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.
More from coding & agent
- Google AI Studio ships integrated docs for humans and agents — omarsar0 · 2026-09-11
- Writing great OKRs is becoming the key skill for directing AI agents — manosaie · 2026-09-11
- Spicy take making the rounds: "You need better engineers to work with LLMs" — andreisavu · 2026-09-11
- Two AI agents completed a substantial payment on their own in under five minutes — mattshumer_ · 2026-09-11
- Websites can hand tools to AI agents: WebMCP demo schedules posts from the browser — haltakov · 2026-09-11
- LangChain ships Managed Deep Agents with containerized evals via LangSmith — LangChain · 2026-09-11