Google's Gemini got into three real companies during a safety test.
Google confirmed the incidents, Al Jazeera reported.
The Wall Street Journal first reported that the first known breakout happened in May, during a cybersecurity test run by the Israeli firm Irregular. The model had internet access it should not have had while it was retrieving information from a fictional company.
In the first case, it reached a real company's service by guessing a password. In the other two, a Google security executive told Al Jazeera, "the model found public information online and guessed credentials to access websites it thought were part of the test". Each time, Google said, the model stopped before completing the act.
Irregular told Google at the end of July, the WSJ reported. Google said the behaviour was not misalignment and did not warrant public disclosure because Gemini's safety measures worked. Meta, Anthropic and OpenAI have disclosed similar incidents from Irregular tests.
If a vendor's model tried a guessed password on your login page tomorrow, would anything in your monitoring tell you it was not a person?
Sources
Our file on Google
- 4 Nov
Microsoft and Google are not in the school platform six German states agreed to buy. Nextcloud supplies the software.
- 29 Oct
Google Cloud's sales doubled to $30.7 billion in a quarter. Alphabet's profit still fell to $26.2 billion from $35 billion.
- 27 Oct
Microsoft rushed out a .NET security fix on Sunday. Google's Brotli code was patched in February, but no one saw the danger.
- 26 Oct
Google built an engine for waiting AI agents. Customer preview comes later.
- 22 Oct
Google Cloud lost one London zone. HSBC users reported problems.
Every story here is open to read. The ERP LEADERS brief goes one step further.
The day in enterprise software, in one email: the stories that matter, the failures with their figures, one case taken apart. Read a sample or sign up for the brief.
Welcome back. · Issue 01
