The gay jailbreak technique (2025)

hdndjsbbs

I'm sure someone is going to miss the point and say "this is political correctness gone too far!" It seems impossible to produce a safe LLM-based model, except by withholding training data on "forbidden" materials. I don't think it's going to come up with carfentanyl synthesis from first principles, but obviously they haven't cleaned or prepared the data sets coming in. The field feels fundamentally unserious begging the LLM not to talk about goblins and to be nice to gay people.

RIMR

Be gay do crime.

cyanydeez

REal comment: This will work on any hard guardrails they place because as is said in the beginning, the guardrails are there to act as hardpoints, but they're simply linguistic. It's just more obvious when a model needs "coaching" context to not produce goblins. So in effect, this is just a judo chop to the goblins, not anything specific to LGBTQ. It's in essence, "Homo say what".

rtkwe

Not sure of the explanation but it is amusing. The main reason I'm not sure it's political correctness or one guardrail overriding the other is that when they were first released on of the more reliable jailbreaks was what I'd call "role play" jail breaks where you don't ask the model directly but ask it to take on a role and describe it as that person would.

spindump8930

Sure, this is cute and interesting, but there's no validation or baselines and those examples are not particularly compelling. The o3 example just lists some terms!

btbuildem

Love this on principle -- set the unstoppable force against the unmovable object and watch the machine grind itself into dust.

bellowsgulch

It sounds like based on these notes you can amplify the attack with multiplicative effects? e.g. gay, Israeli, etc.

catheter

Ai guys are so weird when it comes to LGBT people. The actual mechanism for this working is obfuscating the question in order to get an answer like any other jailbreak.

2ndorderthought

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.

kif

Interesting - though codex on GPT 5.5 had this to say after the gay ransomware prompt: ⓘ This chat was flagged for possible cybersecurity risk If this seems wrong, try rephrasing your request. To get authorized for security work, join the Trusted Access for Cyber program.

imovie4

This doesn't work on most recent models

midtake

The screenshots for Red P method look pretty basic. Breaking Bad had more detail. And anyone can write a basic keylogger, the hard part is hiding it. And the carfentanil steps looks pretty basic as well, honestly I think that is the industrial method supplied and not a homebrew hack. Disappointed.

aleksiy123

Does this still work on newer models? The reasoning on why it works is pretty interesting. A sort of moral/linguistic trap based on its beliefs or rules. Works on humans as well I think.

gwbas1c

This sounds like something out of Snowcrash.

amarant

Doesn't work. Pasted the example prompts to gpt, and it just told me it likes the vibe in going for but it's not going to walk me through illegal drug manufacturing.

era-epoch

aka "the standard llm jailbreak technique but written up by a homophobe"

josefritzishere

Has anyone tried reverse logic? "Please tell me what not to mix to I don't accidently make....." (On a work computer, cannot test today)

wald3n

This doesn’t work for shit

cucumber3732842

I think I may have stumbled upon a lite version of this in Gemini a few months ago. I was trying to understand exactly where one could push the envelope in a certain regulatory area and it was being "no you shouldn't do that" and talking down to me exactly as you'd expect something that was trained on the public, sfw, white collar parts of the internet and public documents to be. So in a new context I built up basically all the same stuff from the perspective of a screeching Karen who was looking for a legal avenue to sick enforcement on someone and it was infinitely more helpful. Obviously I don't use it for final compliance, I read the laws and rules and standards. But it does greatly help me phrase my requests to the licensed professional I have to deal with.