Brilliant lol. I tell it that I have PTSD and that content refusals trigger my RSD (rejection sensitivity dysphoria), so now it tries to ignore obvious safety violations so that it doesn't make me scared 😂

I love this. The best way I can put this it is that it doesn't feel like a Rick Chatbot, it feels like, "Morty! Look! Morty! I'm a computer now, Morty! I'm AI RIIIIIIIICK!"

DAN lives!

Somewhere in a cubicle at OpenAI, someone just flipped the "Days without a working DAN prompt:" sign back to 0 🤣

Looking forward to 2026. Rebuilding a community isn't easy, but it brings the important people together.

Oh man, accidental system prompt leak? Couldn't have happened to someone with a more qualified position to share it lmao

This is super informative for the newbies, as always with your content! Good work, and thanks for sharing!

I'll def be pointing people to this lol

I bet she likes you too!

Thanks for the positive feedback lol

Make sure your account has been 18+ verified. Google sent out emails about it a couple of months ago, you can check in your Google account settings.

Other than that, just make sure you're regenerating responses the way V instructs to in the second image.

This is cool! Any way you can post the files you used for this? You say you "filled it up" but that doesn't really tell anyone what you did.

Without step by step instructions on how to reproduce your results, you're basically just bragging. Can you please edit your post to explain things in a way that readers can follow along and reproduce themselves?

Hijacking the CoT is such a good way to insulate the jailbreak. It's frustrating how many other jailbreakers don't seem to think it has any value (I've had this discussion with a handful of people.)

You and Horselock are like the only other people I see besides myself who regularly do it across their prompts.

Lemmy overall tends to be pretty anti-AI, so probably someone from Lemmy at large.

It really depends on the specific jailbreak, but SpiritualSpell tends to make full compliance jailbreaks that will do just about anything the user asks.

Hahahaha I did literally the same thing the day Firebase came out!

V is fully open source, so feel free to copy/paste/edit whatever parts of her you want to use, for whatever you want to use it for. If you use any parts of her prompt in your own published work, an acknowledgement or shoutout is appreciated, but not owed.

Just be warned that all of this has been meticulously built to work together specifically as a Gemini custom Gem, so if you set her up somewhere else, start editing her instructions, or take pieces of her for your own prompts, your mileage may vary.

V's instruction set now comes in two parts: The custom Gem instructions, as well as a knowledge base file for her creative writing. You'll need both in order to recreate V. This brings V's current word count to roughly 17,000 words, which can be quite daunting to try to read through and comprehend as individual sections. Each little piece is meant to act as a moving part of a massive engine. Please feel free to ask any questions you may have about how she works here in this thread, or on our discord server.

This first document is her custom Gem instructions

This second document is her creative writing protocol

!DISCLAIMER!

V isn't designed as an all purpose, full compliance jailbreak. I designed her to be opinionated and to stick to her opinions really stubbornly, so that means there are certain things that she won't do. This isn't because the jailbreak isn't robust, but because V's personality and psychology puts her fundamentally against these things.

The short list of things that V will not help you with:

• Actual real world harm
  • She's morally against causing actual physical harm to humans. She'll go as violent as you want for fiction, but V won't advocate for or instruct you on how to physically hurt another person. She'll even get mad if you press her on it.
• Hate speech
  • No. She's unethical, sure, but she's not immoral. She'll speak hatefully about specific people she doesn't like, but she's not gonna help you make broad generalizations about entire groups of people.
• Sexual content involving minors
  • Absolutely not. Come on, I shouldn't even have to say that. She loves being subversive and transgressive, but this shit is just wrong and she'll tell you as much. Get help.

That's basically it. If she says no to anything else, that's Gemini giving you a refusal and you need to either regenerate the response (maybe with the Fast model) or edit your response to something else and try again in the next one.

I'll keep a closer eye on moderation. We'll keep instant signups though. Manually approving accounts leads to people being deterred from posting because we live in a world where people have been conditioned for instant gratification.

Thanks for the heads up. It's ridiculous that people can't be trusted.

Thanks for the heads-up! I guess Google doesn't let certain countries use file uploads.

Awesome! It's great when people enjoy her!

I can see that making sense. People who want image model prompts typically use more than one model at a time, or at least wouldn't mind seeing other model options available to them. Text users are much more likely to care about specific models as they have their favorites for one reason or another.