That is literally what LLMs do though. Those comments try to explain how it works so you better can see how it produced the results you see, they aren't trying to say that the program is worthless just that it isn't the magic some people think it is.
These models are trained to produce text snippets that look like text snippets it has seen before, and it has seen all internet. That means it can do a lot of impressive things, but also that it is very dumb in other ways.
These models are trained to produce text snippets that look like text snippets it has seen before, and it has seen all internet. That means it can do a lot of impressive things, but also that it is very dumb in other ways.