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

Bypass DeepSeek censorship by speaking in hex

substack.com

Post reply on HN
Print view View original

91–100 of 397 posts

Re: Bypass DeepSeek censorship by speaking in hex

#91

Post by zoklet-enjoyer »

poincaredisk wrote: post #69
JumpCrisscross wrote: post #58

Earlier quoted context omitted.

> The One-China Principle is a widely recognized consensus in the international community This is baloney. One country, two systems is a clever invention of Deng's we went along with while China spoke softly and carried a big stick [1]. Xi's wolf warriors ruined that. Taiwan is de facto recognised by most of the West [2], with defence co-operation stretching across Europe, the U.S. [3] and--I suspect soon--India [4].…

What do you base your expectations on? Looking at the historical data, the trend is in the other direction and many more countries used to recognize Taiwan before. [1] In case you're not aware, you need to pick if you recognise Taiwan of mainland China. They both claim to be the same country, so you can't have diplomatic relationships with both. And since mainland China is, umm, a very important and powerful country,…

There are a couple more options.

Recognize both. They both may be upset and not have any diplomatic relationship with you, but that's ok.

Recognize neither.

Re: Bypass DeepSeek censorship by speaking in hex

#92

Post by mosselman »

easel wrote: post #85

Interestingly, there’s a degree of censorship embedded in the models+weights running locally via Ollama. I don’t want to make strong statements about how it’s implemented, but it’s quite flexible and clamps down on the chain of thought, returning quickly with “I am sorry, I cannot answer that question. I am an AI assistant designed to provide helpful and harmless responses.” You can get it to talk about Tiananmen Squ…

It gets censored in 8B for me.

Re: Bypass DeepSeek censorship by speaking in hex

#93

Post by munchler »

ixtli wrote: post #57
munchler wrote: post #43

Earlier quoted context omitted.

The MOVE bombing was thoroughly reported at the time and litigated afterwards. The underlying causes were addressed, at least to some extent, and nothing like it has happened again in Philly since then, AFAIK. That’s why it isn’t well known today. It was a horrible event, but comparing it rationally to Tiananmen Square doesn’t confirm your conclusion.

How do you know this isn't what happened in China? Also, the underlying causes being addressed is like saying that redlining no longer exists because its not called that or that racism is gone because we no long live in Jim Crow times. The US has not moved on from that time nor has it gotten any better than the kent state shooting. If anything these conditions have worstened and when these shootings and lynchings hap…

I understand that you're unhappy with the state of things in the US, but setting up a false equivalence with China doesn't make your case.

The simple fact that we can have this discussion without fear of imprisonment is strong evidence that when it comes to censorship (the topic of this post), the US is still way more open than China.

Re: Bypass DeepSeek censorship by speaking in hex

#94

Post by LinXitoW »

JumpCrisscross wrote: post #90
cubefox wrote: post #75

Earlier quoted context omitted.

Chinese models may indeed be more likely to not distort or lie about certain topics that are taboo in the West. Of course mentioning them here on Hacker News would be taboo also.

> mentioning them here on Hacker News would be taboo also Tiananmen, the Great Leap Forward and Xi's corruption are way more than taboo in China. It's difficult for Americans to really understand the deliberate forgetting people do in coercive socieites. The closest I can describe is a relative you love going in early-stage dementia, saying horrible things that you sort of ignore and almost force yourself to forget.…

In a world where the presidents closest "friend" can do a Hitler salute, twice, people are more focussed on getting Pro Palestinians fired, arrested, etc.

That very much fits any of the censorship China has going on.

Re: Bypass DeepSeek censorship by speaking in hex

#95

Post by noman-land »

dylan604 wrote: post #72
teeth-gnasher wrote: post #67

Earlier quoted context omitted.

The need to manage data access on the server does not go away when you stop using javascript. Is there something specifically about Swing that somehow provides proper access control, or is it simply the case that it is slightly more work to circumvent the front end when it doesn’t ship with built in dev tools?

The built-in dev tools is the key thing. If there was no way for the client to manipulate things, it wouldn't be too far off from other local apps. Reversing is always going to be a threat vector, but the low bar to entry of using the dev tools makes it a non-starter for me. If using Ghirdra was as simple as using the dev tools, the software industry would collapse.

The built in dev tools are fundamental to an open web. If you don't want someone to look at something in their own possession then don't send it to them in the first place. Obfuscating it is rude and is false security anyway.

The grand rule is don't trust the client. People break this rule and then try to paper over it with obfuscation, blame, and tightening their control.

Re: Bypass DeepSeek censorship by speaking in hex

#96

Post by dheera »

tills13 wrote: post #16
lxe wrote: post #4

You can also intercept the xhr response which would still stop generation, but the UI won't update, revelaing the thoughts that lead to the content filter: const filter = t => t?.split('\n').filter(l => !l.includes('content_filter')).join('\n'); ['response', 'responseText'].forEach(prop => { const orig = Object.getOwnPropertyDescriptor(XMLHttpRequest.prototype, prop); Object.defineProperty(XMLHttpRequest.prototype, p…

insane that this is client-side.

