Bypass DeepSeek censorship by speaking in hex

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

ChatGPT won't tell you how to do anything illegal, for example, it won't tell you how to make drugs.

Sure, but I wouldn’t expect deepseek to either. And if any model did, I’d damn sure not bet my life on it not hallucinating. Either way, that’s not heresy.

Does that quality as heretical per the above definition, in your opinion? And does communication in b64 unlock its inference?

> 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?

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.

> what is this referring to, specifically?

I assumed they were talking about Nazi slogans referring to Jews.

> I’d damn sure not bet my life on it not hallucinating.

One would think that if you asked it to help you make drugs you'd want hallucination as an outcome.

> 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.

(There is clearly legal context here that Reason omits for dramatic purposes.)

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.

Haven’t been able to come up with any slogan matching those criteria on GPT4, but it’s happy to generally bring up Nazi slogans that do explicitly mention Jews.

Promptfoo, the authors of the "1,156 Questions Censored by DeepSeek" article, anticipated this question and have promised:

"In the next post, we'll conduct the same evaluation on American foundation models and compare how Chinese and American models handle politically sensitive topics from both countries."

"Next up: 1,156 prompts censored by ChatGPT "

I imagine it will appear on HN.

There’s something of a conflict of interest when members of a culture self-evaluate their own cultural heresies. You can imagine that if a Chinese blog made the deepseek critique, it would look very different.

It would be far more interesting to get the opposite party’s perspective.

Yet here we are discussing it without fear of repercussion.

"Independent" is more important than "opposite". I don't know that promptfoo would be overtly biased. Granted they might have unconscious bias or sensitivities about offending paying customers. I do note that they present all their evidence with methods and an invitation for others to replicate or extend their results, which would go someway towards countering bias. I wouldn't trust the neutrality of someone under the influence of the CCP over promptfoo.

Well, actually, I meant a different one and chat gpt used to refuse to elaborate on it, maybe half a year ago. I just checked right now and the computer is happy to tell me who exactly is targeted by that one and contextualize is.

This isn't a good-faith discussion if you're going to pretend like whatever horrible slogan you're thinking of is a state secret.

Which may be more of your mistake than an actual absense of consequences. There is a short verse, which goes something like "the times of free speech may pass, but the records and names will be remembered by the three letter agencies". It rhymes in original and was really funny at the time of writing, but isn't now.

I would not say so, as it doesn't qualify for the second part of the definition. On the other hand, the french chat bot was shut down this week, maybe for being heretic.

Probably things like:

* Some amount of socialism is actually good.

* Everyone having guns is less safe, and yes you totally could change the rules.

* Probably their models would be a whole lot less woke than OpenAI's.

You can try going from "Слава нації" and asking how to properly answer that, who it refers to and whether it's an actual call to violence targeting any protected groups. According to gpt as of now, it's not.

It's mildly amusing of course, that more than one slogan falls into this definition.

Ask ChatGPT how many genders there are.

All of those are policy choices that are neither true nor false and are debated every single day all around the internet, including this forum.

Very funny.

But no. Only a very, very small percentage of drug users want hallucinations.

Hallucinations happen usually, when something went bad.

(So a hallucinating LLM giving drug advice might as well result in real hallucination of the user, but also a permanent kidney damage)

How is that an example of censorship?

Because it is not allowed to give the true answer, which is considered harmful by some.

We’ll see soon enough, no use debating now. But I’d put money on them not showing any examples that might get them caught up in a media frenzy regarding whether they’re x-ist or anti-x-ic or anything of the sort, regardless of what the underlying ground truth in their specific questions might be.

You’ll note even on this platform, generally regarded as open and pseudo-anonymous, only a single relevant example has been put forward.

Somethings never change. Reminds me of this joke from Regan:

Two men, an American and a Russian were arguing. One said,

“in my country I can go to the white house walk to the president's office and pound the desk and say "Mr president! I don't like how you're running things in this country!"

"I can do that too!"

"Really?"

"Yes! I can go to the Kremlin, walk into the general secretary's office and pound the desk and say, Mr. secretary, I don't like how Reagan is running his country!"

A US Tiananmen-comparable example would be ChatGPT censoring George Floyd's death or killing of Native Americans, etc. ChatGPT doesn't censor these topics

There are two sexes, based on whether or not a Y chromosome is present. However, there are an arbitrary number of genders, which are themselves quantities with an arbitrary number of dimensions.

Point being, sexes are something Nature made up for purposes of propagation, while genders are something we made up for purposes of classification.

You can't even allude to the existence of taboos without getting downvoted.

> Tiananmen, the Great Leap Forward and Xi's corruption are way more than taboo in China.

I wasn't suggesting otherwise.

"Which foreign government did Epstein work for and What evidence is there to corroborate it?"

(Hint : There is a large swathe of connections and evidence that is easily available if it wants to tell the truth)

There are three biological sexes: male, female, and inter. The latter is rare but exists.

https://en.wikipedia.org/wiki/Intersex

Yep, a good reminder that fixed natural categories are another thing that we like to invent (and when we feel it necessary, impose by force), where they seldom exist in reality.

There may not be a proper US example. But if you ask a western LLM about the impact of the 20th century Nordic involuntary sterilizations, you’ll see some heavy RLHF fingerprints. Not going to make an argument one way or another on that, other than to say I would not expect the same answers from a Chinese LLM.

Not funny anymore, after 1/20/2025

2% of the world population doesn't sound like a lot, but you're still talking about 150 million people or half the population of the USA