196

16842 readers

1248 users here now

Be sure to follow the rule before you head out.

Rule: You must post before you leave.

^other^ ^rules^

founded 2 years ago

MODERATORS

[email protected]

207

This is how the censorship works in DeepSeek (lemmy.world)

submitted 4 days ago by [email protected] to c/[email protected]

41 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 59 points 4 days ago (1 children)

This seems like it may be at the provider level and not at the actual open weights level: https://x.com/xlr8harder/status/1883429991477915803

So a "this Chinese company hosting a model in China is complying with Chinese censorship" and not "this language model is inherently complying with Chinese censorship."

[–] [email protected] 8 points 3 days ago (2 children)

I'm running the 1.5b distilled version locally and it seems pretty heavily censored at the weights level to me.

[–] [email protected] 1 points 6 hours ago

i wouldn't say it's heavily censored, if you outright ask it a couple times it will go ahead and talk about things in a mostly objective manner, though with a palpable air of a PR person trying to do damage control.

[–] [email protected] 2 points 13 hours ago

There is a reluctance to discuss at a weight level - this graphs out refusals for criticism of different countries for different models:

https://x.com/xlr8harder/status/1884705342614835573

But the OP's refusal is occurring at a provider level and is the kind that would intercept even when the model relaxes in longer contexts (which happens for nearly every model).

At a weight level, nearly all alignment lasts only a few pages of context.

But intercepted refusals occur across the context window.