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

351–360 of 397 posts

Re: Bypass DeepSeek censorship by speaking in hex

#351

Post by mmazing »

pgkr wrote: post #176
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…

Correct. The bias is baked into the weights of both V3 and R1, even in the largest 671B parameter model. We're currently conducting analysis on the 671B model running locally to cut through the speculation, and we're seeing interesting biases, including differences between V3 and R1. Meanwhile, we've released the first part of our research including the dataset: https://news.ycombinator.com/item?id=42879698

I have not found any censorship running it on my local computer.

https://imgur.com/xanNjun

Re: Bypass DeepSeek censorship by speaking in hex

#352

Post by mmazing »

homebrewer wrote: post #295
nicce wrote: post #237

Earlier quoted context omitted.

Is it really in the model? I haven’t found any censoring yet in the open models.

Really? Local DeepSeek refuses to talk about certain topics (like Tiananmen) unless you prod it again and again, just like American models do about their sensitive stuff (which DeepSeek is totally okay with — I spent last night confirming just that). They're all badly censored which is obvious to anyone outside both countries.

Not my experience - https://imgur.com/xanNjun just ran this moments ago.

Re: Bypass DeepSeek censorship by speaking in hex

#353

Post by miohtama »

yndoendo wrote: post #327
miohtama wrote: post #264

Earlier quoted context omitted.

They have the same fear as everyone else "teenager learns how to cook napalm from an AI"

Don't need AI for such things. Just search for the Anarchist Cookbook in a search engine. [0] Amazon even sells it. [0] https://www.amazon.com/Anarchist-Cookbook-William-Powell/dp/...

Exactly

Re: Bypass DeepSeek censorship by speaking in hex

#354

Post by ImHereToVote »

bloppe wrote: post #348
IOUnix wrote: post #330

Earlier quoted context omitted.

I was going to say this as well. To say the human brain is a statistical machine is infinitely reductionistic being that we don't really know what the human brain is. We don't truly understand what consciousness is or how/where it exists. So even if we understand 99.99~ percent of the ohaycial brain, not understanding that last tiny fraction of it that is core consciousness means what we think we know about it can be…

Not an expert but Sam Harris says consciousness does not exist

Well if Sam Harris says it.

Re: Bypass DeepSeek censorship by speaking in hex

#355

Post by ImHereToVote »

unoti wrote: post #346
timeattack wrote: post #281

Earlier quoted context omitted.

Thing that I don't understand about LLMs at all, is that how it is possible to for it to "understand" and reply in hex (or any other encoding), if it is a statistical "machine"? Surely, hex-encoded dialogues is not something that is readily present in dataset? I can imagine that hex sequences "translate" to tokens, which are somewhat language-agnostic, but then why quality of replies drastically differ depending on w…

> Thing that I don't understand about LLMs at all, is that how it is possible to for it to "understand" and reply in hex (or any other encoding), if it is a statistical "machine" It develops understanding because that's the best way for it to succeed at what it was trained to do. Yes, it's predicting the next token, but it's using its learned understanding of the world to do it. So this it's not terribly surprising i…

This comment will be very down voted. It is statistically likely to invoke an emotional response.

Re: Bypass DeepSeek censorship by speaking in hex

#356

Post by 47282847 »

DonHopkins wrote: post #340
nonrandomstring wrote: post #261

Earlier quoted context omitted.

> it implies that at least every business that builds something that can move information around must be knowledgeable about tianenman square Everyone's heard of the "Streisand effect", but there's layers of subtlety. A quite famous paper in attachment psychology by John Bowlby "On knowing what you are not supposed to know and feeling what you are not supposed to feel" is worth considering. Constructive ignorance (li…

Jokes and the Logic of the Cognitive Unconscious Marvin Minsky, Published 1 November 1980 Freud’s theory of jokes explains how they overcome the mental “censors” that make it hard for us to think “forbidden” thoughts. But his theory did not work so well for humorous nonsense as for other comical subjects. In this essay I argue that the different forms of humor can be seen as much more similar, once we recognize the i…

This is why no repressive government or ruler can allow comedy and sarcasm.

Re: Bypass DeepSeek censorship by speaking in hex

#357

Post by 47282847 »

CamperBob2 wrote: post #240
throw_pm23 wrote: post #188

Earlier quoted context omitted.

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

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.

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

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

Re: Bypass DeepSeek censorship by speaking in hex

#358

Post by daxfohl »

tossaway2000 wrote: post #3

> I wagered it was extremely unlikely they had trained censorship into the LLM model itself. I wonder why that would be unlikely? Seems better to me to apply censorship at the training phase. Then the model can be truly naive about the topic, and there's no way to circumvent the censor layer with clever tricks at inference time.

I think there's no better proof than this that they stole a big chunk of OpenAI's model.

Re: Bypass DeepSeek censorship by speaking in hex

#359

Post by B1FF_PSUVM »

CSSer wrote: post #316
B1FF_PSUVM wrote: post #315

Earlier quoted context omitted.

> not as statistical machines, but geometric machines. When you train LLMs you are essentially moving concepts around in a very high dimensional space. That's intriguing, and would make a good discussion topic in itself. Although I doubt the "we have the same thing in [various languages]" bit.

What do you mean, exactly, about the doubting part? I thought it was fairly well known that LLMs possess superior translation capabilities.

Sometimes you do not have the same concepts - life experiences are different.

Re: Bypass DeepSeek censorship by speaking in hex

#360

Post by CamperBob2 »

47282847 wrote: post #357
CamperBob2 wrote: post #240

Earlier quoted context omitted.

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.

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.
Post reply on HN