A faster, better way to prevent an AI chatbot from giving toxic responses
news.mit.eduMuch ado about nothing.
Look, if you type a bunch of hateful text into Word, surprise, it will display that text on your screen. Would anyone really want a tool that did otherwise? Should Clippy pop up and scold you?
It's really not that different with LLMs. If some juvenile folks would get a kick out of seeing some hateful stuff on their screens - so what? Why hobble the tools for everyone else?