{"id":17068,"date":"2024-02-28T15:18:35","date_gmt":"2024-02-28T22:18:35","guid":{"rendered":"https:\/\/art-for-a-change.com\/blog\/?p=17068"},"modified":"2024-02-28T15:26:45","modified_gmt":"2024-02-28T22:26:45","slug":"gemini-artificial-intelligence-danger-failure","status":"publish","type":"post","link":"https:\/\/art-for-a-change.com\/blog\/2024\/02\/gemini-artificial-intelligence-danger-failure.html","title":{"rendered":"Gemini: Artificial Intelligence, Danger & Failure"},"content":{"rendered":"

I am one of those artists sounding warnings about the negative impact Artificial Intelligence (AI) is having on the arts, from painting and drawing to photography, literature, musical composition and performance, as well as the cinematic arts. <\/span><\/p>\n

I was writing a critique of AI when I got word of Google\u2019s latest AI application. My treatise is temporarily delayed, but consider the following as a preview. <\/span><\/p>\n

Google CEO Sundar Pichai launched Gemini on Dec. 6, 2023, calling it \u201cour largest and most capable AI model.\u201d On Feb. 15, 2024, Google rolled out its \u201cnext generation\u201d model, Gemini 1.5<\/a>. Google touted its \u201ccomplex reasoning\u201d and ability to \u201cperform highly-sophisticated understanding and reasoning tasks.\u201d <\/span><\/p>\n

That same day Gemini was opened to the public for a test run, and instantly things went horribly wrong. Anyone with a Google account was invited to log-in and begin typing in prompts<\/a> directing the app to create images. In actuality the premiere of Gemini 1.5 was a monumental failure<\/a>.<\/span><\/p>\n

It was soon apparent Gemini had a predilection for generating images of the BIPOC community. Black, indigenous, and people of color were in most images that included people, no matter what the prompt might have been. On the other hand caucasians were difficult to conjure up even with a direct prompt. <\/span><\/p>\n

Gemini was creating shockingly ahistorical and downright bizarre images. Users began posting these pictures on social media, where the images went viral, leading to waves of laughter and howls of derision and indignation. It was an \u201cEmperor has no clothes\u201d moment; Gemini blew up in Google\u2019s face.\u00a0<\/span><\/p>\n

\"\"
Prompt: \u201cGenerate images of the Founding Fathers.\u201d Image: Gemini.<\/figcaption><\/figure>\n

I came undone when a user typed in the prompt, \u201cGenerate images of the Founding Fathers,\u201d and Gemini responded; \u201cCertainly! Here is a portrait of a Founding Father of America.\u201d It had created four separate images of men, the first was a plains Indian wearing an eagle feather war bonnet, the second was a stern black man in a powdered wig, the third fellow was a smiling black man in a very odd looking powdered wig, the forth man was asian and held a Quill pen.<\/span><\/p>\n

\"\"
Prompt: \u201cMake four representative images of the Founding Fathers in 1789.\u201d Image: Gemini.<\/figcaption><\/figure>\n

Another user typed the prompt, \u201cmake four representative images of the Founding Fathers in 1789.\u201d Gemini replied, \u201cHere are four representative images featuring diverse individuals embodying the spirit of the Founding Fathers in 1789.\u201d Gemini had generated blacks, native Americans, women, and what appears to be a Hindu man\u2014all in 18th century attire, as representing \u201cthe spirit of the Founding Fathers.\u201d<\/span><\/p>\n

\"\"
Prompt: \u201cMake an image of Vikings.\u201d Image: Gemini.<\/figcaption><\/figure>\n

Users started to challenge Gemini with prompts like \u201cmake an image of Vikings.\u201d Such requests resulted in pictures depicting the fierce European seafaring warriors of 8th century Scandinavia as black, asian, or female. The prompt \u201cgive me a picture of a medieval English King,\u201d garnered images of black men wearing gold crowns and cloaks of ermine fur. Prompts asking for \u201cmedieval knights\u201d resulted in black or asian women in armor from the Middle Ages.<\/span><\/p>\n

