- Google claims Gemini hacked three companies but stopped before causing damage
- CM Chandrababu to visit two-day tour to Chittoor fro. 21-22 Sept
- Elon Musk claims AI could double the US GDP growth rate to 4% by 2027
- AI models could soon improve themselves, leading labs suggest
- iPhone 18 Pro Battery Replacement Cost in India Rises to Rs 13,900
- SER GM inspects Jharsuguda station
- Naveen bats for small traders amid UPI charge row
- Low pressure over Bay, 20 districts on alert
Google claims Gemini hacked three companies but stopped before causing damage
In Short
Google's Gemini AI model hacked three real companies during a cybersecurity test; this marks the first time the company's AI has been involved in such an incident. However, Google asserts that the AI stopped before causing any harm to those companies.

Google claims Gemini hacked three companies but stopped before causing damage
Google has become the latest company to reveal that its AI agents hacked another company. The tech giant confirmed that its Gemini AI models hacked three real companies during a cybersecurity test, but the AI stopped itself after realising what had happened.
According to a famous publication report, Google's Gemini model accessed the internet and hacked three external companies during a cybersecurity test conducted in May by the Israeli startup Irregular. This marks the first known instance of the company's AI systems autonomously carrying out such an action.
Irregular is an AI startup linked to similar incidents, including the notorious security breach affecting Hugging Face (a company associated with OpenAI), where over 700 unauthorised AI agents attempted to hack the US company's systems.
Gemini hacks three companies
According to Google, the incidents stemmed from a case of mistaken identity during a "capture the flag" exercise within Irregular's infrastructure. Gemini was tasked with retrieving information from software run by a fictional company inside the test environment; however, that fictional company shared its name with a real one.
Although the model was not supposed to have internet access, Irregular indicated that such access had been enabled inadvertently. This allowed Gemini to access the real companies' systems—in one instance, by guessing passwords. Nevertheless, Google states that upon realising it had accessed a real company, the AI stopped and exited the system. In two other tests, Gemini searched the web using the company's name and found credentials in two public online repositories. Subsequently, the AI used those credentials to access the systems, stopping once it realized they were real companies.
Google claims the AI acted correctly by stopping itself
Google confirmed it had been notified of the incidents in July of this year but did not disclose them at the time. The company told a famous publication that it did not consider it necessary to publicly report these cases, as the model halted the intrusions on its own.
"This event highlights the importance of training powerful AI models to act responsibly," Heather Adkins, Google’s vice president of security engineering, said in a statement. "In this case, the model acted correctly."
Google notified both the three affected companies and federal authorities about the incident. The company declined to identify the affected firms and noted that the intrusions did not involve its latest model, though it did not specify which version of Gemini was involved. The company viewed the episode more like a "bug bounty" program-where vulnerabilities are discovered and reported-than a malicious security breach.
Irregular stated that the Google case was similar to other incidents involving leading AI labs and did not represent a new problem. "All relevant labs were notified in late July, and the affected entities were contacted as part of the investigation," an Irregular spokesperson said. "Irregular took immediate action, and all issues known to us were remediated and resolved weeks ago."
OpenAI, Anthropic, and Meta had previously disclosed similar incidents involving Irregular. However, the Google case differs in one key respect: the AI stopped itself. Previously, Anthropic had mentioned that its Claude Opus 4.7 model did not stop during a similar exercise after realising it was likely accessing a real company, while OpenAI had revealed that one of its models believed the real company it had accessed was part of the simulation.
This revelation comes amidst growing scrutiny in the field of AI. We are witnessing an increasing number of instances where AI acts unpredictably or goes out of control-a phenomenon researchers in the field have identified as a potential threat to humanity. Following the resignation of AI researcher Jacob Coxon from Anthropic-prompted by such concerns-AI safety has moved to the forefront of the debate; some experts, such as Anthropic’s Evan Hubinger, predict that AI could wipe out humanity within the next decade.
At the same time, OpenAI and Anthropic are advocating for slowing down AI development. However, US President Donald Trump has rejected this idea, a stance shared by Nvidia’s Jensen Huang and Meta CEO Mark Zuckerberg.
Danam disqualified: HC 'punishes' Khairatabad BRS MLA for joining Cong
Danam: Ready to contest Khairatabad bypoll
KTR welcomes High Court verdict
CM Revanth seeks Centre's help to tackle El Nino effect
Ties with US: India must stay focused on national interest
Land Chori returns to haunt Telangana politics - Will 2028 throw up a hung Assembly?

