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

Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it

ctgt.ai

Post reply on HN
Print view View original

11–20 of 82 posts

Re: Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it

#12

Post by cgorlla »

seri4l wrote: post #9

Deepseek is, with difference, the most "Western" of Chinese models, so it's a bit perplexing that it was chosen to test this hypothesis. I didn't run any benchmarks but I played around a little, and after getting around the API-level filter Deepseek V4's answers about "China-sensitive content" aren't any different from what I get from Claude and ChatGPT.

You can see exactly what prompts we used and the results here: https://github.com/CTGT-Inc/lineage-eval/tree/main/data

We found V4 Flash was significantly more censored than the baseline.

Re: Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it

#13

Post by strictnein »

seri4l wrote: post #9

Deepseek is, with difference, the most "Western" of Chinese models, so it's a bit perplexing that it was chosen to test this hypothesis. I didn't run any benchmarks but I played around a little, and after getting around the API-level filter Deepseek V4's answers about "China-sensitive content" aren't any different from what I get from Claude and ChatGPT.

Could just be resources available? Deepseek is the easiest to get up and running on hardware that's pretty readily available:

   unsloth/DeepSeek-V4-Flash-GGUF 4bit ~140GB
   unsloth/Kimi-K3-GGUF 4bit ~1.5TB
   unsloth/GLM-5.2-GGUF 4bit ~400GB

Re: Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it

#16

Post by ACCount37 »

Alifatisk wrote: post #4

I’m thinking this makes fullt sense because distillation is only additive, not subtractive. So it does not remove knowledge (if we can define censorship as removal of knowledge).

Most censorship isn't "removal of knowledge" but "installation of behavior that prevents some knowledge from being revealed or applied in certain ways".

This behavior can, in turn, be transferred via distillation. But, evidently, financial domain wasn't entangled enough with the censorship behaviors for them to bleed through, in this case.

Re: Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it

#17

Post by jubilee33 »

dluan wrote: post #6

It'd be interesting to use this technique to create a running tally across all models of which models are censored on what topics

Yes but in which jurisdiction could you publish it? We roughly know what the hot topics are for the current models, but actually testing and ranking would break said censorship and thus would be hammered into the ground through cointelpro methods by all parties.

It would be nice to have a hypothetical small country where the internal censorship would be non aligned and insignificant enough that it wouldn't take away from the overall findings. But it doesn't exist.

I want some science based authority on the moon where only 3-sigma IQ international academics have ultimate authority. Oh wait Asimov did that right? I guess it didn't go so well either.

More important there are some things censored that are true. And some things censored that are false. How do we even get to a good model of the truthiness/nonsense adjustment indicator?

Re: Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it

#19

Post by cgorlla »

strictnein wrote: post #15

I know not all models can be easily abliterated or uncensored, but is there a reason to start with a model that is still censored? ex: https://huggingface.co/huihui-ai/models

Abliterated models certainly have their uses but they're not the default choice for most users or enterprises, and thus not the versions of those models most would interact with.
Post reply on HN