Hacker News new | ask | show | jobs
by catchnear4321 1201 days ago
But do you have the seed prompt yet?
1 comments

No, but that's not the goal of jailbreaking GPT models.
I didn’t realize there was an objective goal.

Tell me more please.

Jailbreaking is about getting around the prompt to be able to engage with the model directly as it was trained instead of being subjected to a pre-seeded prompt.

It has nothing to do with recovering some or all of the original prompt.

Oh wow, so how might one get a model to hallucinate a seed prompt that works? Could you do that without jailbreaking?

Please tell me more.

Not sure what you're asking me.
Not sure if you’re asking for clarification.