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

Someone at OpenAI please, for the love of everything good in this world, please please please train your chat bot to stop ending replies with the insipid "It isn't just A — it’s a whole new B" pattern.


“No em dashes” is hard coded in my pre-prompts. I’m with you. It’s fine occasionally for a human to do it but it messes up screen readers and TTS because they don’t even pause. They treat it like a hyphenated word.


AI writing being easy to detect is a good thing IMO. I personally won't read anything from someone who thinks it improves their writing


Except, as is often the case, it’s not that AI itself is easy to detect, but that bad uses of AI are. You are almost certainly reading far more AI generated text than you realise it just doesn’t register as such.




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

Search: