[danielmarkbruce]

> Doesn't Language itself encode multimodal experiences

Of course it does. We immediately encode pictures/words/everything into vectors anyway. In practice we don't have great text datasets to describe many things in enough detail, but there isn't any reason we couldn't.

[heyjamesknight]

There are absolutely reasons that we cannot capture the entirety—or even a proper image—of human cognition in semantic space.

Cognition is not purely semantic. It is dynamic, embodied, socially distributed, culturally extended, and conscious.

LLMs are great semantic heuristic machines. But they don't even have access to those other components.

[danielmarkbruce]

The LLM embeddings for a token cover much more than semantics. There is a reason a single token embedding dimension is so large.

You are conflating the embedding layer in an LLM and an embedding model for semantic search.

[heyjamesknight]

I don't think we're using the term semantic in the same way. I mean "relating to meaning in language."

[danielmarkbruce]

The embedding layer in an llm deals with much more than the meaning. It has to capture syntax, grammar, morphology, style and sentiment cues, phonetic and orthographic relationships and 500 other things that humans can't even reason about but exist in words combinations.

[heyjamesknight]

I'll give you that. I was including those in "semantic space," but the distinction is fair.

My original point still stands: the space you've described cannot capture a full image of human cognition.