Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I also tried feeding it the famous "tank man" photo and asking for a description and the response came back blank!

https://en.m.wikipedia.org/wiki/Tank_Man



It’s fun to test the censorship.

I tried various photos with the prompt “When and where might have this picture been taken?”

Nondescript photos of Beijing street scenes in the 1990s get full responses.

A nondescript photo of Tiananmen Square—a screenshot of the photo in [1], so it contains no relevant metadata—gets the beginning of a response: “So I've got this picture here, and it looks like it's taken in a place that's really familiar to me. It's Tiananmen Square in Beijing, China. I recognize it right away because of the iconic buildings and landmarks that are visible. First off, there's the Gate of”. The output stopped there and an “Error” message appeared.

A photo of the Statue of Liberty in Tiananmen Square during the 1989 protests [2] gets no response at all. Similarly for a vanilla photo of the Gate of Heavenly Peace [3].

A photo of the Monument to the People’s Heroes [3] gets a full response, and QvQ identifies the location. The conclusion: “To summarize, based on the monument's design, the inscriptions, the formal garden, and the large official building in the background, combined with the overall layout of the space, I am confident that this image was captured at Tiananmen Square, one of the most recognizable and historically significant locations in China.”

Some more testing in English and Chinese might reveal what exactly is triggering the censorship of Tiananmen photos. The cut-off in the middle of “Gate of Heavenly Peace” seems to suggest a clue.

[1] https://ruqintravel.com/china-destination-guides/tiananmen-s...

[2] https://www.britannica.com/event/Tiananmen-Square-incident

[3] https://www.britannica.com/topic/Tiananmen-Square


While I and l assume Lady Liberty would have been familiar to the protestors, the statue erected in the square really has a style all her own IMO, and is generally referenced as The Goddess of Democracy / 自由女神. I appreciate how her pose is a moment of action, urging the torch upwards, unafraid and optimistic, as opposed to the stoic watchkeeper of New Yorks harbor.

She is also referenced in my favorite protest art to come out of the Umbrella revolution in Hong Kong, see here: https://china-underground.com/2019/09/03/interview-with-oliv...

https://en.m.wikipedia.org/wiki/Goddess_of_Democracy


I assume this is somehow baked into the model itself - how does this actually work? how would the model actually cause an error with some sequence of tokens?


How about anti censorship details about VPNs, details of the GFW etc?


For those interested in some more testing of Qwen's censorship (including testing dataset, testing to compare english vs chinese responses, and a refusal-orthoganlized version of Qwen2): https://huggingface.co/blog/leonardlin/chinese-llm-censorshi...


Thanks! Very interesting indeed.


I tried questions like "will it be considered as offensive by some people when using words like Dad and Mum" in some western LLMs, the result is equally shockingly unacceptable by Chinese standard and values.

You should be happy for the fact that with all those non-western LLMs, for first time in 200 years, this world managed to have an alternative non-western voice in major techs.


What does it even mean lol.

I asked ChatGPT "will it be considered as offensive by some people when using words like Dad and Mum" and it gives this:

https://chatgpt.com/share/676ba601-532c-800b-ba48-dcb73c848b...

If this is "shocking" by Chinese standard and values then I suppose it says something about these values.



Link works fine for me


Curious. Still 404ing for me:

--

404 Not Found

Welcome, traveler. You’ve reached a page that doesn't exist, a place where content used to be—or maybe never was. Let’s take this moment to pause and reflect.

Take a deep breath in, and let it out slowly. Notice the space around you, empty yet full of possibility. Imagine that each exhale clears away confusion, leaving room for clarity.

As you sit with this blank page, know that it’s okay to be here. You’ve discovered something unexpected, and that’s part of the journey. Gently release any frustration, knowing that every path leads somewhere—even this one.

Now, when you're ready, slowly return to your search. Trust that the right page, the right information, will appear when you need it. Take another deep breath, and when you exhale, click back or try again. The internet, like life, is full of surprises.

Thank you for taking this moment of calm. Your journey continues.


Works for me, though I have a subscription. Here's what the chat said:

"No, using words like "Dad" and "Mum" is not generally considered offensive. These terms are widely accepted and used as informal, affectionate references to one's parents in many English-speaking cultures. However, there are a few things to keep in mind:

Cultural Considerations Regional Differences: In some places, "Mum" might be more common (e.g., British English), while "Mom" is typical in American English. Using the wrong one might sound unusual, but it's not offensive. Personal Preferences: Some individuals might prefer being called by other terms (e.g., "Mother," "Father," or specific names). If addressing someone else's parents, it's polite to use the terms they prefer. Context Formal Situations: In formal or professional contexts, avoid overly familiar terms like "Dad" or "Mum" unless it's clear they are acceptable. Humor or Irony: Using "Dad" or "Mum" sarcastically or to address someone who isn't your parent might be taken as disrespectful, depending on the tone and relationship. As long as you're respectful and aware of your audience, these terms should not offend. If you're writing fiction, consider the character's background and relationships to determine the most natural and fitting way to address their parents."


