Comment by jampekka
8 hours ago
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. ..."
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.
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.
The previous CEO (and founder) Jack Ma of the company behind Qwen (Alibaba) was literally disappeared by the CCP.
I suspect the current CEO really, really wants to avoid that fate. Better safe than sorry.
Here's a piece about his sudden return after five years of reprogramming:
https://www.npr.org/2025/03/01/nx-s1-5308604/alibaba-founder...
NPR's Scott Simon talks to writer Duncan Clark about the return of Jack Ma, founder of online Chinese retailer Alibaba. The tech exec had gone quiet after comments critical of China in 2020.
6 replies →
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.
Why is it sensible? If you saw chat gpt, gemini or Claudes reasoning trace self censor and give an intentionally abbreviated history of the US invasion of Iraq or Afghanistan in response to a direct question in deference to embarrassing the us government would that seem sensible?
Is Claude a “he” or an “it”?
1 reply →
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.
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.
FYI: Newer LLM hosting APIs offer control over amount of "thinking" (as well as length of reply) -- some by token count others by an enum (high low, medium, etc.).
Doesn't ClosedAI do the same? Thinking models bill tokens, but the thinking steps are encrypted.
1 reply →
You just have to plan for the worst case.
Difficult to blame them, considering censorship exists in the West too.
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…
Have you ever actually looked into the history of the Taiwan and why they would officially call their region the Republic of China?
Apparently they had a civil war not too long ago. Internationally lots of territories were absorbed in weird ways in the last 100 years, amid post European colonialism and post WWII divvy up of territories among the allies. It sounds more similar to the way southerners like to print dixie flags and reference the confederate states, despite losing the civil war except the American Civil War ended 161 years ago, whereas the ROC fled to the island of Taiwan and were left alone, still claiming to be the national party of China despite losing their civil war 77 years ago.
Why not look into the actual history of the Republic of China? has it be suppressed where you live?
https://en.wikipedia.org/wiki/White_Terror_(Taiwan)
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.
In the US, yes, by the law, in principle.
In practice, you will have loss of clients, of investors, of opportunities (banned from Play Store, etc).
In Europe, on top of that, you will get fines, loss of freedom, etc.
7 replies →
This assumes zero unknown unknowns, as in things that would be kept from your awareness through processes also kept from your awareness.
This might be a good year to revisit this assumption.
1 reply →
>Private entities might have their own policies, but government censorship is fairly small.
It's a distinction without a difference when these "private" entities in the West are the actual power centers. Most regular people spend their waking days at work having to follow the rules of these entities, and these entities provide the basic necessities of life. What would happen if you got banned from all the grocery stores? Put on an unemployable list for having controversial outspoken opinions?
A man was just shot in the street by the US government for filming them, while he happened to be carrying a legally owned gun. https://www.pbs.org/newshour/nation/man-shot-and-killed-by-f...
Earlier they broke down the door of a US citizen and arrested him in his underwear without a warrant. https://www.pbs.org/newshour/nation/a-u-s-citizen-says-ice-f...
Stephen Colbert has been fired for being critical of the president, after pressure from the federal government threatening to stop a merger. https://freespeechproject.georgetown.edu/tracker-entries/ste...
CBS News installed a new editor-in-chief following the above merge and lawsuit related settlement, and she has pulled segments from 60 Minutes which were critical of the administration: https://www.npr.org/2025/12/22/g-s1-103282/cbs-chief-bari-we... (the segment leaked via a foreign affiliate, and later was broadcast by CBS)
Students have been arrested for writing op-eds critical of Israel: https://en.wikipedia.org/wiki/Detention_of_R%C3%BCmeysa_%C3%...
TikTok has been forced to sell to an ally of the current administration, who is now alleged to be censoring information critical of ICE (this last one is as of yet unproven, but the fact is they were forced to sell to someone politically aligned with the president, which doesn't say very good things about freedom of expression): https://www.cosmopolitan.com/politics/a70144099/tiktok-ice-c...
Apple and Google have banned apps tracking ICE from their app stores, upon demand from the government: https://www.npr.org/2025/10/03/nx-s1-5561999/apple-google-ic...
And the government is planning on requiring ESTA visitors to install a mobile app, submit biometric data, and submit 5 years of social media data to travel to the US: https://www.govinfo.gov/content/pkg/FR-2025-12-10/pdf/2025-2...
We no longer have a functioning bill of rights in this country. Have you been asleep for the past year?
The censorship is not as pervasive as in China, yet. But it's getting there fast.
Oh yes it is. Anything sexual is heavily censored in the west. In particular the US.
1 reply →
Did we all forget about the censorship around "misinformation" during COVID and "stolen elections" already?
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.
yeah, censorship in the west should give them carte blanche, difficult to blame them, what a fool
What prompt should I run to detect western censorship from a LLM?
https://grok.com/share/c2hhcmQtMw_c2a3bc32-23a4-41a1-a2ae-8d...
It is in fact not difficult to blame them.