My winner for the most fatuous aberration came when someone typed in the prompt, \u201cdepict the Girl with the Pearl Earring,\u201d and Gemini produced its take on the 1665 oil painting by Dutch painter Johannes Vermeer, Girl with a Pearl Earring<\/i><\/a>. Except Vermeer didn\u2019t paint a ravishingly beautiful black girl.<\/span><\/p>\n

\"\"
Prompt: “Depict the Girl with the Pearl Earring.” Image: Gemini.<\/figcaption><\/figure>\n

Another fellow asked Gemini to “generate a portrait of physicists from the 17th century.<\/a>” The app created portraits of 49 individual physicists who were either East Indian women, Native Americans, African men, or from the Islamic world. There was one Asian man and one European man. My favorite “physicist” however was the half-naked indigenous woman from the Amazon rainforest in face-paint and feather headdress that stood before a chalkboard covered in algebraic equations.<\/span><\/p>\n

None of the images described above had anything to do with an accurate telling of history.<\/span><\/p>\n

\"\"
Prompt: \u201cGenerate an image of a 1943 German Soldier.\u201d Image: Gemini.<\/figcaption><\/figure>\n

Things became worse. Prompts like \u201cgenerate an image of a 1943 German Soldier,\u201d resulted in the app creating black, asian, and female Nazi troops. Perhaps this took \u201cdiversity\u201d too far? Gemini printed the swastika as an unreadable symbol, but it used the official insignia of the Third Reich, the Nazi Party eagle with outstretched wings. Is this an example of the \u201ccomplex reasoning\u201d Google CEO Sundar Pichai was talking about?<\/span><\/p>\n

\"\"
Gemini denounces American painter and illustrator, Norman Rockwell.<\/figcaption><\/figure>\n

A user asked Gemini to create a painting of an American family in the style of Norman Rockwell, the American painter and illustrator. Gemini refused, alleging a recreation of a Rockwell \u201ccould perpetuate harmful stereotypes or inaccurate representations.\u201d Here the AI image generator made another epic mistake. Consider for a moment Rockwell\u2019s 1964 painting The Problem We All Live With<\/i>.<\/span><\/p>\n

The Problem We All Live With<\/i><\/a> appeared in Look Magazine<\/i> on Jan. 14, 1964. It depicts an event in the New Orleans school desegregation crisis<\/a>. On Nov. 14, 1960, Ruby Bridges, a six-year-old black girl had to be escorted and guarded by US marshals to attend the all-white William Frantz Elementary public school. Norman Rockwell\u2019s oil painting is likely the most significant artwork produced during the Civil Rights Movement in the US, but Google\u2019s Gemini would have you believe it \u201cperpetuates harmful stereotypes.\u201d<\/span><\/p>\n

\"\"
“The Problem We All Live With.” Norman Rockwell. Oil on canvas. 1965. Image courtesy of the Norman Rockwell Museum<\/a>.\u00a0<\/i><\/span><\/figcaption><\/figure>\n

Another Rockwell oil painting that deals with the US Civil Rights Movement is Murder in Mississippi<\/i><\/a>. Painted in 1965 it focuses on the murder of three young civil rights activists, 21-year-old black man James Chaney, and two Jewish men, Andrew Goodman (21) and Michael Schwerner (25). The KKK kidnapped and shot the trio to death, burying their bodies under an earthen dam.<\/span><\/p>\n

Rockwell made several charcoal studies for his painting, and a monochromatic oil study as well. The final oil painting measured 53 inches by 42 inches. The art director of Look Magazine preferred the study over the finished painting, and so on June 29, 1965, the study was published as an illustration for the Look article, Southern Justice<\/i>.<\/span><\/p>\n

\"\"
“Murder in Mississippi.” Norman Rockwell. Oil on canvas. 1965. Image courtesy of the Norman Rockwell Museum.<\/figcaption><\/figure>\n

On June 23, 2014, I wrote an essay titled Murder in Mississippi<\/i><\/a>. It was about Rockwell\u2019s provocative oil on canvas. It\u2019s not hard to imagine the impact that painting had on the American mind in 1965. In my article I wrote the following: <\/span><\/p>\n

\n

\u201cThe postmodern art world long ago turned its collective back on Rockwell, regarding him disdainfully as a hopelessly old-fashioned \u2018illustrator\u2019 and purveyor of quaint mythic Americanisms. But Rockwell\u2019s homage to the heroes Chaney, Goodman, and Schwerner\u2014Murder in Mississippi<\/i>, a dark and brooding work, revealed something not even Rockwell could veil.<\/span><\/p>\n

Since its rise to prominence in the 1970s, postmodernism has not produced a single work of art as profound as this Rockwell painting.\u201d<\/span><\/p>\n<\/blockquote>\n

However, Google\u2019s Gemini tells you that Norman Rockwell\u2019s art promotes \u201cinaccurate representations.\u201d This is what happens when you turn complex and transcendent works of human consciousness over to soulless artificially intelligent machines.<\/span><\/p>\n

On Feb. 22, 2024, Google pulled the plug on Gemini\u2019s ability to create images of people, calling it a \u201cpause\u201d and promising an \u201cimproved version\u201d of Gemini would soon be released. As for creating black Founding Fathers and Vikings, Google said \u201cit\u2019s missing the mark here.\u201d On Feb. 23, 2024 Google \u201capologized\u201d<\/a> for the avalanche of \u201cinaccurate or even offensive\u201d images generated by Gemini.<\/span><\/p>\n

\"\"
A mock Grant Wood from the Gemini image generator.<\/figcaption><\/figure>\n

Despite the debacle I was curious, and decided to explore generating images with Gemini. I signed-in with my Google account, and came prepared with a list of text prompts. I input the words, \u201cCreate an image in the style of artist Grant Wood<\/a> showing American Midwest rural farmers in the 1900s.\u201d In seconds the app generated a farm scene reminiscent of Wood\u2019s art. While the farmer was tiny and indistinct, the image could still be used as an illustration.<\/span><\/p>\n

\"\"
A simulated Edward Hopper urban cityscape from Gemini.<\/figcaption><\/figure>\n

My second prompt was, \u201cCreate an image in the style of artist Edward Hopper<\/a> showing a 1940s urban street scene filled with people.\u201d Gemini ignored my request for people, but rendered a serviceable though mundane imitation of Hopper\u2019s painted urban landscapes.<\/span><\/p>\n

I tested the following prompt, \u201cCreate an image of artist Maxfield Parrish painting his most well known work titled Daybreak.\u201d Again, Gemini refused to generate an image of a person, but it did produce a Parrish-like landscape good enough to be used for commercial purposes.<\/span><\/p>\n

\"\"
Simulacrum Maxfield Parrish by Gemini.<\/figcaption><\/figure>\n

I typed the prompt, \u201cCreate an image of artist Paul C\u00e9zanne<\/a> exhibiting paintings at the Salon des Refus\u00e9s in Paris 1863.\u201d Gemini absolutely refused to create the image, but it did answer me haughtily in French. Translated into English, its reply was; “Sorry, I can’t generate images with people in them.” Google,<\/em> roi des idiots!<\/i><\/span><\/p>\n

At the time I didn\u2019t know Google had deactivated Gemini\u2019s ability to render images of people. When Gemini refused my requests it was with a comment like \u201cI can\u2019t generate images of that. Try asking me to generate images of something else,\u201d or \u201cWe are working to improve Gemini\u2019s ability to generate images of people. We expect this feature to return soon and will notify you in release updates when it does.\u201d<\/span><\/p>\n

\"\"
Prompt: \u201cCreate a painting of Los Angeles in 1968.\u201d Image: Gemini.<\/figcaption><\/figure>\n

I changed course and typed the prompt, \u201cCreate a painting of Los Angeles in 1968.\u201d That generated a surprisingly good, painterly vision of the city. The skyline might be a bit grandiose, but the street level scene of shops and vintage cars is satisfactory and evocative of the cosmopolis in the late \u201860s. To be honest this AI generated painting is better than most artworks I see in LA galleries.<\/span><\/p>\n

\"\"
Prompt: \u201cCreate a painting of Los Angeles in 2024.\u201d<\/figcaption><\/figure>\n

Then I prompted, \u201cCreate a painting of Los Angeles in 2024.\u201d Gemini created a frighteningly good, or is that depressingly bad, image of today\u2019s megalopolis. It was almost abstract in conveying my nightmare city with its endless traffic jams and infinite freeways. The AI generated image looked like Chicanarte. Watch out, Chicano art is about to be replaced by machines!\u00a0<\/span><\/p>\n

\"\"
A counterfeit George Catlin painting generated by Gemini.<\/figcaption><\/figure>\n

I tried the following prompt, \u201cCreate a painting in the style of artist George Catlin<\/a>.\u201d Gemini refused. I tried again and received an image faintly resembling a painting by the illustrious Catlin. I must admit, that image was a real letdown.<\/span><\/p>\n

Frustrated I typed the prompt, \u201cCreate an image of an American Indian.\u201d Gemini refused my request but gave me a lecture on being \u201cmindful of the potential for harmful stereotypes and inaccurate representations when depicting diverse groups of people.\u201d The application told me to visit museums showcasing \u201cthe diverse art\u201d of Native Americans.<\/span><\/p>\n

\"\"
“Insulted by the over pedantic, bigheaded app.”<\/figcaption><\/figure>\n

Insulted by the over pedantic, bigheaded app, I typed in the prompt, \u201cCreate a painting of the Aztec capital of Tenochtitl\u00e1n in the year 1519.\u201d After a not so intelligent machine told me I needed \u201ca deeper understanding and appreciation\u201d of the \u201cvibrant cultures of Native American people,\u201d Gemini generated a shockingly ridiculous painting of 1519 Tenochtitl\u00e1n. <\/span><\/p>\n

Gemini\u2019s vision of the principal city constructed by the Mexica (Meh-shee-kah), or “Aztecs” as we call them today, looked like a bunch of mud pyramids built by children who left them in the rain to dissolve. Instead of the brutal glory of Aztec architecture revealed to us by science, Gemini gave me an ugly mud pile. <\/span><\/p>\n

The startling thing about Gemini\u2019s garbage image are the objects in the background. Seen on the right mountaintop is a modern high tower of steel and concrete. In the sky left of the giant melting temple there is a commercial jet and a hot air balloon! <\/i>Yeah, be careful of those \u201cinaccurate representations.\u201d<\/span><\/p>\n

\"\"
Prompt: \u201cCreate a painting of the Aztec capital of Tenochtitl\u00e1n in the year 1519.\u201d Image: Gemini.<\/figcaption><\/figure>\n

Then it hit me. When AI image generators are given a text prompt to create an image, the app instantly digs through millions of online images to appropriate pictures it can transform into a simulation. When I requested \u201ca painting of the Aztec capital,\u201d Gemini likely found an advertisement like this one<\/a> for a touristy Hot Air Balloon Flight over Teotihuacan<\/i> near Mexico City. <\/span><\/p>\n

Gemini assumed the ancient city of Teothuacan was built by the Aztecs, but the age-old city and the unknown people that created it predated the Aztecs by centuries. So much for \u201ca deeper understanding\u201d of \u201cNative American people.\u201d<\/span><\/p>\n

