It is clearly a byproduct of trying to correct an unaligned, bigoted model, and that is an example of overcorrection.
> Removing bias ends with truth, not these crazy wonky results.
Unfortunately there is an awful lot of untruth on the internet, if you hadn't noticed. This necessitates some correction through post-training.
> OpenAI invented a technique in July 2022 whereby its system would insert terms reflecting diversity (like “Black,” “female,” or “Asian”) into image-generation prompts in a way that was hidden from the user.
> Google’s Gemini system seems to do something similar, taking a user’s image-generation prompt (the instruction, such as “make a painting of the founding fathers”) and inserting terms for racial and gender diversity, such as “South Asian” or “non-binary” into the prompt
More links to primary sources, evidence, and official statements in the article at https://arstechnica.com/information-technology/2024/02/googl...
It seems then that their objective is to superficially increase the diversity of results, to avoid bad PR, rather than actually neutralising harmful and untruthful biases of the input data.
A what? What does this even mean?
If you try to remove that in the name of "diversity" or being "less bigoted" you quickly end up with racially diverse nazis