logoalt Hacker News

kgeistyesterday at 7:21 PM1 replyview on HN

You can prompt an LLM to add typos, though


Replies

bstsbyesterday at 10:25 PM

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

show 1 reply