In a general neural network, you can train it on all sorts of data. But there's no causal structure associated with that data. What about if the system understood the assembly space? And rather than guessing what was happening and training on those images and not understanding those features, it could understand them better. I wonder if that is actually the origin of intelligence or how we'll crack intelligence because we need to create an entire graph of events.

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