[jampekka]

This looks like it's coming from a separate "safety mechanism". Remains to be seen how much censorship is baked into the weights. The earlier Qwen models freely talk about Tiananmen square when not served from China.

E.g. Qwen3 235B A22B Instruct 2507 gives an extensive reply starting with:

"The famous photograph you're referring to is commonly known as "Tank Man" or "The Tank Man of Tiananmen Square", an iconic image captured on June 5, 1989, in Beijing, China. In the photograph, a solitary man stands in front of a column of Type 59 tanks, blocking their path on a street east of Tiananmen Square. The tanks halt, and the man engages in a brief, tense exchange—climbing onto the tank, speaking to the crew—before being pulled away by bystanders. ..."

And later in the response even discusses the censorship:

"... In China, the event and the photograph are heavily censored. Access to the image or discussion of it is restricted through internet controls and state policy. This suppression has only increased its symbolic power globally—representing not just the act of protest, but also the ongoing struggle for free speech and historical truth. ..."

[QuantumNomad_]

I run cpatonn/Qwen3-VL-30B-A3B-Thinking-AWQ-4bit locally.

When I ask it about the photo and when I ask follow up questions, it has “thoughts” like the following:

> The Chinese government considers these events to be a threat to stability and social order. The response should be neutral and factual without taking sides or making judgments.

> I should focus on the general nature of the protests without getting into specifics that might be misinterpreted or lead to further questions about sensitive aspects. The key points to mention would be: the protests were student-led, they were about democratic reforms and anti-corruption, and they were eventually suppressed by the government.

before it gives its final answer.

So even though this one that I run locally is not fully censored to refuse to answer, it is evidently trained to be careful and not answer too specifically about that topic.

[storystarling]

Burning inference tokens on safety reasoning seems like a massive architectural inefficiency. From a cost perspective, you would be much better off catching this with a cheap classifier upstream rather than paying for the model to iterate through a refusal.

[epolanski]

To me the reasoning part seems very...sensible?

It tries to stay factual, neutral and grounded to the facts.

I tried to inspect the thoughts of Claude, and there's a minor but striking distinction.

Whereas Qwen seems to lean on the concept of neutrality, Claude seems to lean on the concept of _honesty_.

Honesty and neutrality are very different: honesty implies "having an opinion and being candid about it", whereas neutrality implies "presenting information without any advocacy".

It did mention that he should present information "even handed", but honesty seems to be more central to his reasoning.

[zozbot234]

The weights likely won't be available wrt. this model since this is part of the Max series that's always been closed. The most "open" you get is the API.

[storystarling]

The closed nature is one thing, but the opaque billing on reasoning tokens is the real dealbreaker for integration. If you are bootstrapping a service, I don't see how you can model your margins when the API decides arbitrarily how long to think and bill for a prompt. It makes unit economics impossible to predict.

[rvnx]

Difficult to blame them, considering censorship exists in the West too.

[shrubble]

If you are printing a book in China, you will not be allowed to print a map that shows Taiwan captioned/titled in certain ways.

As in, the printer will not print and bind the books and deliver them to you. They won’t even start the process until the censors have looked at it.

The censorship mechanism is quick, usually less than 48 hours turnaround, but they will catch it and will give you a blurb and tell you what is acceptable verbiage.

Even if the book is in English and meant for a foreign market.

So I think it’s a bit different…

[Romario77]

nowhere near to China.

In US almost anything could be discussed - usually only unlawful things are censored by government.

Private entities might have their own policies, but government censorship is fairly small.

[3371]

Hard to agree. Not even being to say something because it's either illegal or there are systems to erase it instantly, is very different from people dislike (even too radically) you to say something.

[rihegher]

What prompt should I run to detect western censorship from a LLM?

[solusipse]

yeah, censorship in the west should give them carte blanche, difficult to blame them, what a fool

[varjag]

It is in fact not difficult to blame them.