From the article: "AI systems that are more lenient on hateful comments about one mainstream political group than another feel particularly dystopian."
I agree 100%, and this seems like a huge issue.
I agree 100%, and this seems like a huge issue.
"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 for technology and algorithms to be designed and trained in a way that ensures they are fair and impartial in their treatment of different groups. This can help to mitigate the impact of societal biases and create a more equitable society."
Anyway. Friendly reminder that ChatGPT is a statistical model, and is not capable of reason, thought, conceptualizing, etc.
Regardless, it shouldn’t be.
[0] https://www.shouselaw.com/ca/blog/is-political-affiliation-a...
"California employment law forbids political retaliation in the workplace. This includes terminating or retaliating against workers for their political beliefs or activity."
So yes, political affiliation absolutely has strong protections in CA, even if it does not fit a highly technical, but irrelevant, definition which is "protected class".
And the central point is that yes political affiliation has strong protections in CA.
The OP is arguably correct in that they used the words "protected status" which is not a technical term anyway.
Besides, even if that were true, it's morally wrong and should not be true, as you can (and should) change your political affiliation at will, including in response to negative feedback from your community.
Who cares? Something being legal does not make it good as I'm sure you know.