[scotty79]

It could be a diffusion model with a latent model of what needs to be said that will generate whole message or coversation (progressively) at once.

Although I love how next token prediction leads to text showing up gradually, in case of local models, accompanied by modulated coil whine of my GPU. It's how the 80s shown us the intelligent computers should communicate.

[roenxi]

Aren't they already doing that though? And it turned out to be equivalent to a next-token-predictor.

[scotty79]

This could be a strong signal that it's actually intelligence since it's all equivalent.