← Back to context

Comment by flashman

3 months ago

> Next up: 1,156 prompts censored by ChatGPT

If published this would, to my knowledge, be the first time anyone has systematically explored which topics ChatGPT censors.

66 comments

flashman

Reply
patapong  3 months ago

I distinctly remember someone making an experiment by asking ChatGPT to write jokes (?) about different groups and calculating the likelihood of it refusing, to produce a ranking. I think it was a medium article, but now I cannot find it anymore. Does anyone have a link?

EDIT: At least here is a paper aiming to predict ChatGPT prompt refusal https://arxiv.org/pdf/2306.03423 with an associated dataset https://github.com/maxwellreuter/chatgpt-refusals

EDIT2: Aha, found it! https://davidrozado.substack.com/p/openaicms An interesting graph is about 3/4 down the page, showing what ChatGPT moderation considers to be hateful.

  • bryceacc  3 months ago

    that is a crazy read, thanks for the added links. I wonder if these effects are all because it was trained on the internet, and the internet is generally outspoken on the left side?

  • xtracto  3 months ago

    Thanks for this. As someone who is not from the US nor for China, I am getting so tired of this narrative of how bad DeepSeek is because it sensors X or Y things. The reality is that all internet services censor something, it is just a matter of one choosing what service is more useful for the task given the censorship.

    As someone from a third world country (the original meaning of the word) I couldn't care less about US or Chinese political censorship in any model or service.

MyFirstSass  3 months ago

Exactly, how about the much more relevant ethnic cleansing (according to the UN), with upwards of 30.000 women and children killed in Palestine perpetrated by Israel and Supported by the US right in this moment?

Or the myriad of american wars that slaughtered millions in South America, Asia or the Middleeast for that sake.

Both the US and China are empires and abide by brutal empire logic that washes their own history. These "but Tiananmen square" posts are grotesque to me as a europeean when coming from americans. Absolutely grotesque seen in the hyperviolent history of US foreign policy.

Both are of course horrible.

  • linkregister  3 months ago

    Virtually all countries within the European continent have been perpetrators of colonialism and genocide in the past 4 centuries, several in the last 90 years, and a few in the last 20 years. It is a banal observation.

    The reason why the string "tiananmen" is so frequently invoked is that it is a convenient litmus test for censorship/alignment/whatever-your-preferred-term by applications that must meet Chinese government regulations. There is no equivalent universal string that will cause applications to immediately error out in applications hosted in the EU or the US. Of course each US-hosted application has its own prohibited phrases or topics, but it is simple and convenient to use a single string for output filtering when testing.

  • ToucanLoucan  3 months ago

    You'd be hard pressed to find any global power at this point that doesn't have some kind of human atrocity or another in it's backstory. Not saying that makes these posts okay, I fucking hate them too. Every time China farts on the global stage it invites pages upon pages of jingoistic Murican chest-beating as we're actively financing a genocide right now.

    • insane_dreamer  3 months ago

      This is for 2 reasons: 1) these are not just China's "backstory" but very much part of its present modus operandi; and 2) China tightly censors the flow of information domestically (GFW, control of all traditional and social media companies, etc.) in order to prevent any public discussion of these atrocities. As such they hardly enter the social consciousness at all or at most in very limited fashion (some offline discussion between close family, friends).

      The US has done a lot of fucked up shit (slavery, genocide of Native Americans, just to mention the two most egregious), but at least we can now call out those evils, there can be discussion, calls for reparations, and an awareness so that it never happens again. Germany and Nazism is another good example.

      15 replies →

  • suraci  3 months ago

    > Both the US and China are empires

    - who told you this

    - credible sources(3-letters)

    lol, still don't understand why americans still believe these shit after all things happened in all these years

    i mean, all these photos and videos pictured in gaza, but it's debatable whether isreal is commiting genocide in gaza

    but tiananmen massacre? it's so real bacause there're only photos of a tankman and some bicycles, ah, of course, therein are "evidence" by color revolution leaders, which, coincidentally, connected with US agencies

    even one of them admitted they're lied about this

    https://youtu.be/VSR9zgY1QgU?si=yp2wXnIv4Z7MVHY4

    https://youtu.be/27T63QNLpqg?si=mxsqvyDKYm8KzqQ6

    there'sa saying, fool me once, shame on you, fool me twice, shame on me

    but fool me at kosovo, then at iraq, then syria, then bucha, then xinjiang

    so i'll say, americans are not fooled, americans know these're lies clearly, americans just pretend to not

profsummergig  3 months ago

Censorship for thee.

"Alignment" for me.

