[zeehio]

When I listen to speech synthesis systems from the 80s, like the one from Stephen Hawking, I feel they are easy to understand but "robotic", they sound all the same in a "robotic" sense.

LLMs seem to suffer from that as well. The length of the answers has lower variance than the length from humans. The number of paragraphs, the length of each paragraph, the structure of the paragraphs... All that is kind of predictable, so when I read a text that does not have that structure I usually don't think it's written by an LLM. However if the text has that structure then I can suspect it may come from an LLM. I believe in some months we will all be used to the LLM style and we will get much better to identify it... And then chatbots will probably be changed to sound less robotic...

[jiggawatts]

It's actually very easy to convince an LLM to output perfectly natural text, it's just that their default mode is that verbose corporate boilerplate speak.

You can request responses in some specific style by the name of a popular author, or just provide a bunch of examples for it to copy.

I like responses in the style of an "Encyclopaedia Dramatica article", which tends to be both hilarious and also a bit less guarded and hence more honest.