> I usually have the entire sentence in my inner dialogue before I even start typing
Interesting. Perhaps the question then becomes, does your inner dialogue simply chain the words one after another, or does it come up with sentences as whole?
I have a friend who listens carefully and starts to mouth and even mumble his brain’s predictions for the next words I am going to say. So, I fuck with him by unexpectedly (even to myself) changing my words (or even the sentence) half way through when I catch him doing it. Predictably, I don’t like being predictable.
The fact that ChatGPT does so well is perhaps a sign we do somewhat generate sentences on the fly. Obviously we mostly listen and read sequentially.
One could test it by using an external random bell to signal you should try and make a significant sentence change e.g. from English to Spanish. How much practice would it take?
From 1984: In the middle of Hate Week, the speaker is halfway through a sentence about hating Eurasia, he is given a note, and he continues the sentence except now Oceania is not, and has never been, at war with Eurasia, and it is Eastasia that is now hated.
It's impossible to form meaningful sentences without having a model of the sequence of the words, this is as true for a human as for a markov chain, but that doesn't mean it then follows that human sentences are just sophisticated markov chains, the nature of sentences means that they must be a sequence of words regardless of the implementation details behind the hood of the sentence creator.
Why would it? It would make more sense to start with concepts ("dog", "brown"), and then pull it into words ("That dog is brown") - given that we're trying to convey a thought that seems to be far more likely than us chaining things - we start with the intent to communicate something, the markov chain does not.
Interesting. Perhaps the question then becomes, does your inner dialogue simply chain the words one after another, or does it come up with sentences as whole?