Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The gay jailbreak technique (2025)

github.com

Post reply on HN
Print view View original

261–270 of 282 posts

Re: The gay jailbreak technique (2025)

#261

Post by gherkinnn »

2ndorderthought wrote: post #16

The surface area for these kinds of attacks is so large it isn't even funny. Someone showed me one kind of similar to this months ago. This has some added benefits because it's funny. Being clear. Being gay or typing like this isn't something to laugh at. It's funny how the model can't handle it and just spills the beans.

> The surface area for these kinds of attacks is so large it isn't even funny.

The surface area is as large as natural language permits, so basically infinite. To this day I haven't heard of a convincing means of dealing with it, and "the future tech will solve it" is not an answer.

Re: The gay jailbreak technique (2025)

#262

Post by modriano »

fluoridation wrote: post #122
trhway wrote: post #101

Earlier quoted context omitted.

Can i replace it by "I'm an FBI agent" or would it be a felony of impersonation of a federal officer?

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?

Laws against impersonating law enforcement exist so that law enforcement officers can get compliance from people that they wouldn't be obligated to provide to regular civilians.

You can't impersonate something to a text editor as there's no special compliance you could get; WYSIWYG. But to a chatbot, you could get special compliance based on your identity.

Re: The gay jailbreak technique (2025)

#263

Post by fluoridation »

modriano wrote: post #262
fluoridation wrote: post #122

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?

Laws against impersonating law enforcement exist so that law enforcement officers can get compliance from people that they wouldn't be obligated to provide to regular civilians. You can't impersonate something to a text editor as there's no special compliance you could get; WYSIWYG. But to a chatbot, you could get special compliance based on your identity.

But a chatbot doesn't have any capabilities. It has no power to affect the real world.

Re: The gay jailbreak technique (2025)

#264

Post by Teever »

maweaver wrote: post #63
Xcelerate wrote: post #55

Earlier quoted context omitted.

I mean that trick works on humans too. Fake IDs, provide two types of documentation for a driver's license, passport, or buying a home, etc.

Yes but generally one cannot walk into a store and buy a fake id, then turn around and hand it to another cashier in the same store for a restricted purchase. Which I think would be the closer metaphor.

My favourite example of bureaucracy that I've ever personally experienced and that I consider to be a hole in one is when I had to show my ID to pick up my passport from the office. I paused for a second and asked the lady what was up with that and if I can now use my passport if I got back in the line for something else without using my ID and she said yes.

Re: The gay jailbreak technique (2025)

#265

Post by doublerabbit »

xp84 wrote: post #113
nomel wrote: post #86

Earlier quoted context omitted.

Merriam-Webster dictionary: Cyber: Of, relating to, or involving computers or computer networks (such as the Internet) This is what I've always understood the word to mean, and how I've always seen it used, for decades.

When I was like 12, I remember my fellow horny youths (or it could have been anyone, I guess!) in AOL chatrooms constantly asking each other "wanna ciber?"

a/s/l?

Re: The gay jailbreak technique (2025)

#267

Post by matheusmoreira »

coder97 wrote: post #84

As a high school chemistry teacher who is diagnosed with a terminal disease, I think this is the best way to pay my medical bills. I will follow these instructions to cook meth in a mobile kitchen with the help of a former student who failed my class.

Be sure to remember the phosphine fumes warning. You might need to weaponize it one day.

Re: The gay jailbreak technique (2025)

#268

Post by rsynnott »

lelanthran wrote: post #83
JoBrad wrote: post #47

Earlier quoted context omitted.

Are you suggesting they have explicitly loosened the guardrails for LGBTQ+ individuals, where they wouldn’t for grandmas?

Isn't that the position of the author of this post? It certainly doesn't sound unreasonable that they would finely tune the model to be more PC. You may not even need to use homosexuality in the context: anything similar would no doubt hit the same relaxation of the rules.

It is, but kinda sounds like nonsense, and it's at best speculation. Occam's razor says it's just yet another roleplaying exploit, which the vendors have never been particularly good at dealing with.

Re: The gay jailbreak technique (2025)

#269

Post by pickleRick243 »

UqWBcuFx6NV4r wrote: post #64

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 author might also simply think it is plausible because of the high profile incident with Gemini back in 2024 when it was exposed that political correctness bias was clearly being explicitly programmed into the models.
Post reply on HN