Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

honestly, yes, i really suspect this is true. i’ve been using chatgpt since the beta days to help with studying chinese, and i’ve noticed over the months that its replies have gotten increasingly wordy.

the good thing is that you can tell it to be more concise, less bot-like, not so apologetic, etc., and it’ll trim down its responses for as long as it can “remember” (whatever the token limit is on persistence). it’ll be great when llms have, by default, a bit of persistent memory to remember things like this



>it’ll be great when llms have, by default, a bit of persistent memory to remember things like this

ChatGPT already has this (not sure if it's Plus-only). In your user profile, there's a "Custom Instructions" entry where you can give it persistent prompts.


oh hey, i just saw this option after you mentioned it. thanks. it’s really quite helpful


I’ve also noticed wordiness go up but in their subscription product it doesn’t make sense because it just costs them.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: