[simion314]

The censorship is too sensitive if it gets triggered by a children story. I am using the open ai API at my work , and our users write books, including children stories , other example is it triggered on a story about monkeys because of "Racism".

Here is an example story, try to translate it , but maybe avoidAI since it might censor it https://www.povesti-pentru-copii.com/ion-creanga/capra-cu-tr...

[LeafItAlone]

>The censorship is too sensitive if it gets triggered by a children story.

It’s just imitating real life of people getting to sensitive about children’s books and trying to censor them:

https://www.nbcnews.com/news/amp/rcna202193

[alganet]

You can complain to their support, not to me.

I don't find it sensitive, and I remain on the side of ethical restrictions.

[simion314]

Someone asked here examples of what people are using that triggers the censorship, I gave you example of legal,, moral and normal content because the implication is that you only get censored if you are trying to do illegal stuff or adult stuff.

If you only use it for code you will not see the censorship that often, though Gemini once refused to write a SQL DELETE because it is to dangerous.

[alganet]

You said you wanted "no censorship", I explained why it exists with a cheerful metaphor, then you said "it's too sensitive" (like your car seat belt is too tight).

Decide what you are. If you want no seat belts, I think you're insane. If it's too tight, then you need to complain to the manufacturer.

I only asked about examples to make you explain what you meant. Once it was clear, the conversation actually ended.

[simion314]

Go back to the start of the thread, I gave example of censorship either beeing buggy or just stupidly setup so it makes happy both USA extremes.

I give you examples, I do not ask you to fix it. YOu just need to have the mental strength to admit that other people hit the censorship in day to day, in work related circumstances instead of defending the Big Tech by pretending that nobody normal would hit this issues.

[alganet]

I defend safety guardrails for open models too. Big Tech or not, I think they're good.

You're not asking me to fix it, but you are complaining to the wrong peer AND you don't know how to describe the problem you want to fix.

If you work with it, you should take the advice and open a bug report to your provider.