How could a newer model be better at making up information? Do you understand basic information theory? Or maybe what you're saying is you don't actually have any ideas and are happy to do what everyone else has done before you so it makes no difference?
The older models were less good at inferring intent. The new ones just seem to do a better job.
It’s just surprising how few people understand this. It’s not like it’s new either. Polyani’s theory of tacit knowledge captured this back in 1958