alt Hacker NewsWhat invent human consciousness?
> LLMs are vulnerable to classes of attacks that humans just aren’t
Name three that don't have direct analogues with humans.
Replies
efficax • yesterday at 7:00 PM
where is the analog for hiding instructions in a document that tell the human to please injure itself and the person just says 'oh ok, injuring myself as requested'
➕ show 1 reply
Re write the assistant message and see how easy it is to bypass a system prompt. How far do you have to stretch to get a human analogue? Short term amnesia?