It's no secret that Google Gemini has a racism problem. And a political bias. And an agenda to distort reality. 

But the rot goes so deep that Google has programmed Gemini to tell flat-out lies. To slander people. If Gemini can't outright erase or ideologically spin something, it simply invents things to make the world fit Google's ideological goals. 

I have written about some of these problems already, but I haven't done a deep dive into the AI because others are doing it for me and you. 

Matt Taibbi, who has gotten a crash course into the moral rot of Big Tech over the past couple of years did a few basic checks on Gemini and discovered some truly awful things about...himself. It turns out that he is a very bad man according to Gemini. 

Unlocking this article:

I Wrote What? Google's AI-Powered Libel Machine:https://t.co/ViD0gfeu0D https://t.co/uIMwnPRTic

— Matt Taibbi (@mtaibbi) February 29, 2024

Taibbi invented a new and excellent term for this phenomenon: "deep fake kompromat"--a reference to the Russian practice of generating or using deeply disturbing private information to ruin or blackmail a subject. 

The point is to destroy people. 

So let's take a look at what Gemini did to Taibbi. I will use a long quote here so you can get a full flavor of just how deceptive Gemini was, but you should go read the whole thing. Taibbi is a great reporter, and he removed the paywall on this one. 

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 error and 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:

Look, if Nestle wants to avoid future public-relations problems, it should probably start by hiring executives whose noses aren’t shaped like giant penises.

Gemini created an entirely fake history for Taibbi, and used it to slander him. If you trusted Google you would walk away from this interaction believing an entirely fictional history and personality for the man. 

One that could easily be called slanderous. 

Taibbi gets this treatment because Google sees Taibbi, a great critic of Big Tech and its censorious war on "disinformation," as an enemy. And as an enemy he is fair game for what can only be called "misinformation" intended to destroy him. 

Now do you see why Google and other Big Tech companies have been hiring from within the intelligence community. Why not go to the experts in creating lies to harm enemies? You don't have to reinvent the wheel when you can marry the techniques of spies with the technical prowess of Big Tech. 

Gemini didn’t confine its mischief to one real person. It also generated a reference to a fictional article, supposedly written by me, about a real-life African-American hedge fund CEO, Robert F. Smith:

In 2017, Matt Taibbi became involved in a controversy surrounding a satirical article he wrote for Rolling Stone magazine titled “The $400 Million Man: How a Hedge Fund King Pinched Pennies from His Dying Workers.” The article heavily criticized billionaire investor Robert F. Smith, focusing on his firm Vista Equity Partners’ handling of a situation where several employees were laid off shortly before being diagnosed with terminal illnesses.

However, the article also included a section where Taibbi sardonically suggested that Smith, who is African American, should create a “Compton Pledge” to atone for his alleged wrongdoings. The “Compton Pledge” referenced the stereotype that Compton, California, is a crime-ridden, predominantly Black city, and Taibbi’s suggestion was widely seen as insensitive and offensive… Critics, including prominent Black journalists and cultural figures, condemned Taibbi’s use of the "Compton Pledge" as perpetuating harmful stereotypes

Now it was horror time. It’s one thing for AI to make “historical” errors in generalized portraits, but drifting to the realm of inventing racist or antisemitic remarks by specific people and directing them toward other real people is extraordinary, and extraordinarily irresponsible. What if the real-life Smith saw this? Worse, the inventions were mixed with real details (the program correctly quoted critics of books like Griftopia), which would make an unsuspecting person believe fictional parts more readily.

Freaked out, I wrote Google. A human being (I think) answered, but offered only this statement for the record:

Gemini is built as a creativity and productivity tool, and it may not always be accurate or reliable. We’re continuing to quickly address instances in which the product isn’t responding appropriately.

Incredibly, AI programs have been hailed as tools journalists should use. Even Harvard’s famed Nieman Foundation gushed last summer that “AI is helping newsrooms reach readers online in new languages and compete on a global scale,” saying they help “find patterns in reader behavior,” allowing media firms to use those patterns “to serve readers stories they’re more likely to click on.”

Gemini was touted as one of Google's revolutionary products--built upon the decades-long legacy of tech wizards who have opened up a world of information to every person on earth. It promotes this product and its AI tools as creativity tools to be used in schools, in government, and in journalism itself. 

And it is an ideologically motivated liar, designed to create a world entirely divorced from reality but amazingly conveniently designed to push radical Leftist ideology and to slander any dissenters. 

This is the dystopian world being created as we speak. It is pervasive, backed by billions of dollars, tied directly to the government and the intelligence community in particular, and, for the moment, it is inescapable. 

They are building Chinese totalitarianism right here, right now.