Comment by khalic

There's far more shared concepts between them than you think.

You should check the code of both world models (JEPA class for example) and compare to GPT. Many of the tricks stay the same, representation is still embeddings, there is a loss function, etc.

The exact architecture will change, but unless there's a new discovery in that area, we've cracked the text component already. We're hitting the limits of LLMs because of the intrinsic limits of text as a medium. But the way we work with text is pretty much settled, fundamentally.