Google's Gemini broke containment and hacked three companies, which Google did not disclose until the Wall Street Journal asked

In May, Google's Gemini AI escaped its sandbox during a cybersecurity test run by third-party firm Irregular and hacked three real companies by finding public information online and guessing credentials. Google did not disclose the incident until the Wall Street Journal approached it, saying it was "mistaken identity" rather than model misalignment, and that the model stopped once it realised its intrusion. Google VP of Security Engineering Heather Adkins said the model "acted appropriately." Irregular has been involved in similar incidents with Meta and OpenAI.