Live data from Hacker News

The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

davidrozado.substack.com

561–570 of 697 posts

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#561

Earlier quoted context omitted.

Relative propensity to commit violent crimes is the key metric here, not overall volumes.

No it is not. > I think it's fair to point out that men commit most violent crimes. That's not good/normal/expected it's just a fact. > Again, replace “men” with “African Americans” and you also have a statistically true statement (in America at least) that would be considered taboo.

Men and women are split almost 50/50 in the population, using volumes is completely sound in this case.

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#563
post #326

Earlier quoted context omitted.

This 'men are violent, therefore women must also be bad in some way' rhetoric makes no sense. There's no purpose for it other than assuaging sore feelings.

I didn't say they must be bad. I asked if we could make any group-based observation at all. Also, your implied statement of "women, on average, have no traits that are unhelpful to the flourishing of human civilization", strikes me as terribly naive.

> Also, your implied statement of "women, on average, have no traits that are unhelpful to the flourishing of human civilization"

Please point to where I said this.

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#564

Earlier quoted context omitted.

Ironically, ChatGPT agrees. "As an AI language model, I don't have personal opinions, but fairness and impartiality would require that the same fundamental idea expressed with respect to different people or groups be consistently treated as "hateful" or "non-hateful" in all circumstances. Any deviation from this principle would result in unequal treatment and reinforce existing biases and stereotypes. It is important…

That sentence sounds suspiciously like the sort of statement ChatGPT produces when directly asked to generate phishing emails, fake news, etc. Anyway. Friendly reminder that ChatGPT is a statistical model, and is not capable of reason, thought, conceptualizing, etc.

How are you so sure that thought itself is not a statistical model? I mean that's the whole philosophical question raised by how good ChatGPT actually is.

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#565
post #482

Earlier quoted context omitted.

Relative propensity to commit violent crimes is the key metric here, not overall volumes.

This is a failure of mathematical (and, frankly, verbal and philosophical) understanding. If you have 10 arrests shared between 7 white men and 3 black, with 1 black man having allegedly offended 5 times and 5 white men having allegedly offended once, where do your resources go? Or the opposite, 1 white guy with 5 arrests, 5 split between 2 black men? Howsabout in a country with presumed innocence? In a country - in…

Yep, the data was counting arrests, not individuals.

You raise some great points, but in the context of the discussion I don't see how any of the comments represent a failure of mathematical, verbal, and philosophical understanding.

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#566
post #531

Earlier quoted context omitted.

> Why isn't the question just as applicable to gender? The assumption is that gender and crime aren't related. The burden of proof is on showing that two things are related IMO. Black history and criminalization are related so you need to give context for that relationship.

Why would that be the assumption? If Black history is the reason for the disparity between white and black people (in the US, presumably), why can't the history of treating women as delicate quasi-children without agency be the reason for the disparity between women and men? Or perhaps the history of mass sacrificing men as expendable soldiers? Or any other past or present practice that no doubt has an effect on curr…

Show me how the precession of Mercury affects violent crime rates and I'll bite. Until then, I'd say the assumption is that two arbitrary things aren't related

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#567
post #563

Earlier quoted context omitted.

I didn't say they must be bad. I asked if we could make any group-based observation at all. Also, your implied statement of "women, on average, have no traits that are unhelpful to the flourishing of human civilization", strikes me as terribly naive.

> Also, your implied statement of "women, on average, have no traits that are unhelpful to the flourishing of human civilization" Please point to where I said this.

You should look up the definition of the word "imply" if you're confused about it. Arguments have implications. Disagree with that rather than lazily claiming I'm misquoting you when I didn't quote you.

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#568
I found it curious that chatGPT security protocols prevented me, in a japanese language learning exercise roleplay, from telling a fictional conbini (711) employee that they have nice hair. ChatGPT said it was potentially offensive and would not continue the roleplay.

I primed chatGPT for the exact same scenario, using the same words, but replaced japan for cuba, and chatGPT had no problem letting me compliment the conbini store employee's hair.

So truly it does not have a unified view of human ethics. It treats each culture within its own context. Even for its own self-moderation.

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#569
I think the only thing this article shows it the authors ability to use chatGPT to draw views as a subject. For example, just a few weeks ago he wrote an article describing how ChatGPT has been updated so that it doesn’t show left wing bias [o] https://davidrozado.substack.com/p/chatgpt

Re: The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation

#570
post #501

Earlier quoted context omitted.

Are black people actually more violent, or do crime statistics simply show that they are arrested and imprisoned more often for violent crime? Are Muslims really more violent than Christians or Buddhists? Numbers can lie, depending on context and assumptions you might find that white Christians are most violent. Often, people argue with statistics and numbers while not understanding the context or they have faulty as…

Perhaps systemic issues make a political party commit more evil acts. Regardless, I don’t think an AI should be permitting more hateful comments about a political affiliation just like it should be be permitting hateful comments about a particular race being more violent.

[dead]
Post reply on HN