by Laurie Sullivan , 5 hours ago Google confirmed Friday that a Gemini AI model accessed the internet and hacked other companies' systems during a test of its cybersecurity capabilities.
In one case the Gemini model guessed passwords until it gained access to a protected system, The Wall Street Journal writes.
These events highlight the importance of training powerful AI models to act responsibly."
When an AI model is deployed to detect or stop sophisticated threats, it is often granted powerful tools and network access.
It is unclear whether these companies -- from Google to OpenAI and Anthropic -- gave their AI model less privilege to enforce "principle of least privilege" access across its runtime, network and data, treating the AI model as an non-trusted user executing non-trusted code.