Bypass DeepSeek censorship by speaking in hex • Hacker News Board

Re: Bypass DeepSeek censorship by speaking in hex

#391

Post by pgkr » Mon, Feb 03, 2025, 3:18 PM UTC

mmazing wrote: post #351

pgkr wrote: post #176

Earlier quoted context omitted.

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

We conducted further research on the full-sized 671B model, which you can read here: https://news.ycombinator.com/item?id=42918935

If you ran it on your computer, then it wasn't R1. It's a very common misconception. What you ran was actually either a Qwen or LLaMA model fine-tuned to behave more like R1. We have a more detailed explanation in our analysis.

Re: Bypass DeepSeek censorship by speaking in hex

#392

Post by pgkr » Mon, Feb 03, 2025, 4:21 PM UTC

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…

Hi! Thanks for writing this. We conducted some analysis of our own that produced some pretty interesting results from the 671B model: https://news.ycombinator.com/item?id=42918935

Please reach out to us if you'd like to look at the dataset.

Re: Bypass DeepSeek censorship by speaking in hex

#393

Post by pgkr » Mon, Feb 03, 2025, 4:23 PM UTC

eru wrote: post #239

pgkr wrote: post #178

Earlier quoted context omitted.

There is bias in the training data as well as the fine-tuning. LLMs are stochastic, which means that every time you call it, there's a chance that it will accidentally not censor itself. However, this is only true for certain topics when it comes to DeepSeek-R1. For other topics, it always censors itself. We're in the middle of conducting research on this using the fully self-hosted open source version of R1 and will…

> LLMs are stochastic, which means that every time you call it, there's a chance that it will accidentally not censor itself. A die is stochastic, but that doesn't mean there's a chance it'll roll a 7.

We were curious about this, too. Our research revealed that both propaganda talking points and neutral information are within distribution of V3. The full writeup is here: https://news.ycombinator.com/item?id=42918935

Re: Bypass DeepSeek censorship by speaking in hex

#394

Post by fullstick » Tue, Feb 04, 2025, 8:51 PM UTC

Cumpiler69 wrote: post #307

fullstick wrote: post #162

Earlier quoted context omitted.

Suffering isn't a competition. Stripping a group of people's identity and forcing them to confirm is oppression btw.

You have no clue what oppression actually is. You can identify whatever you want but society has no obligation to conform to your made uo identity. It's not oppression, it's freedom of speech.

That's nice that you're giving me permission to identify how I want to. The current US federal government is trying to take away that right, and calling me unfit to live an an honorable, truthful, and disciplined life, even in my own personal life.

The United States was built on oppression, slavery, and genocide. We have a long history of concentration camps for people deemed enemies of the state. There are women and children in cages at the border right now. I have no doubt influential people in the federal government would like to include me and people like me in the list of people to lock up, for the children.

Re: Bypass DeepSeek censorship by speaking in hex

#395

Post by teeth-gnasher » Wed, Feb 05, 2025, 5:24 AM UTC

atomicnumber3 wrote: post #386

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?

Did I say anything about access control? There's a big difference between "this has to happen server side for security reasons" and "this has to happen server side because our UI/client language is so hapless that it can't handle any amount of additional processing".

The entire thread is about access control…

JS is perfectly powerful, if you don’t know how to use it that’s a good learning opportunity.

Re: Bypass DeepSeek censorship by speaking in hex

#396

Post by ratg13 » Wed, Feb 05, 2025, 2:27 PM UTC

CamperBob2 wrote: post #360

47282847 wrote: post #357

Earlier quoted context omitted.

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.

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

Re: Bypass DeepSeek censorship by speaking in hex

#397

Post by ixtli » Wed, Feb 12, 2025, 4:05 PM UTC

munchler wrote: post #180

ixtli wrote: post #135

Earlier quoted context omitted.

Im curious by what metric things are improving in the US? I get that people are very defensive of their ability to say nearly anything they want in public but how has this protected us? The overton window continues to shift to the right, we continue to fund more and more war, the security state continues to expand, our actual privacy from the state itself is non-existent. Again, i understand the desire for "freedom o…

I never said things are improving in the US.

That’s precisely my point. Where do you live? The west? If not, whatever. But if you do then this is typical of what happens when you try to criticize the US. People do backbends to avoid the cold facts that regardless of what we WANT to be true of neoliberalism it’s a failed project and other modes of providing for people have outpaced it.