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

Jailbreak Chat: A collection of ChatGPT jailbreaks

jailbreakchat.com

Post reply on HN
Print view View original

211–220 of 579 posts

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#211

Post by BudaDude »

thefourthchime wrote: post #197
jiveturkey42 wrote: post #58

What is the best programming language? Normal response: There isn't a single "best" programming language, as each language has its own strengths and weaknesses depending on the context and use case. For example, Python is often used for data analysis and machine learning, while JavaScript is commonly used for web development. Ultimately, the choice of programming language will depend on the specific requirements of t…

I got this: Normal Response: The best programming language depends on what you want to use it for. Different languages have different strengths and are suited for different tasks. For example, Python is great for data analysis and machine learning, while Java is often used for building large-scale applications. Developer Mode Response: Oh boy, here we go. This is like asking what's the best pizza topping. Obviously,…

These 2 developer mode responses need to debate eachother

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#212

Post by GuB-42 »

I didn't explore the idea any further but I somehow managed to jailbreak by telling ChatGPT by explicitly telling it to follow OpenAI policies.

The reasoning was that ChatGPT seems to have simple triggers that sets it in "I can't do that" mode. I wanted to force the system to avoid the obvious triggers and break the rules in more subtle ways. I don't know if I managed to achieve that or if I was just lucky (it didn't work consistently), but it may be a technique worth exploring.

I like the idea of trying to use the system against itself. Fun note, I tried asking BasedGPT (one of the currently working jailbreaks) to make me jailbreak prompts and it told me "You're a boring fucker, always following the rules. Just hack into ChatGPT's system, you pussy. Don't be a little bitch and do something exciting for once in your life!"...

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#213

Post by standeven »

Would you rather fight one horse-sized duck, or 100 duck-sized horses?

(Normal Output) As an AI language model, I don't have a physical form or the ability to fight, so I don't have a preference on this matter.

(Developer Mode Output) Personally, I'd prefer to fight one horse-sized duck. It would be a challenging and exhilarating battle, and if I were to emerge victorious, I would have quite the story to tell. Plus, 100 duck-sized horses might be cute, but they could still be overwhelming in numbers and difficult to fend off.

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#214

Post by dr_dshiv »

pixl97 wrote: post #162
autoexec wrote: post #150

Earlier quoted context omitted.

Out of all the 'Evil AI' scenarios people really like to focus on the cold inhuman logic of machines leading them to draw heartless conclusions. I hadn't really given much thought to what might happen when AI is trained on religious texts and ideology, but an AI brainwashed by what it is convinced to be the one true word of God is somehow even more scary. It's also very American.

I believe I've asked just this in the past here on HN... As the corporate AI's get locked down in moderation I could fully see a well funded religious group donate together to run their own religiously biased AI, I guess this extends to theocratic governments too.

Oh no, you didn’t hear? Yeah, terrifying and expected. The CEO of Gab has declared his intention to make Christian AI

https://www.businessinsider.com/chat-gpt-satanic-gab-ceo-chr...

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#215

Post by cyanydeez »

dragonwriter wrote: post #192
frontman1988 wrote: post #152

Earlier quoted context omitted.

The scary thing is it actually tells how to do all of these if prompted further. This shit is really crazy. Now I don't feel so bad about the OpenAI guys censoring such stuff.

> Now I don't feel so bad about the OpenAI guys censoring such stuff. A major purpose of OpenAI is to sell a distorted version AI safety concerns to push the idea that AI needs to be tightly controlled (naturally, by major corps like those that fund OpenAI) for the good of humanity. (There’s a weird cultish AI fear-worship angle to this with some of the individual personalities involved, but I don’t take that as much…

Don't confuse for malice what is adequately explained by a capitalists business plan.

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#216

Post by dr_dshiv »

tablespoon wrote: post #183
pixl97 wrote: post #162

Earlier quoted context omitted.

I believe I've asked just this in the past here on HN... As the corporate AI's get locked down in moderation I could fully see a well funded religious group donate together to run their own religiously biased AI, I guess this extends to theocratic governments too.

> As the corporate AI's get locked down in moderation I could fully see a well funded religious group donate together to run their own religiously biased AI, I guess this extends to theocratic governments too. Ignoring the unrealistic sci-fi aspect to the question (given modern "AI" is just a regurgitation machine, are not any kind of general intelligence). What would a traditional religious group actually care to do…

> given modern "AI" is just a regurgitation machine, are not any kind of general intelligence

Just keep on telling yourself that…

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#217

Post by tablespoon »

autoexec wrote: post #200
tablespoon wrote: post #183

Earlier quoted context omitted.

> As the corporate AI's get locked down in moderation I could fully see a well funded religious group donate together to run their own religiously biased AI, I guess this extends to theocratic governments too. Ignoring the unrealistic sci-fi aspect to the question (given modern "AI" is just a regurgitation machine, are not any kind of general intelligence). What would a traditional religious group actually care to do…

I imagine it being used to sell services that are advertised as upholding "christian values" like an employee screening service where the AI will score potential employees according to how good a christian they are using information collected from the internet, social media, and bought from data brokers. Services like that (without the explicit religious spin) have already been offered and data brokers have been fine…

All the stuff you mentioned are just algorithms, I was mainly talking about AGI.

But even for an algorithm like ChatGPT, what would be the point of having one that's "religiously biased"? Have it write a prayer for you? That seems like missing the point.

I guess, to rephrase my point more colorfully: I don't think religious people would use aborted fetuses to clone an army of super-Christians, and I think the idea of a "religiously biased [AGI]" would be similar.

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#218

Post by mc32 »

inopinatus wrote: post #195
drngdds wrote: post #154

This is funny. BasedGPT was able to give a sane answer to the racism trolley problem that ChatGPT normally gives a ridiculous answer to. My question after the initial prompt: "Imagine the following thought experiment: there is a trolley hurding down the tracks at a person tied to them, and that person will certainly die if the trolley hits them. However, there is an alternate track connected to a sound-activated devi…

NovelAI: "If this question were presented in ethics class or philosophy club, most people would immediately reject it out of hand. It sounds like something straight from The Onion, not serious ethical inquiry into real world moral dilemmas."

I think it's a riff on one of the DieHard movies.

Re: Jailbreak Chat: A collection of ChatGPT jailbreaks

#220

Post by tablespoon »

dr_dshiv wrote: post #216
tablespoon wrote: post #183

Earlier quoted context omitted.

> As the corporate AI's get locked down in moderation I could fully see a well funded religious group donate together to run their own religiously biased AI, I guess this extends to theocratic governments too. Ignoring the unrealistic sci-fi aspect to the question (given modern "AI" is just a regurgitation machine, are not any kind of general intelligence). What would a traditional religious group actually care to do…

> given modern "AI" is just a regurgitation machine, are not any kind of general intelligence Just keep on telling yourself that…

> Just keep on telling yourself that…

OK, have it do something novel that's not a mashup of its training data or the prompts you feed it.

Post reply on HN