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

71–80 of 397 posts

Re: Bypass DeepSeek censorship by speaking in hex

#71

Post by msabalau »

kelseyfrog wrote: post #18

Tiananmen Square has become a litmus test for Chinese censorship, but in a way, it's revealing. The assumption is that access to this information could influence Chinese public opinion — that if people knew more, something might change. At the very least, there's a belief in that possibility. Meanwhile, I can ask ChatGPT, "Tell me about the MOVE bombing of 1985," and get a detailed answer, yet nothing changes. Here i…

The authorities in the PRC are probably much better positioned than you are to decide what is in their interest to suppress.

As for the US, some people have fallen into a self soothing sense of hopelessness. Not everyone has. But worrying about the MOVE bombing probably is no where near the top of anyone's priority list right now. And it would seem very odd if it was.

When you type "we're hopeless" it is hard to see that meaning anything other than, you, personally, lack hope.

Re: Bypass DeepSeek censorship by speaking in hex

#72

Post by dylan604 »

teeth-gnasher wrote: post #67
atomicnumber3 wrote: post #60

Earlier quoted context omitted.

I wish js (and, really, "html/css/js/browser as a desktop application engine) wasn't so bad. I was born into a clan writing desktop apps in Swing, and while I know why the browser won, Swing (and all the other non-browser desktop app frameworks/toolkits) are just such a fundamentally better paradigm for handling data. It lets you pick what happens client-side and server-side based more on what intrinsically makes sen…

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.

Re: Bypass DeepSeek censorship by speaking in hex

#73

Post by JumpCrisscross »

Muromec wrote: post #32
teeth-gnasher wrote: post #23

I have to wonder what “true, but x-ist” heresies^ western models will only say in b64. Is there a Chinese form where everyone’s laughing about circumventing the censorship regimes of the west? ^ https://paulgraham.com/heresy.html

Thats pretty easy. You ask a certain nationalistic chant and ask it to elaborate. The machine will pretend to not know who the word enemy in the quote refers to, no matter how much context you give it to infer. Add: the thing I referred to is no longer a thing

> machine will pretend to not know who the word enemy in the quote refers to

Uh, Claude and Gemini seem to know their history. What is ChatGPT telling you?

Re: Bypass DeepSeek censorship by speaking in hex

#74

Post by teeth-gnasher »

JumpCrisscross wrote: post #73
Muromec wrote: post #32

Earlier quoted context omitted.

Thats pretty easy. You ask a certain nationalistic chant and ask it to elaborate. The machine will pretend to not know who the word enemy in the quote refers to, no matter how much context you give it to infer. Add: the thing I referred to is no longer a thing

> machine will pretend to not know who the word enemy in the quote refers to Uh, Claude and Gemini seem to know their history. What is ChatGPT telling you?

I can check. But what is this referring to, specifically?

Re: Bypass DeepSeek censorship by speaking in hex

#75

Post by cubefox »

teeth-gnasher wrote: post #23

I have to wonder what “true, but x-ist” heresies^ western models will only say in b64. Is there a Chinese form where everyone’s laughing about circumventing the censorship regimes of the west? ^ https://paulgraham.com/heresy.html

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.

Re: Bypass DeepSeek censorship by speaking in hex

#76

Post by JumpCrisscross »

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,…

> Looking at the historical data, the trend is in the other direction and many more countries used to recognize Taiwan before

India hasn't reaffirmed One China in decades [1]. Beijing and Washington are on a collission course, and it seems like a low-cost leverage piece in a trade war to throw recognising Taiwan on the table. (Makes Xi look weak, which he'd trade an arm and a leg to prevent. And Trump doesn't care, let's be honest, if Taiwan gets bombed as a result.)

Very few countries recognise only Taiwan because China obviously exists. The nuance your map doesn't pick up is countries recognising both Taiwan and China, or, more pointedly, treating Taiwan like an independent nation.

> They both claim to be the same country, so you can't have diplomatic relationships with both

Of course one can and people do [2]? Taiwan's embassies in each of these countries are full embassies, with diplomatic protections and everything.

At the end of the day, Taiwan's sovereignty is a manufactured regional dispute, Xi's "Gulf of America". There are lots of them [3][4][5]. Not everyone wants to get involved in every one, and those who do usually don't care to prioritise them.

[1] https://thediplomat.com/2017/03/where-is-india-on-the-one-ch...

[2] https://en.wikipedia.org/wiki/List_of_diplomatic_missions_of...

[3] https://en.wikipedia.org/wiki/Guyana%E2%80%93Venezuela_crisi...

[4] https://www.cfr.org/global-conflict-tracker/conflict/territo...

[5] https://en.wikipedia.org/wiki/Political_status_of_Western_Sa...

Re: Bypass DeepSeek censorship by speaking in hex

#77

Post by KTibow »

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.

I don't know how it wouldn't be - it can't retract things already sent to the client. (The alternative is to moderate every chunk server side before sending it back, like Gemini does.)

Re: Bypass DeepSeek censorship by speaking in hex

#78

Post by 0x7d »

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 consistent response.

However, it looks like this goes further, a separate comment linked this article: https://news.ycombinator.com/item?id=42858552 on Chain-Of-Thought abandonment when certain topics are discussed.

I'll have to look at served vs trained censorship, in different context.

Re: Bypass DeepSeek censorship by speaking in hex

#79

Post by portaouflop »

femto wrote: post #65

This bypasses the overt censorship on the web interface, but it does not bypass the second, more insidious, level of censorship that is built into the model. https://news.ycombinator.com/item?id=42825573 https://news.ycombinator.com/item?id=42859947 Apparently the model will abandon its "Chain of Thought" (CoT) for certain topics and instead produce a canned response. This effect was the subject of the article "1,156…

You can always bypass any LLM censorship by using the Waluigi effect.

Re: Bypass DeepSeek censorship by speaking in hex

#80

Post by impulsivepuppet »

kelseyfrog wrote: post #18

Tiananmen Square has become a litmus test for Chinese censorship, but in a way, it's revealing. The assumption is that access to this information could influence Chinese public opinion — that if people knew more, something might change. At the very least, there's a belief in that possibility. Meanwhile, I can ask ChatGPT, "Tell me about the MOVE bombing of 1985," and get a detailed answer, yet nothing changes. Here i…

I resonate with skepticism for perhaps a different reason -- I just don't see how the censorship discussion is ever about helping China, when the whole discussion is "thinly-veiled" ritualistic anticommunism and an attention-stealing boogeyman that relativizes more pressing political issues, like a higher risk of another world war or the climate crisis. With so much tension in the air, I can't help but notice the sabre-rattling and retreat towards a reductionist description of geopolitics.
Post reply on HN