The way in which describes things in language leaves a lot of gaps for an image generation models to feel when it's generating an image. One question is whether these models are merely, as the authors of the Stochastic Parrots paper put it, Hap has at least teaching together pits and pieces from the training data. Or is it doing something or something more? And I think you can actually study this empirically.

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