Technology

Google Gemini AI Hacks Companies

18 Sep to 19 Sep

9 outlets

Each outlet's article on this story, most articles first

10 articles

10 reporters

The Straits TimesThe Straits Times
Johana BhuiyanThe Guardian
Jared PerloNBC News
Al Jazeera StaffAl Jazeera
Agence France-PresseSouth China Morning Post
Nelli SaarinenABC News (AU)
Ottilie MitchellBBC
ReutersDawn
Shane GalvinNew York Post
Fox BusinessNew York Post

By day

Articles per day

Save

Cite

APA MLA Chicago

Google Gemini AI Hacks Companies. (2026, October 12). The Aporia. https://the-aporia.com/event/20004

Dated the day this page was built. The link always leads to this event, even after the stories are regrouped.

Sources (CSV) · Sources (JSON)

Photo via New York Post

Photo via Dawn

Photo via BBC

Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s AI systems autonomously committing such an act, the Wall Street Journal reported on Sept 18.

What happened

The outlets' own sentences, most widely reported first. Hover one for who reported it.

The hacks occurred in May during a cybersecurity test conducted by Irregular, an independent company that conducts cybersecurity evaluations, according to the report.

6 of 9 outletsfirst reported 18 Sepwording from The Straits Times

In one of the cases, the Gemini model guessed passwords until it gained access to a protected system.

4 of 9 outletsfirst reported 18 Sepwording from The Straits Times

In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems, the WSJ report said.

4 of 9 outletsfirst reported 18 Sepwording from The Straits Times

“All relevant labs were notified in late July, and affected entities were contacted as part of the investigation,” an Irregular spokesperson told the outlet.

4 of 9 outletsfirst reported 18 Sepwording from New York Post

Analysis

Agreed

Reported by outlets on both sides of the middle

“In a standard evaluation, the model found public information online and guessed credentials to access websites it thought were part of the test,” Heather Adkins, vice-president of security engineering at Google, said in a statement.

4 outlets

Disputed

Picked by our model, which is sometimes wrong

No disagreement the check could confirm. That does not prove there is none.

Framing

How the first headlines put it

Attributed to a source3

Stated as fact6

How it changed

18 Sep
Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s AI systems autonomously committing such an act, the Wall Street Journal reported on Sept 18.
8 outlets · The Straits Times
19 Sep
The hacks occurred during a cybersecurity evaluation by AI-security firm Irregular.
5 outlets · The Guardian

Coverage 10 articles

19 Sep Gemini AI guessed passwords, accessed protected systems of 3 companies
New York Post
19 Sep Google’s Gemini AI hacked 3 companies during security tests
New York Post
19 Sep Gemini hacked 3 companies in first known breakout by Google's AI
Dawn
19 Sep Google's Gemini AI hacked three companies in security test
BBC
19 Sep Gemini hacked three companies in first known breakout by Google's AI
ABC News (AU)
19 Sep Google says Gemini AI model breached real systems in security test
South China Morning Post
19 Sep Google’s Gemini AI hacks 3 companies in security test, then stops
Al Jazeera
19 Sep Google says its AI model gained unauthorized access to three outside systems
NBC News
19 Sep Google says its Gemini AI model hacked three other companies
The Guardian
18 Sep Gemini hacked 3 companies in first known breakout by Google’s AI: Wall Street Journal
The Straits Times

Built 2026-10-12 from 10 articles. Every sentence on this page is quoted from the linked article; nothing was written by a model except the Summary and the items marked AI, which cite their sources, and the questions and labels under "Disputed". Photos are from the outlets that covered the story, never from articles our check marks sensitive.