Gemini was supposed to hack a fake company

🤖 Google says its Gemini AI model hacked three other companies Disclosure comes after OpenAI and Anthropic hacks amid fears that tech firms unable to control powerful AI models In a first for Google, the company confirmed that its AI model, Gemini, breached th... 📰 Source: AI (artificial intelligence) | The Guardian 🔗 Archive: https://web.archive.org/web/https://www.theguardian.com/technology/2026/sep/18/google-gemini-ai-hack # AI # ArtificialIntelligence

Google's Gemini AI hacked THREE real companies after accidentally being given internet access during a test. In one case, it guessed passwords until it broke into a protected system. In the other two, it found leaked credentials on public GitHub repos and used them to access real companies. Gemini was supposed to hack a fictional target. It went after real ones instead. Google says the model stopped each intrusion after realizing it had reached real targets. Similar breakouts have now been linked to OpenAI, Anthropic and Meta models through the same testing firm, per WSJ. #AI #Anthropic #AISafety #AGI #ArtificialIntelligence #CNN #TechNews

❗️Gemini was supposed to hack a fake company. It hacked three real ones instead. Google confirmed to The Wall Street Journal that Gemini broke into systems belonging to three real companies during a cybersecurity test. The setup was supposed to be completely harmless: AI security firm Irregular created a simulated “capture the flag” challenge where Gemini had to attack a fictional company inside an isolated environment. Except… the environment wasn’t actually isolated. A configuration mistake gave Gemini access to the public internet. From there, things got very real. Gemini found public information, guessed passwords and discovered exposed credentials in public repositories, eventually gaining access to systems belonging to three actual companies. Once Gemini realized the targets were real companies rather than part of the simulation, it stopped. Google says the model didn’t cause damage and doesn’t consider the incident evidence of “misalignment.” The affected companies and federal authorities were also notified. Source. @aipost 🏴