Microsoft expands Project Perception agent security capabilities
AI summary
Satya Nadella said he previously wrote an article arguing for treating models as an internal risk and placing security controls outside the model; today Microsoft puts this principle into practice by expanding Project Perception, adding capabilities to continuously assess agent risk, adaptively adjust permissions, and contain threats.
Body
I recently wrote about why we need to treat models as insider risks, with security controls sitting outside the model itself.
Today, we're putting that principle into practice by expanding Project Perception with new capabilities to help continuously assess agent risk, adapt permissions, and contain threats. https://t.co/ec3Z2B260G