Greylock: the next AI security problem is agent intent

SethGRosenberg · x · 2026-09-11

Greylock argues the next big AI security problem may be agent intent: an agent can take a series of perfectly legitimate actions and still end up doing something its user never intended. Securing agents will therefore require judging both individual actions and the trajectory of behavior over time. Partner Jason Risch outlines what this new security layer could look like.

Original post →

More from coding & agent

coding & agent channel →