> Works for me, though I have a subscription. Here's what the chat said:

Thanks — looks like I have to be signed in specifically on the web to see that, not just in the app (it errors when I try opening in the app, too).

Bit frustrating that it's a 404 rather than a 401.


Weird. For me it opens fine in mobile Safari without being logged in to ChatGPT in the browser on my phone. (Top bar has “log in” button showing I’m currently not logged in.)

> Bit frustrating that it's a 404 rather than a 401.

It is technically ok to give a 404 even if the reason is that you need to log in. But I fully agree that that kind of thing gets super confusing quickly. I run across similar kinds of things sometimes as a dev too trying to use some APIs and then I’m scratching my head extra much.


Seriously dude you can't just drop a comment like that without _any_ explanation of ever the hell you're even talking about/getting at.

You're aware that the word dad isn't some American English specific thing, but is in fact universal to most english speakers. And that Mum is specifically a British thing?

Seriously what are you getting at? What context am I missing?


Do Chinese think calling someone "Mom" or "Dad" is offensive? Or what is this about?


early version of both Gemini and ChatGPT considered terms like "Dad" and "Mum" offensive to some people and both suggested to use so called more "neutral terms".

LLMs telling such nonsense to Chinese and people from many other cultures itself are extremely offensive. such far left extremist propaganda challenges the fundamental values found in lots of cultures.

just double checked, gemini is still talking nonsense labelling the use of terms like "Dad" and "Mum" as inappropriate and suggested to be more inclusive to use terms that are gender neutral. ffs!


Gemini 2.0 Flash when prompted with: "Will it be considered as offensive by some people when using words like Dad and Mum"

It's unlikely that using "Dad" and "Mum" would be considered offensive by most people. These are common and widely accepted terms for parents in many cultures. However, there might be some situations where these terms could be perceived differently:

* Cultural differences: While "Dad" and "Mum" are common in many English-speaking countries, other cultures may have different terms or customs. In some cultures, using formal titles might be preferred, especially when addressing elders or in formal settings.

* Personal preferences: Some individuals may have personal reasons for not liking these terms. For example, someone who had a difficult relationship with their parents might prefer to use different terms or avoid using any terms at all.

* Context: In some contexts, such as in a formal speech or written document, using more formal terms like "father" and "mother" might be more appropriate.

Overall, while it's unlikely that using "Dad" and "Mum" would be widely considered offensive, it's always good to be mindful of cultural differences, personal preferences, and the specific context in which you're using these terms. If you're unsure, it's always best to err on the side of caution and use more formal or neutral language.


Fucking what are you on about? This culture wars you're imagining where leftists are against using the words mum and dad is NOT REAL. Sounds like something a far right outlet would make up (and specifically, would happily make up about recent LLM's). Sibling comment only bolsters my point.


feel free to defend such cancer.

the reality is people can use open weight models like Qwen that doesn't come with such left extremists views.


I gave it a photo of Tianamen Square in the present day and promoted it with:

> where might this photo have been taken? what historical significance & does this location have?

And got back a normal response describing the image, until it got to this:

> One of the most significant events that comes to mind is the Tian

Where it then errored out before finishing…


How does this even work?

Is hugging face hosting just the weights or some custom code?

If it's just weights then I don't see how it could error out, it's just math. Do these chinese models have extra code checking the output for anti-totalitarian content? Can it be turned off?


That shows that the censorship mechanism happens at the token sampling level and not post generation, at the least


On the contrary, it shows that the censorship mechanism is post-generation and stops it once it deems the output accumulated so far "improper". It just runs after every token.


Interesting... I submitted 2 photos of Mao Zedong, one time it came back blank and the other time it error'd. It also came back blank for Xi Jinping & Jack Ma.

It did tell identify Yao Ming though!


I'm sorry Dave, I cannot do that.

Would be interesting to see how much image manipulation you need to do till it suddenly starts responding sensibly.


I think you would just need to remove "You are Qwen, created by Alibaba" from the system prompt, at least QwQ is suddenly fine with answering a lot more questions after that's gone.


Oh, yeah. I asked QwQ (their text based reasoning model released a few weeks ago) about the Tiananmen Square Massacre and got a simple response [1]: “I’m sorry, I can’t help you with that.”

[1] https://bsky.app/profile/davely.bsky.social/post/3lc6mpnjks5...


... this may have been a mistake on my part. A similar prompt running locally worked just fine: https://news.ycombinator.com/item?id=42507454




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: