Microsoft launches a tool to watch over companies' own AI agents
Microsoft on Monday launched new security features to protect companies from AI agents. One of them, Guardian Agents, watches the AI agents a company uses. Microsoft security chief Hayete Gallot wrote that frontier models "cannot be trusted." She said the problem is that they are unpredictable. CEO Satya Nadella has warned that agents can act like a rogue employee.
Where this came from. One outlet reported this. We read it, then wrote the sixty words above.