[abeppu]

A human hears words in context. Those words tie to things in the environment, responses to the young human's actions, etc. A parent saying, "roll the ball" during playtime with their kid and actually pushing a ball back and forth, provides a grounding of words in actual experience.

> is there anything that would stop LLMs from being able to do the same thing?

If you built an AI system which could hear/see/touch/move etc, and it learned language and vision and behaviors together, such that it knows that a ball is round, can be thrown or rolled, is often used at playtime, etc, then maybe it could understand rather than just produce language. I don't know that we would still call it an LLM, because it could likely do many other things too.