Reasoning how? LLMs are statistical models, not brains.
My point was that it should be.
The training is on images and text, and the output is text. But nothing constrains the model in the middle of those two ends to only model based on language features, as opposed to world features discoverable from the language and images.
So if you make your model through slow thinking and discovery chatgpt just builds it to a billion words.
The result is the same
A LLM (that hasn't been trained on any data regarding this topic) is unlikely to demonstrate the same bouba/kiki effect seen among humans. https://en.wikipedia.org/wiki/Bouba/kiki_effect
People continue to claim LLMs are just parrots. But then there is never a solid rebuttal to how humans are different.