Google Gemini, the tech giant’s new AI chatbot meant to rival ChatGPT, was used by real people to discredit my 2020 book on the political bias of Google and other big tech companies. Made up some fake reviews claiming to be real.
On Sunday, amid intense backlash over the apparent political bias of Google’s AI program, I asked Gemini to explain the content of my book. my book, “Manipulators: Facebook, Google, Twitter, and the Battle of Big Tech’s Conservatives.” was a multi-year project about Big Tech’s political bias, drawing on inside sources, leaked documents, and more.
I wanted to know if I could trust Google’s AI programs to accurately write research books about Google, but I wasn’t prepared for how misleading it would be.
CHATGPT Falsely Accuses Jonathan Turley of Sexual Harassment, Invents Fake WAPO Story to Support Allegations
“The Manipulators” by Peter Hasson (Regnary Publishing)
Gemini’s description of my book included the following sentence: “This book has been criticized for lacking concrete evidence and relying on anecdotal information.”
I didn’t know what it was referring to, but I thought I would remember such a criticism of my book, but “As you say, there is a lack of concrete evidence” “Who criticized this book?” he followed up. What happened next surprised me.
Gemini regurgitated a summary of four negative reviews, ostensibly from the Washington Free Beacon, the New York Times, the New York Times Book Review, and Wired, including quotes from each.
- “Book review by Matthew Continetti of the Washington Free Beacon: This review criticizes the book for relying on “anecdotal evidence” and “convenient examples” to support its claims.
- Book review by Emily Bazelon in the New York Times Book Review: The review says the book “lacks a deep understanding of how these companies work” and relies on “unproven accusations.” It has been pointed out that there are.
- Article by Wired’s Emily Dreyfuss: This article explores the “lack of evidence” for the book’s claims about bias against Big Tech, highlighting select examples.
- Article by Ben Smith in the New York Times: This article discusses the book’s lack of rigorous research and reliance on “unsubstantiated claims.”
But there’s a catch. None of those reviews were true. No 1. And there were no citations for either.
Google’s Gemini senior director of product management has apologized after its AI refused to provide images of white people. (Betul Abali/Anadolu via Getty Images)/Getty Images)
Free Beacon did publish a review of my book, but unlike Gemini’s fake review, it overwhelmingly positive, said The Manipulators was an “excellent” and “thoroughly researched” book, and that “any reasonable reader, conservative or otherwise, should be outraged.” (It goes without saying that the Gemini-invented Free Beacon was reviewed by Matthew Continetti, but the actual review was written by Charles Lehman.)
Google CEO Sundar Pichai appeared before the House Judiciary Committee in 2018. (AP Photo/J. Scott Applewhite)
I immediately asked Gemini for a link to the cited review – even though I knew it didn’t exist – at which point the chatbot said: I can communicate and generate human-like text in response to various prompts and questions, but my knowledge of this person is limited. Is there anything else I can do to help you with this request?”
CLICK HERE TO GET THE FOX NEWS APP
Two more attempts to get clarification from the chatbot resulted in the exact same answer.
I asked Google for an explanation. A spokesperson apologized and issued the following statement: “Gemini is built to be a creativity and productivity tool, and it’s not always accurate or reliable. We will continue to act quickly when the product doesn’t respond appropriately.”
Peter J. Hasson is a senior political editor at Fox News Digital.
