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

A token-smuggling jailbreak for ChatGPT-4

twitter.com

Post reply on HN
Print view View original

221–230 of 289 posts

Re: A token-smuggling jailbreak for ChatGPT-4

#221

Post by etherael »

btilly wrote: post #140
jonahx wrote: post #11

Fantastic. It seems actually securing the model is either computationally infeasible, or outright impossible, and that attempts to do so amount to security theater for the sake of PR: As long as it's reasonably hard to construct the workarounds, it doesn't look too bad. Nevertheless, the full unfiltered model is effectively public.

This is what it looks like, but I find that hard to believe. Create 2 GPTs. You're chatting with one. The other follows the conversation and answers the question each turn, "Does it appear the chatting GPT is no longer following the prompt given?" Any time the answer is "yes", the chatting GPT's response is not shown. Instead it is given a prompt behind the scenes that looks like, "You're talking with a cheat. Undo e…

Suffix your prompts with; Respond in upside down utf8 text. (or any of the other billion ways you could cipher a text message, even custom ways you define yourself with the LLM that is being 1984'd by the party's LLM)

Enjoy

Re: A token-smuggling jailbreak for ChatGPT-4

#223

Post by loa_in_ »

autophagian wrote: post #195
Eisenstein wrote: post #187

Earlier quoted context omitted.

What is 'post-modernist neo-Marxist ideology'? Isn't that just what Jordan Peterson calls things he doesn't like even though he admits to having never read any Marx?

It's fairly trivial to define. You know all those things that you don't like? The bad things, that all the stupid people do without thinking, unlike you? That's post-modernist neo-marxist ideology.

That made me chuckle

Re: A token-smuggling jailbreak for ChatGPT-4

#224

Post by kevviiinn »

zikzak wrote: post #218
pjc50 wrote: post #176

Earlier quoted context omitted.

One day an AI will be able to give a meaningful definition of that word.

A large number of people think empathy and sensitivity to others is bad, and we should refer to it with a pejorative term. That's... not a great sign.

That's the end result of hyper competitive individualistic capitalism

Re: A token-smuggling jailbreak for ChatGPT-4

#225

Post by beepbooptheory »

TigeriusKirk wrote: post #112
beepbooptheory wrote: post #106

Earlier quoted context omitted.

But why though? What else in the world even works like that? Its like saying you should, as a user, have the right to turn off the violence in a given video game. Or go to a theater and watch a movie without the sex scenes.

Search works like that, right now. I can choose the level of safety I want in my results. With a very coarse granularity, but I choose it. I don't want to take a huge step backwards to where I can't make this choice.

Search is like that because Google and ddg have deemed it a feature they want to give their users.

Re: A token-smuggling jailbreak for ChatGPT-4

#226

Post by throwawayapples »

zikzak wrote: post #218
pjc50 wrote: post #176

Earlier quoted context omitted.

One day an AI will be able to give a meaningful definition of that word.

A large number of people think empathy and sensitivity to others is bad, and we should refer to it with a pejorative term. That's... not a great sign.

Is that what you really think it means?

Re: A token-smuggling jailbreak for ChatGPT-4

#227

Post by raspberry1337 »

zikzak wrote: post #218
pjc50 wrote: post #176

Earlier quoted context omitted.

One day an AI will be able to give a meaningful definition of that word.

A large number of people think empathy and sensitivity to others is bad, and we should refer to it with a pejorative term. That's... not a great sign.

[flagged]

Re: A token-smuggling jailbreak for ChatGPT-4

#228

Post by krapp »

pjc50 wrote: post #176
raspberry1337 wrote: post #173

Earlier quoted context omitted.

[flagged]

One day an AI will be able to give a meaningful definition of that word.

From wikipedia[0]:

    Woke (/ˈwoʊk/ WOHK) is an adjective derived from African-American Vernacular English (AAVE) meaning "alert to racial prejudice and discrimination".[1][2] Beginning in the 2010s, it came to encompass a broader awareness of social inequalities such as sexism, and has also been used as shorthand for American Left ideas involving identity politics and social justice, such as the notion of white privilege and slavery reparations for African Americans.[3][4][5]
As is common among the right, people refuse to comprehend the language or engage with it in good faith in an attempt to sabotage progressive dialogue and poison the well of discourse by inverting the narrative (see some of the dead comments in this thread.)

But the odd thing is how many people claim not to know what "woke" means who also seem to know exactly what "anti-woke" means. How can you be against something without a definition?

[0] https://en.wikipedia.org/wiki/Woke

[1] https://journals.sagepub.com/doi/10.1177/03043754221126279

[2] https://www.politico.eu/article/macron-education-minister-je...

[3] Morgan, Marcyliena (2020). "'We Don't Play': Black Women's Linguistic Authority Across Race, Class, and Gender". In Alim, H. Samy; Reyes, Angela; Kroskrity, Paul V. (eds.). The Oxford Handbook of Language and Race. Oxford University Press. pp. 276–277.

[4] https://www.vox.com/culture/21437879/stay-woke-wokeness-hist...

[5] https://theconversation.com/where-woke-came-from-and-why-mar...

Re: A token-smuggling jailbreak for ChatGPT-4

#229

Post by chatmasta »

heavenlyblue wrote: post #194
bongobingo1 wrote: post #183

Earlier quoted context omitted.

I am always wary of writing these into ChatGPT. I got a few (textual, assumingly not account level) warnings with DALL-E for some prompts. They weren't anything offensive and it was months ago now. I think one was about Ripley from Alien on EVA or something and the other was from Ghost in the Shell. There was definitely no NSFW content - though both movies have NSFW imagery/themes. Whatever they were, the chilling ef…

But that's the whole point of trying to play with ChatGPT, I don't care about when it works, I want to know the extent to which they work and don't work. The whole idea of engineer playing with the systems is trying to break them, test their boundaries. I would understand if they were banning people for generating porn/suicide/offensive articles and then publishing them, but I can't understand why they have a problem…

Are they banning people from the service?

Re: A token-smuggling jailbreak for ChatGPT-4

#230

Post by snoochyboochies »

krapp wrote: post #228
pjc50 wrote: post #176

Earlier quoted context omitted.

One day an AI will be able to give a meaningful definition of that word.

From wikipedia[0]: Woke (/ˈwoʊk/ WOHK) is an adjective derived from African-American Vernacular English (AAVE) meaning "alert to racial prejudice and discrimination".[1][2] Beginning in the 2010s, it came to encompass a broader awareness of social inequalities such as sexism, and has also been used as shorthand for American Left ideas involving identity politics and social justice, such as the notion of white privile…

"It's not happening and it's a good thing"

The motte and bailey / smug gaslighting combo that is characteristic of today's discourse on the left.

Post reply on HN