logoalt Hacker News

dist-epochlast Sunday at 9:56 PM1 replyview on HN

People are already prompting with "yeah, don't do these things":

https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing


Replies

ssl-3last Sunday at 10:39 PM

"That's such a great observation that highlights an important social issue — let's delve into it!"

I've been prompting the bot to avoid its tics for as long as I've been using it for anything; 3 years or so, now, I'd guess.

It's just a matter of reading and understanding the output, noticing patterns that are repetitious or annoying, and instructing the bot as such: "No. Fucking stop that."