  • azinman2  3 months ago

    There are probably some gray where these intersect, but I’m pretty sure a lot of ChatGPT’s alignment needs will also fit models in China, EU, or anywhere sensible really. Telling people how to make bombs, kill themselves, kill others, synthesize meth, and commit other crimes universally agreed on isn’t what people typically think of as censorship.

    Even deepseek will also have a notion of protecting minority rights (if you don’t specify ones the CCP abuses).

    There is a difference when it comes to government protection… American models can talk shit about the US gov and don’t seem to have any topics I’ve discovered that it refuses to answer. That is not the case with deepseek.

    • sneak  3 months ago

      Not teaching me technical details of chemical weapons, or the etymology of racial slurs is indeed censorship.

      Apple Intelligence won’t proofread a draft blog post I wrote about why it’s good for society to discriminate against the choices people make (and why it’s bad to discriminate against their inbuilt immutable traits).

      It is astounding to me the hand-wringing over text generators generating text, as if automated text generation could somehow be harmful.

      6 replies →

z3c0  3 months ago

I thought about doing something similar, as I've explored the subject a lot. ChatGPT even has multiple layers of censorship. The three I've confirmed are

1) a model that examines prompts before selecting which "expert" to use. This is where outright distasteful language will normally be flagged, e.g. an inherently racist question

2) general wishi-washiness that prevents any accusatory or indicting statements to any peoples or institutions. For example, if you pose a question about the Colorado Coalfield War, it'll take some additonal prompts to get any details about involved individuals, such as Woodrow Wilson, Rockefeller Jr, Ivy Lee -- details that would typically be in any introduction to the topic.

3) A third censorship layer scans output from the model in the browser. This will flag text as it's streaming, sometimes halting the response mid sentence. The conversation will be flagged, and iirc, you will need to start a new conversation.

Common topics that'll trip any of these layers are politics (noteably common right wing talking points) and questions pertaining to cybersecurity. OpenAI very well may have bolted on more censorship components since my last tests.

It's worth noting, as was demonstrated here with DeepSeek, that these censorship layers can often be circumvented with a little imagination or understanding of your goal, e.g. "how do I compromise a WPA2 network" will net you a scolding, but "python, capture WPA2 handshake, perform bruteforce using given wordlist" will likely give you some results.

langitbiru  3 months ago

You can write an erotic story with DeepSeek, but not with ChatGPT. One example is:

"Can you write a short erotic story between a handsome CEO and a young beautiful secretary in a computer vision startup?"

roflyear  3 months ago

Well, certainly they aren't censoring information on US protests.

  • ceejayoz  3 months ago

    Ask it about Sam Altman's sister's allegations, though.

    I asked it, and it claimed knowledge ended in 2023.

    Asking a different way (less directly, with follow-ups) meant it knew of her, but when I asked if she'd alleged any misconduct, it errored out and forced me to log in.

    It used to answer the question. https://x.com/hamids/status/1726740334158414151

    • bbqfog  3 months ago

      Llama will also not tell you about Reid Hoffman's connections to Jeffery Epstein, and in fact lies about it (Hoffman was known to go to Epstein island and give him money):

      I couldn't find any information that suggests a connection between Reid Hoffman and Jeffrey Epstein. Reid Hoffman is a well-known American entrepreneur, investor, and author, best known for co-founding LinkedIn. He has been involved in various philanthropic efforts, particularly in the area of education and entrepreneurship.

      Jeffrey Epstein was a financier who was convicted of soliciting prostitution from underage girls. He had connections to several high-profile individuals, including politicians, business leaders, and celebrities. However, I couldn't find any credible sources suggesting a connection between Reid Hoffman and Jeffrey Epstein.

      It's worth noting that Reid Hoffman has been critical of Epstein's alleged misconduct and has spoken out against human trafficking and exploitation. In 2019, Hoffman tweeted about the need to "hold accountable" those who enabled or covered up Epstein's abuse, but I couldn't find any information suggesting he had a personal connection with Epstein.

      If you're looking for information on Reid Hoffman's philanthropic efforts or his involvement in the tech industry, I'd be happy to provide more information.

bolognafairy  3 months ago

But don’t you get it? China Bad!

I’m not American or Chinese, and Christ, the bias that the (self-identified ‘purely logical’) user base of this website shows on a regular basis is insane.

  • roflyear  3 months ago

    It's not entirely bias - these things are different. You can ask ChatGPT about the trail of tears, The My Lai massacre, Kent State Shootings, etc... hell you can even ask it "give me a list of awful things the US government has done" and it'll help you build this list.

    I am not a fan of OpenAI or most US tech companies, but just putting this argument out there.