Microsoft’s security chief says frontier AI models cannot be trusted and the company just launched Guardian Agents to police agents and prevent them going rogue.
This is coming from a company selling AI agents.
They’re now selling protection from the AI agents they and others sell you doing crimes
TechCrunchMicrosoft says AI agents are like insider threats as 'frontier models can't be trusted' | TechCrunchMicrosoft wants enterprises to closely watch the agents that employees use with systems not controlled by AI labs like OpenAI and Anthropic.