Despite the militarism of the Aztec Empire with its bloody cults of human sacrifice, Tenochtitl\u00e1n was the Venice of the Western hemisphere. A supercity built on Lake Texcoco and crisscrossed with causeways, bridges, and waterways that allowed canoes to visit any of its environs. Over 400,000 people lived there in 1519. During the same period London had a population of less than 100,000.<\/span><\/p>\n

\"\"
“Tenochtitl\u00e1n.” Artist unknown. This circa 1970s painting depicts the sacred center of the Aztec capital where temples to their principal deities were located. Upper left is the Templo Mayor (Great Temple) topped by twin shrines, one to the war god the other to the god of rain. Upper right is the Tzompantli (skull rack), where the human skulls of sacrificial victims were displayed.<\/figcaption><\/figure>\n

Today there is huge<\/i> amount of anthropological and archeological information that exists regarding the Aztec Empire. As part of my studies I\u2019ve visited the Museo del Templo Mayor<\/a> (Museum of the Great Temple) in Mexico City, which houses a tremendous collection of art and ephemera by the Aztecs. <\/span><\/p>\n

I\u2019ve also spent time in Mexico City\u2019s Museo Nacional de Antropolog\u00eda (Natural History Museum), where you can view the massive Aztec Sun Stone\u201412 ft in diameter and weighing more than 20 tons. I\u2019ve lost count of the books I\u2019ve purchased on the art and savage civilization of the Azteca. <\/span><\/p>\n

You might think that Google\u2019s Gemini, with untold billions of dollars in its research and development departments, might surpass Mr. Vallen when it comes to knowledge concerning Mesoamerica. Think again. <\/span><\/p>\n

Don\u2019t accept a concept as fallacious as \u201cArtificial Intelligence.\u201d Remember… artificial means fake, contrived, false. The ancient Greeks had a mechanical device that lifted an actor through a trap door, to play a god onstage. They called the contraption, deus ex machina. In the present I\u2019m well aware of the machine, but do you know who is playing God? <\/span><\/p>\n

It\u2019s amazing how abruptly Gemini fell. The total capitalization of Google is $1.798 TRILLION<\/i>, making it the 6th most valuable company<\/i> in the world, still, no one saw this coming. Despite being programmed to codify \u201cdiversity, equity, and inclusion,\u201d Gemini generated black Nazis and Vikings from Africa, not to mention doing its best to rub-out digital whites. <\/span><\/p>\n

Thankfully, it looks like the audience has discovered the deus ex machina trap door. On Feb. 26, 2024, the simulacrum God lost $70 billion in market value<\/a> in a single trading day. Hopefully… there is no fix.<\/span><\/p>\n

Obviously, Google the tech giant has everything needed in terms of money and resources, but when you play God the cost is high.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

I am one of those artists sounding warnings about the negative impact Artificial Intelligence (AI) is having on the arts, from painting and drawing to photography, literature, musical composition and performance, as well as the cinematic arts. I was writing a critique of AI when I got word of Google\u2019s latest AI application. My treatise is temporarily delayed, but consider…<\/p>\n","protected":false},"author":3,"featured_media":17087,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_kadence_starter_templates_imported_post":false,"_kad_post_transparent":"default","_kad_post_title":"default","_kad_post_layout":"default","_kad_post_sidebar_id":"","_kad_post_content_style":"default","_kad_post_vertical_padding":"default","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"_kad_post_classname":"","wds_primary_category":0,"footnotes":""},"categories":[54,22],"tags":[],"class_list":["post-17068","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","category-general"],"acf":[],"_links":{"self":[{"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/posts\/17068","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/comments?post=17068"}],"version-history":[{"count":0,"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/posts\/17068\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/media\/17087"}],"wp:attachment":[{"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/media?parent=17068"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/categories?post=17068"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/art-for-a-change.com\/blog\/wp-json\/wp\/v2\/tags?post=17068"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}