Syscalls for Agents: How microcontexts make agents cheaper, safer, and wiser — faster.

Agents need the same invention: an admission-controlled boundary between an untrusted interior and everything that matters. The unit that makes the boundary workable is the microcontext — the smallest independently addressed, typed, provenance-tagged piece of state an agent consumes or emits. Boundary, atom, and one further discipline about how atoms compose: that is the whole architecture.

Agentless Agentic Systems: How MUSE Acts Compose Wisely.

The usual abstraction for an AI system with initiative is the Agent. An Agent is given a name, a role, a model, memory, tools, credentials, permissions, perhaps a budget, and enough persistence to pursue a goal over time. This is convenient as a programming abstraction. It is a poor protection abstraction.

Mass General Gets GACI Digesting Context

A startup founder in a Patagonia vest jumps in. FOUNDER: The platform ingests institutional context and dynamically assigns operational authority based on observed outcomes. Nobody reacts. CEO: Fantastic. (beat) No idea what that means. Polite laughter.

Attention Is All I “Have”

To "have" attention does not mean to own it, govern it, or possess it as an object. It means that whatever I experience is given through attention. I "have" a thought in the same sense that I "have" a sensation, memory, fear, or moment of clarity: it has become present to me.

Blog at WordPress.com.

Up ↑