top | item 46847927

(no title)

mritchie712 | 28 days ago

in 2024, yes.

what AI are you using where this still works?

discuss

order

wat10000|28 days ago

I haven’t tried it in a while, but LLMs inherently don’t distinguish between authorized and unauthorized instructions. I’m sure it can be improved but I’m skeptical of any claim that it’s not a problem at all.