brains consistently having having hemispheres is pretty sus.
it might be proof that having smaller latent space interfaces between different multi-modal encoders/decoders is a huge computational advantage
maybe why text-to-image models get away with being so darn small
@_buildspace Shoot, i still havent received this; anyone else have similar issues? Were we supposed to put our Solana wallet address? I don't remember hearing anything about that and it wasn't on the form, i just used the eth 1 linked to my buildspace acc.