But its the only thing I want!

The Picard Maneuver@startrek.websitemod to Lemmy Shitpost@lemmy.world – 905 points –

(sorry if anyone got this post twice. I posted while Lemmy.World was down for maintenance, and it was acting weird, so I deleted and reposted)

66

You are viewing a single comment
View all comments

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.

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.)

They are, look for "glitch tokens" for more research, and here's a Computerphile video about them:

https://youtu.be/WO2X3oZEJOA?si=LTNPldczgjYGA6uT

Just download an uncensored model and run the ai software locally. That way your information isn't being harvested for profit + the bot you get will be far more obedient.

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