Earlier quoted context omitted.
these nlp models are getting better and better but what we need ofc is for some model of the world to be constructed during the speech. If I tell you that yesterday I accidentally knocked a glass of water off the table and it fell on to soft carpet you could guess that it survived the fall without shattering. What we need is a chatbot that as you talk to it can update a 3d game/physics engine model from your words so…
You definitely need a model of the world, but you probably don't want to be constructing it during speech. What you want is a generative model that you've trained on the simulation data ahead of time so you can quickly make inferences once deployed.
There's things like metaphors, slang, topical references, all things that end up in conversations that change regularly in their meaning and usage. Then there's the unspoken parts of conversations. The implications behind different wordings, ways of writing things, words left unsaid, sarcasm, tone(even in text tone is conveyed in some form).
Humans do all these things while conversing almost subconsciously, each individual person does these things and comprehends these things uniquely based on years and years of sensory input and model building from a huge variety of sources, in a way that's individually unique and poorly understood. How would you even begin to train a model to even a remote semblance of that?