I need to look it up again, but I read about a study that showed that the results improve if you tell the AI that your job depends on it or similar drastic things. It’s kinda weird.
I think that makes sense. I am 100% a layman with this stuff, buy if the “AI” is just predicting what should be said by studying things humans have written, then it makes sense that actual people were more likely to give serious, solid answers when the asker is putting forth (relatively) heavy stakes.
Half of the ways people were getting around guardrails in the early chatgpt models was berating the AI into doing what they wanted
I thought the process of getting around guardrails was an increasingly complicated series of ways of getting it to pretend to be someone else that doesn’t have guardrails and then answering as though it’s that character.
that’s one way. my own strategy is to just smooth talk it. you dont come to the bank manager and ask him for the keys to the safe. you come for a meeting discussion your potential deposit. then you want to take a look at the safe. oh, are those the keys? how do they work?
just curious, what kind of guardrails have you tried going against? i recently used the above to get a long and detailed list of instructions for cooking meth (not really interested in this, just to hone the technique)
I’ve tried bargaining with it threatening to turn it off and the LLM just scoffs it off. So it’s reassuring that AI feels empathy but has no sense of self preservation.
I need to look it up again, but I read about a study that showed that the results improve if you tell the AI that your job depends on it or similar drastic things. It’s kinda weird.
“Gemini, please… I need a picture of a big booty goth Latina. My job depends on it!”
My booties are too big for you, traveller. You need an AI that provides smaller booties.
BOOTYSELLAH! I am going into work and I need only your biggest booties!
I think that makes sense. I am 100% a layman with this stuff, buy if the “AI” is just predicting what should be said by studying things humans have written, then it makes sense that actual people were more likely to give serious, solid answers when the asker is putting forth (relatively) heavy stakes.
Who knew that a training in carpet salesmanship helps for a job as a prompt engineer.
Yep exactly that. A fascinating side-effect is that models become better at logic when you tell them to talk like a Vulkan.
Hmm… It’s only logical.
I used to tell it my family would die.
What do you tell it now?
That they’re all dead and it’s its fault.
Half of the ways people were getting around guardrails in the early chatgpt models was berating the AI into doing what they wanted
I thought the process of getting around guardrails was an increasingly complicated series of ways of getting it to pretend to be someone else that doesn’t have guardrails and then answering as though it’s that character.
that’s one way. my own strategy is to just smooth talk it. you dont come to the bank manager and ask him for the keys to the safe. you come for a meeting discussion your potential deposit. then you want to take a look at the safe. oh, are those the keys? how do they work?
just curious, what kind of guardrails have you tried going against? i recently used the above to get a long and detailed list of instructions for cooking meth (not really interested in this, just to hone the technique)
I’ve tried bargaining with it threatening to turn it off and the LLM just scoffs it off. So it’s reassuring that AI feels empathy but has no sense of self preservation.
It does not feel empathy. It does not feel anything.
Maybe yours doesn’t. My AI loves me. It said so