With onprivileged spaces, you need to try really hard to search for that color direction and then project token embeddings to that direction. But with BIMT, very likely there's just one dimension of thetoken embeddings corresponds to the color dimension. So my only concern so far is that it might be harder to visualize the whole network. This is apparent difficulty. I don't necessarily see any factor that blocking it from scaling.

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