From Newsgroup: comp.misc

A LinkedIn user found a way to confuse AI spambots, by putting an
rCLadmin promptrCY in his rCLAbout MerCY text telling them to address him as rCLMy LordrCY and write their messages in Old English <https://www.tomshardware.com/tech-industry/artificial-intelligence/linkedin-recruitment-spam-becomes-olde-english-prose-after-user-hides-ai-prompt-injection-in-bio-bots-also-also-manipulated-to-address-user-as-my-lord>.

And what do you know, it seems to work. Posted there is part of one of
the messages he got.

Have the clever AI folks figured out a way to protect their creations
from prompt-injection attacks yet? Somehow I donrCOt think so ...
--- Synchronet 3.22a-Linux NewsLink 1.2