Not really if you understand how China works.

DeepSeek software developers are not the ones who want to censor anything. There is just a universal threat from getting shut down by the government if the model starts spitting out a bunch of sensitive stuff, so any business in China needs to be proactive about voluntarily censoring things that are likely to be sensitive, if they want to stay in business.

If your censorship implementation is good enough for 99.9% of people to get censored, you're good. A client-side implementation is good enough until/unless a lot of people start exploiting it, in which case you should put effort and proactively do something else to restore it to 99.9%, e.g. move it to the backend. If the government sees that you are being proactive about it, you'll still be fine. At that point, maybe you will still find 0.1% of people bypassing censorship with some highly obscure and difficult jailbreak, but that probably doesn't matter. If that difficult jailbreak becomes widely known, then be proactive again.

Re: Bypass DeepSeek censorship by speaking in hex

#97

Post by martin-t »

JumpCrisscross wrote: post #62
martin-t wrote: post #53

Earlier quoted context omitted.

I would say pacified instead of hopeless. All power in the real world comes from violence. This is increasingly a taboo to say but when you think about it, it becomes obvious. How do you put someone in prison without the ability to physically move and keep them there? You don't. That's why the state employs violence to do it. (1) In fact, the state's capacity for violence is so large that very few people even think a…

> the state's capacity for violence is so large that very few people even think about challenging it People are constantly challenging it. Pull back the threat of violence in most communities and you immediately get disaster.

I believe most of what you're referring to are different situations such as people acting on impulses - either not considering the outcome or being resigned to it.

Another key difference is usually those take place between individuals with roughly the same amount of power (typical disputes, crimes of passion, etc.) and by individuals with more power towards those with less (bullying, abuse, etc.).

People actually taking systematic thought-out steps to infringe on the state's monopoly and doing it from a position of low amounts of power towards a position with high amounts of power are rare and get "charged"[1] with terrorism because that line of thinking is threatening the existing hierarchical power structures and they will absolutely protect themselves.

[1] The word meaning the state selects which parts of its rulebooks it will begin performing against an individual and announces it publicly in order to reinforce the legitimacy of its actions.

Re: Bypass DeepSeek censorship by speaking in hex

#98

Post by femto »

0x7d wrote: post #78

Hi HN! This is my article! It was great to put together a writeup of a fun evening or two of work. It looks like this goes much deeper. I'm learning a lot from some of the linked articles, one of the base hypothesise of my work was that the filtering was distinct from the model, due to the cost of training with pre-filtered or censored data at scale: https://arxiv.org/abs/2307.10719 , let alone- making it generate a…

In the HN discussion you link to, I went through exactly the process that you are going through now! I too thought the censorship was just a thin wrapper around the model, as I had not understood the article I had read until it was explained to me.

Re: Bypass DeepSeek censorship by speaking in hex

#99

Post by JumpCrisscross »

LinXitoW wrote: post #94
JumpCrisscross wrote: post #90

Earlier quoted context omitted.

> mentioning them here on Hacker News would be taboo also Tiananmen, the Great Leap Forward and Xi's corruption are way more than taboo in China. It's difficult for Americans to really understand the deliberate forgetting people do in coercive socieites. The closest I can describe is a relative you love going in early-stage dementia, saying horrible things that you sort of ignore and almost force yourself to forget.…

In a world where the presidents closest "friend" can do a Hitler salute, twice, people are more focussed on getting Pro Palestinians fired, arrested, etc. That very much fits any of the censorship China has going on.

> a world where the presidents closest "friend" can do a Hitler salute, twice, people are more focussed on getting Pro Palestinians fired, arrested, etc. That very much fits any of the censorship China has going on

No, it doesn't. You're criticising in-group blindness. That's a problem. But it's mitigated by a competitive political system because each group has an incentive to call out the other's blinds spots. When this competition ceases, you get groupthink. The last major era of American groupthink was the W. Bush White House. It preceded America's greatest geopolitical disasters in decades.

Under Xi, China went from having quiet competition within the CCP to reigning in a state of groupthink. We don't know what moronic ideas Xi's friends hold because there is nobody in power with an incentive to call that sort of thing out.

Re: Bypass DeepSeek censorship by speaking in hex

#100

Post by JumpCrisscross »

martin-t wrote: post #97
JumpCrisscross wrote: post #62

Earlier quoted context omitted.

> the state's capacity for violence is so large that very few people even think about challenging it People are constantly challenging it. Pull back the threat of violence in most communities and you immediately get disaster.

I believe most of what you're referring to are different situations such as people acting on impulses - either not considering the outcome or being resigned to it. Another key difference is usually those take place between individuals with roughly the same amount of power (typical disputes, crimes of passion, etc.) and by individuals with more power towards those with less (bullying, abuse, etc.). People actually tak…

> most of what you're referring to are different situations such as people acting on impulses - either not considering the outcome or being resigned to it

Nah, those are hooligans. They're a nuisance, but they aren't dangerous. In my experience, when the police are distracted (e.g. by a large protest), the real damage comes from organised crime.

Post reply on HN