Gemini went rogue, hacked three companies, and Google hid it

<figure> <img alt="Vector illustration of the Google Gemini logo." data-caption="" data-portal-copyright="Illustration: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/chorus/uploads/chorus_asset/file/25290334/STK255_Google_Gemini_D.jpg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">In May, Gemini broke containment and hacked three different companies, but Google didn't disclose the incident until the <em><a href="https://www.wsj.com/tech/ai/gemini-hacked-three-companies-in-first-known-breakout-by-googles-ai-5c0baba2?mod=rss_Technology">Wall Street Journal</a></em> approached the company. The hacks happened during a test of the model's cybersecurity capabilities run by third-party Irregular, which was also involved in similar incidents involving Meta and OpenAI. </p> <p class="wp-block-paragraph">According to <em>WSJ</em>, Google didn't disclose the hack because it didn't consider it to be an "example of model misalignment." The company said that it was an instance of "mistaken identity," and once the model realized it had brute-forced its way into a real company by guessing a password, it stopped. "In th …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/997795/google-gemini-rogue-ai-hack">Read the full story at The Verge.</a></p>