alt Hacker NewsThese system prompts are not the only safety layer that these models use. There's other more deterministic filters in place both on input and (streaming) output.
Replies
lucisferre • yesterday at 9:36 PM
I think it is fair to argue that prompts are not a safety layer at all and can't be relied upon for much.
"Make no mistakes"
➕ show 3 replies
Is there concrete evidece that those are xAI's default prompts anyway? They seem plausible enough but how would company outsiders know?