at the very least you could say "parsing and predicting text, images, and audio". and you would be correct - physical embodiment and spatial reasoning are missing.
Just spatial resoning, people have already demonstrated it controlling robots.
It's all just text though, both images and audio are presented to LLM as a text, the training data is a text and all it does is append small bits of text to a larger text iteratively. So parent poster was correct.
>It's all just text though, both images and audio are presented to LLM as a text