The way I think about thinking co-amps is you start with just a big black box. You try to get it to do what you want. Next step is, all right, well, how can I break this down into smaller things I understand? How can I call the model? And then you check it. It's like they're doing atomic sub parts of tasks, which are integrated to so I expect a co-amp. They're not models. They're systems. So ultimately, what I expect a powerful co-amp system to look like is it will be a system of many moving parts that have clear interfaces between them. We won't have these crazy things that we can

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