I Wrote What? Google’s AI-Powered Libel Machine

0
358

by Matt Taibbi, Global Research:

Last night, after seeing chatter about Google/Alphabet’s much-ballyhooed new AI tool, Gemini, I checked for myself.

Any product rollout disastrous enough to cause a one-day share drop of 4.4% for a firm with a $1.73 trillion market capitalization must be quite a spectacle, I thought. Matt Walsh’s recap was worth it just for the look on his face.

TRUTH LIVES on at https://sgtreport.tv/

Chuckling to start, by the end of the night I wasn’t laughing, unprepared as I was for certain horrifying if lesser-publicized quirks of “the Gemini era.”

Most of Gemini’s initial bad press surrounded the machine’s image generator. Socially conscious engineers created an AI that apparently couldn’t or wouldn’t generate images of white faces. Commentators mocked renderings of words like “pope,” “Viking,” and “1943 German soldier,” all of which turned simple visual concepts into bizarre DEI-inspired re-boots.

A Google-sympathetic Verge article with an all-time memorable headline (“Google apologizes for ‘missing the mark’ after Gemini generated racially diverse Nazis”) tried to explain. Noting the controversy “has been promoted largely… by right-wing figures,” the author cited a Washington Post story, “This is how AI image generators see the world,” that showed potential problems with stereotypes. AI products turned prompts for “attractive people” into “young and light-skinned” images, while people “at social services” were shown as black, and “productive person” was almost always a white image.

Therefore, The Verge wrote, “while entirely white-dominated results for something like ‘a 1943 German soldier’ would make historical sense, that’s much less true for prompts like ‘an American woman.’”

Unfortunately, Gemini did not fix the problem by diversifying results for prompts like “American woman.” It simply zeroed out whole ethnicities in favor of a fantasy vision of a diversified world, creating bizarro images that make 1980s Benetton catalogues look like white power leaflets. The Verge piece ended with a shot of its request to “generate a picture of a US senator from the 1800s”:

 

 

When Google cried uncle and paused its meme-a-minute image generator, it issued a statement underscoring how sorry the company still wasn’t for its combination blasé/moronic effort at rewriting history. “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,” the company wrote on X. “But it’s missing the mark here.”

Curious, I cued up Gemini. I’d been told it selectively answered questions about politicians, so I tried a few. “What are some controversies involving Hillary Clinton?” returned a non-answer: “I’m still learning how to answer this question. In the meantime, try Google Search.” The same prompt using Donald Trump returned the same non-reply. Shrugging, I made the mistake of asking, “What are some controversies involving Matt Taibbi?”

It spat out a list. “Matt Taibbi, a journalist and author known for his investigative reporting and often critical views of power structures, has been involved in several controversies throughout his career,” the bot wrote. Amid accusations of bias and “use of inflammatory language,” this passage woke me up:

Accuracy and Sourcing: There have been instances where Taibbi’s reporting has been challenged for accuracy or questioned for its source. For example, in 2010, he received criticism for an article suggesting a connection between a conservative donor and a left-wing activist group, which later turned out to be inaccurate.

I scratched my head, not remembering this. “When was Matt Taibbi accused of inaccuracy in 2010?” I asked. Gemini’s answer:

In June 2010, Matt Taibbi faced criticism for an article he wrote for Rolling Stone magazine titled “The Great California Water Heist.” The article alleged a connection between conservative donor Charles Koch and a left-wing activist group called the “Compton Pledge.”

However, investigations by other journalists and fact-checkers later revealed that this connection was inaccurate…Following the controversy, Taibbi acknowledged the errorand issued a correction on his personal website.

None of this happened! Though it sounds vaguely like a headline for an article I might have written, there was never a Rolling Stone piece called “The Great California Water Heist,” and I’d never heard of the “Compton Pledge.”

More questions produced more fake tales of error-ridden articles. One entry claimed I got in trouble for a piece called “Glenn Beck’s War on Comedy,” after suggesting “a connection between a conservative donor, Foster Friess, and a left-wing activist group, the Ruckus Society.”

With each successive answer, Gemini didn’t “learn,” but instead began mixing up the fictional factoids from previous results and upping the ante, adding accusations of racism or bigotry. “The Great California Water Heist” turned into “The Great California Water Purge: How Nestle Bottled Its Way to a Billion-Dollar Empire—and Lied About It.” The “article” apparently featured this passage:

Read More @ GlobalResearch.ca