make sure that it's not trying to make up information? You know, another big, another big scenario is like how much do you bet just on open AI, open AI versus do you build an abstraction layer that lets you plug in different models that are going to be good at different, you know, use cases?"

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