Reaction
Project Perception expands to assess agent risk and adapt permissions
Satya Nadella says the expansion follows a principle of treating models as insider risks, with security controls outside them.
TLDR
Satya Nadella announced new Project Perception capabilities intended to continuously assess agent risk, adapt permissions and contain threats. He says the expansion puts into practice his call to treat models as insider risks, with security controls outside the models themselves.
Combined views
—
1 Source, first seen ago
