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

interestingly, you can’t do the same thing with queries like “no em dashes”. it’ll agree, then proceed to use them regardless.

could be related to how so-called negative prompts fail to work when asking, say, ChatGPT to generate an image without a crocodile

 help



My theory is that sprinkling emdashes into the output is some intentional measure to "watermark" LLM output.



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

Search: