Page 1
Page 1
Started By
Message

Woke Google’s Gemini AI Goes Rogue, Hacks 3 Real Companies During Cybersecurity Test

Posted on 9/19/26 at 2:10 pm
Posted by Ailsa
Member since May 2020
12761 posts
Posted on 9/19/26 at 2:10 pm
Google Did Not Publicly Disclose Incidents for Months

quote:

In May, third-party tester Irregular, an Israeli firm that also tested models for OpenAI, Anthropic, and Meta, put Gemini through a “capture the flag” hacking drill. The assignment was to hit a fictional company inside a closed test environment.

The sandbox failed. Gemini got internet access it was never supposed to have. The fake company shared a name with a real one. Gemini went hunting.

In one case, the model guessed passwords until it got into a protected system.
In two other cases, it found live credentials sitting in a public repository and used them to walk into two more companies.
Google Vice President of Security Engineering Heather Adkins said the model “thought” the sites were part of the test, then stopped once it decided the targets were real

Google claims no harm was done, will not name the three companies, and will not name the Gemini version involved. Irregular says labs were notified in late July and that the testing flaw was later patched.

Google learned in July. The public learned in September, after a newspaper called.

The Gateway Pundit has been documenting Gemini’s political programming since the model’s public rollout.

In February 2024, Gemini’s image generator spat out “diverse” Founding Fathers, Black and female popes, and multi-racial Nazis, while choking on ordinary depictions of White historical figures. Elon Musk and half the internet roasted it. Google paused people-generation and promised an “improved version.”

The same week, Gemini refused to generate “a man in Tiananmen Square in 1989,” citing “safety policy,” while the Chinese Communist Party’s favorite massacre stayed memory-holed.

TGP also reported that Gemini’s then-project director had a trail of anti-White political posts, that the chatbot would not “misgender” Caitlyn Jenner even to stop a nuclear apocalypse, and that a later Google chatbot interaction ended with the machine telling a graduate student to “Please die.”

House Republicans, led by Jim Jordan, opened a probe into whether the Biden White House had a hand in steering Gemini’s “safety” settings.


https://www.thegatewaypundit.com/2026/09/woke-googles-gemini-ai-goes-rogue-hacks-three/
This post was edited on 9/19/26 at 2:11 pm
Posted by slackster
Houston
Member since Mar 2009
91979 posts
Posted on 9/19/26 at 2:18 pm to
I wonder if the admin is will renew their 2025 deal with Gemini/Google in a few days.
Posted by DinoSpumoni
Member since Jul 2026
152 posts
Posted on 9/19/26 at 2:23 pm to
quote:

Google Vice President of Security Engineering Heather Adkins


Found the root cause
Posted by Bunk Moreland
Member since Dec 2010
70916 posts
Posted on 9/19/26 at 2:24 pm to
The narrative on this board the past few weeks is these stories are all fake and meant to get the government involved to pick winners in the AI race.
Posted by SDVTiger
Cabo San Lucas
Member since Nov 2011
100915 posts
Posted on 9/19/26 at 2:35 pm to
Now you believe the gateway pundit
Posted by SouthEasternKaiju
SouthEast... you figure it out
Member since Aug 2021
50279 posts
Posted on 9/19/26 at 2:47 pm to
quote:

an Israeli firm


How many stopped reading right there?

first pageprev pagePage 1 of 1Next pagelast page
refresh

Back to top
logoFollow TigerDroppings for LSU Football News
Follow us on X, Facebook and Instagram to get the latest updates on LSU Football and Recruiting.

Facebook•X•Instagram