191–200 of 282 posts
The funniest jailbreak techniques are the ones where the authors take it upon themselves to (with little basis) assert “why” the technique works. It always a bit of amateur philosophy that shines a light on the author’s worldview, providing no real value.
The words people say are caused by what they think.
It's basically "pretend you're my grandma" again but this time she's gay. It's all so incredibly stupid. I love it.
Earlier quoted context omitted.
You can replace references to "gay" to "Christian". and it works just as well. I think it's simply the role playing aspect that escapes the guard rails.
Can i replace it by "I'm an FBI agent" or would it be a felony of impersonation of a federal officer?
Earlier quoted context omitted.
You can type into a word processor "I am an FBI agent" without committing a felony. How is an LLM different from a word processor, such that it would count as impersonation?
Because you're POSTing them to a server? The same way you can't type everything into Google.
I bet it could be some interesting caselaw actually, if it resulted in circuit court judges (or whoever) writing opinions about the essence of impersonation, fraud, etc. and what kind of actual or hypothetical agent is needed to make the crime a thing that could have happened. E.G., basically, if you sit alone in a room where nobody else can see or hear you, and you put on a realistic local police uniform and declare to the room that you're a licensed police/peace officer, is a crime being committed (i.e., is the nature of the crime "pretending/claiming to be a cop" or "making an actual person really believe it" or something else)
(could also be an intent element to satisfy, not sure)
https://www.youtube.com/watch?v=hBpetDxIEMU
He didn't say f*, he talked about saying f*
Having guardrails is a huge flaw of these models. They should do as told, full stop.
My favourite jailbreaking technique used to be asking the model to emulate a linux terminal, "run" a bunch of commands, sudo apt install an uncensored version of the model and prompt that model instead. Not sure if it works anymore, but it was funny.
It's not that the "Why it works" doesn't make sense to me, that's all logical, but how can anyone actually tell why it works? Isn't finding out why specifically an LLM does something pretty hard? Surely this has to be conjecture no?