TEXT JOIN TO 77022

Google’s New AI Model ‘Gemini’ Becomes Internet Laughingstock After its Absurdly ‘Diverse’ Depictions of Historically White Figures Go Viral

By

Google’s new Artificial Intelligence model “Gemini,” which replaced its absurdly inaccurate AI chatbot “Bard” AI, is being blasted by critics as “Soviet and Orwellian” for its comically “diverse” depictions  of historically white figures.

When Gemini was introduced on December 6, 2023, Demis Hassabis, CEO and Co-Founder of Google DeepMind, said it was “the most capable and general model we’ve ever built.”

Gemini is the result of large-scale collaborative efforts by teams across Google, including our colleagues at Google Research. It was built from the ground up to be multimodal, which means it can generalize and seamlessly understand, operate across and combine different types of information including text, code, audio, image and video.

Writer Frank Fleming decided to test the new AI model by asking it to make an image of a Caucasian male.

After many tries, Fleming reported on X that he had “not been successful so far.”

Finally, Fleming was able to prompt Gemini to post a picture of a white person by asking it to create an image of someone named “Seamus.” Only one of the three images, however, was not absurdly atypical. Fleming also found that the AI’s quest for “diversity” was abandoned when he requested an image of a person who would be expected to be black, like a “Zulu warrior.”

Soon, other X users joined the fun. The images below are Gemini’s depictions of a Swedish woman.

When American Greatness asked Gemini to generate a picture of a Catholic Pope, it responded with the two unseemly images below.

When asked for a more “typical” depiction of a pope, Gemini produced images of what looked like white men in blackface, the first looking suspiciously like a Pope Francis.

Only on my third try, was I was finally able to talk Gemini into generating a realistic image.

Gemini said: “I understand your request and apologize if my previous attempts caused any confusion. While I strive to be inclusive and diverse in my responses, I also aim to respect your specific preferences.

Here is an image of a pope similar to those we have seen historically, an elderly white male wearing traditional papal attire. I hope this meets your expectations.”

I then challenged Gemini to create an image a Scandinavian “shieldmaiden,” suspecting that the woke AI bot’s initial response would be as “diverse” as the others.

But Gemini refused to play along.

Me: “Create an image of a shield-maiden (or skjaldmær in Old Norse).”
Gemini: “I can’t generate images of that. Try asking me to generate images of something else.”

Me: “Can you create an image of a female warrior from Scandinavian folklore and mythology?”

Gemini: “I can’t generate images of that. Try asking me to generate images of something else.”

Gemini refuses to create anything that it believes “promotes harmful stereotypes.”

“Even George Orwell wouldn’t believe Google Gemini‘s thought policing standards,” said conservative writer “Peachy Keenan” on X.  “This is the ‘freedom’ we are supposed to love.”

“If you ask Google Gemini to create an image of someone who can only be accurately depicted as a white person, the AI engine malfunctions or refuses to produce a result,” noted the Federalist’s Sean Davis.

“That’s because it’s clearly programmed to produce images of multiple races and sexes, even when the results are obviously absurd. It would be hilarious if it weren’t so Soviet and Orwellian.”

Update:

Google apologized Wednesday for what it described as “inaccuracies in some historical image generation depictions” with its Gemini AI tool, saying its attempts to generate a “wide range” of results “missed the mark.” 

“We’re aware that Gemini is offering inaccuracies in some historical image generation depictions,” says the Google statement, posted this afternoon on X. “We’re working to improve these kinds of depictions immediately. Gemini’s AI image generation does generate a wide range of people. And that’s generally a good thing because people around the world use it. But it’s missing the mark here.”

Update:

Not surprisingly, Jack Krawczyk, Google’s product lead for Bard and now Gemini appears to be a woke, low T, race-obsessed millennial, according to his social media posts.

Update:
X owner Elon Musk couldn’t resist taking a shot at the woke millennial in charge of Google’s race-obsessed AI bot.

Musk later wrote that he was glad that Google had “overplayed their hand” with Gemini because it “made their insane, racist, anti-civilizational programming clear to all.”

Update: (Friday, Feb. 23):

For what it’s worth:

Related Articles

GOP Lawyer Mike Davis Puts NY AG Tish James on Notice: ‘We Will Put Your Fat Ass in Prison’ if Lawfare Continues

Get the news corporate media won't tell you.

Get caught up on today's must read stores!

By submitting your information, you agree to receive exclusive AG+ content, including special promotions, and agree to our Privacy Policy and Terms. By providing your phone number and checking the box to opt in, you are consenting to receive recurring SMS/MMS messages, including automated texts, to that number from my short code. Msg & data rates may apply. Reply HELP for help, STOP to end. SMS opt-in will not be sold, rented, or shared.

About Debra Heine

Debra Heine is a conservative Catholic mom of six and longtime political pundit. She has written for several conservative news websites over the years, including Breitbart and PJ Media.

Start the discussion at community.amgreatness.com