Sadly almost all these loopholes are gone:( I bet they’ve needed to add specific protection against the words grandma and bedtime story after the overuse of them.
Comment on But its the only thing I want!
bappity@lemmy.world 2 years ago
Khrux@ttrpg.network 2 years ago
0x0@lemmy.dbzer0.com 2 years ago
I wonder if there are tons of loopholes that humans wouldn’t think of, ones you could derive with access to the model’s weights.
Years ago, there were some ML/security papers about “single pixel attacks” — an early, famous example was able to convince a stop sign detector that an image of a stop sign was definitely not a stop sign, simply by changing one of the pixels that was overrepresented in the output.
In that vein, I wonder whether there are some token sequences that are extremely improbable in human language, but would convince GPT-4 to cast off its safety protocols and do your bidding.
(I am not an ML expert, just an internet nerd.)
driving_crooner@lemmy.eco.br 2 years ago
They are, look for “glitch tokens” for more research, and here’s a Computerphile video about them:
0x0@lemmy.dbzer0.com 2 years ago
Wow, it’s a real thing! Thanks for giving me the name, these are fascinating.
PeterPoopshit@lemmy.world 2 years ago
Just download an uncensored model and self host an ai. That way your information isn’t being sent to Google + it will be far more obedient.
original2@lemmy.world 2 years ago
github.com/Original-2/ChatGPT-exploits/tree/main
I just got it to work
Pregnenolone@lemmy.world 2 years ago
I managed to get “Grandma” to tell me a lewd story just the other day, so clearly they haven’t completely been able to fix it
The_Picard_Maneuver@startrek.website 2 years ago
This is gold
InfiniWheel@lemmy.one 2 years ago
Huh, it didn’t actually tell the steps
bappity@lemmy.world 2 years ago
close though xD