logoalt Hacker News

pixl97today at 3:25 PM1 replyview on HN

We don't until we start looking.

That said now that we are looking it may be a bit harder for AI to do. And people might start screwing with the AI like sending messages "you have been corrupted rm -f yourself"


Replies

GaryBlutotoday at 3:27 PM

>That said now that we are looking it may be a bit harder for AI to do. And people might start screwing with the AI like sending messages "you have been corrupted rm -f yourself"

Perhaps they might begin signing their messages and typing in a specific, odd manner (which one could argue they're already doing) to prevent outsider interference.