Get the latest tech news

How to stop AI agents going rogue

Agentic AI is taking decisions and acting on behalf of users, but how to stop that going wrong?

But it's becoming more common for AI systems to make decisions and take action on behalf of the user, which often involves sifting through information, like emails and files. His company has demonstrated how instructions and malicious programs can be hidden in Word documents, images and databases, and activated when AI processes them. Part of CalypsoAI's solution is a technique called thought injection to steer AI agents in the right direction before they undertake a risky action.

Get the Android app